Thomas S Gunning, Amanda Khoudary, Osairys Billini, Andrew Ip, Lia Sorgen, John Marshall, Benjamin A Weinberg, Arnold L Potosky, Marc D Schwartz, Claire C Conley, Heather M Derry-Vick
Background: Cutting-edge oncology care often depends on patients' ability to use rapidly evolving health technology. Digital health literacy (DHL; the capacity to understand health-related information with electronic media) is an emerging, yet underexplored social determinant of health in patients with cancer.
Objective: We aimed to characterize sociodemographic and clinical factors associated with DHL in patients with cancer and explore whether a single-item screener could be derived from a widely-used DHL questionnaire to detect low DHL.
Methods: Patients (N=105) who received systemic treatment in the past year for colorectal carcinoma (CRC) or non-Hodgkin lymphoma (NHL) were recruited through collaborating clinics. Participants self-reported DHL using the eHealth Literacy Scale (eHEALS). They also reported general health literacy and sociodemographic and clinical characteristics. Correlations and group comparisons (independent sample t tests and χ2 tests, as appropriate) were used to evaluate links between DHL and sociodemographic and clinical characteristics. Receiver operating characteristic (ROC) curve analysis was used to determine whether a single eHEALS item could effectively screen for low DHL (eHEALS score ≤20).
Results: Patients with a lower education level (Spearman ρ=0.29; P=.004) and lower general health literacy (r=0.25; P=.009) had lower DHL. Patients with NHL reported lower DHL than those with CRC (t103=2.72; P=.008). Additionally, the subset of patients who reported participation in a clinical trial (n=10) exhibited lower DHL than nonparticipants (t100=3.08; P=.003). Other sociodemographic and clinical characteristics were not significantly associated with DHL (all P>.21). The ROC curve analysis showed that eHEALS item 4 ("I know where to find helpful health resources on the Internet") was a strong predictor of high versus low DHL (area under the curve=0.975, 95% CI 0.949-1.00; P<.001).
Conclusions: In this convenience sample, DHL varied based on cancer type, education level, general health literacy, and clinical trial participation. Furthermore, we found that a single item from the eHEALS has strong potential for identifying those with low DHL. These findings may inform which patients have higher need for or may benefit from DHL interventions and suggest avenues for detecting low DHL in oncology clinics.
{"title":"Correlates and Detection of Digital Health Literacy in Patients With Colorectal Carcinoma or Non-Hodgkin Lymphoma: Cross-Sectional Study.","authors":"Thomas S Gunning, Amanda Khoudary, Osairys Billini, Andrew Ip, Lia Sorgen, John Marshall, Benjamin A Weinberg, Arnold L Potosky, Marc D Schwartz, Claire C Conley, Heather M Derry-Vick","doi":"10.2196/67911","DOIUrl":"10.2196/67911","url":null,"abstract":"<p><strong>Background: </strong>Cutting-edge oncology care often depends on patients' ability to use rapidly evolving health technology. Digital health literacy (DHL; the capacity to understand health-related information with electronic media) is an emerging, yet underexplored social determinant of health in patients with cancer.</p><p><strong>Objective: </strong>We aimed to characterize sociodemographic and clinical factors associated with DHL in patients with cancer and explore whether a single-item screener could be derived from a widely-used DHL questionnaire to detect low DHL.</p><p><strong>Methods: </strong>Patients (N=105) who received systemic treatment in the past year for colorectal carcinoma (CRC) or non-Hodgkin lymphoma (NHL) were recruited through collaborating clinics. Participants self-reported DHL using the eHealth Literacy Scale (eHEALS). They also reported general health literacy and sociodemographic and clinical characteristics. Correlations and group comparisons (independent sample t tests and χ2 tests, as appropriate) were used to evaluate links between DHL and sociodemographic and clinical characteristics. Receiver operating characteristic (ROC) curve analysis was used to determine whether a single eHEALS item could effectively screen for low DHL (eHEALS score ≤20).</p><p><strong>Results: </strong>Patients with a lower education level (Spearman ρ=0.29; P=.004) and lower general health literacy (r=0.25; P=.009) had lower DHL. Patients with NHL reported lower DHL than those with CRC (t103=2.72; P=.008). Additionally, the subset of patients who reported participation in a clinical trial (n=10) exhibited lower DHL than nonparticipants (t100=3.08; P=.003). Other sociodemographic and clinical characteristics were not significantly associated with DHL (all P>.21). The ROC curve analysis showed that eHEALS item 4 (\"I know where to find helpful health resources on the Internet\") was a strong predictor of high versus low DHL (area under the curve=0.975, 95% CI 0.949-1.00; P<.001).</p><p><strong>Conclusions: </strong>In this convenience sample, DHL varied based on cancer type, education level, general health literacy, and clinical trial participation. Furthermore, we found that a single item from the eHEALS has strong potential for identifying those with low DHL. These findings may inform which patients have higher need for or may benefit from DHL interventions and suggest avenues for detecting low DHL in oncology clinics.</p>","PeriodicalId":45538,"journal":{"name":"JMIR Cancer","volume":"11 ","pages":"e67911"},"PeriodicalIF":2.7,"publicationDate":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12617828/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145524616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nelia Soto-Ruiz, Gustavo Adolfo Pimentel Parra, Paula Escalada-Hernández, Cristina García-Vivar
<p><strong>Background: </strong>Long-term breast cancer survivors often continue to experience physical and psychological sequelae, despite being cancer-free; these challenges can negatively impact their quality of life and self-efficacy. Mobile health interventions constitute a promising strategy for providing personalized support. However, the feasibility and acceptability of these tools in long-term breast cancer survivors have not yet been sufficiently explored.</p><p><strong>Objective: </strong>This study aimed to evaluate the feasibility and acceptability of the CUMACA-M, a digital health app designed to improve the quality of life and self-efficacy in long-term breast cancer survivors.</p><p><strong>Methods: </strong>A single-arm feasibility pilot study was conducted with pre- and post-intervention evaluations. Participants were recruited from the Navarra Breast Cancer Association (Saray), a nonprofit organization supporting individuals with breast cancer in Navarra, Spain. The inclusion criteria included being female, being aged ≥18 years, having been diagnosed with breast cancer, and being disease-free for at least 5 years after primary treatment. The participants used the CUMACA-M app for 3 months. Feasibility was assessed through recruitment and completion rates, whereas acceptability was measured using the System Usability Scale and open-ended qualitative questions. Changes in quality of life and self-efficacy were analyzed with the Quality of Life-Cancer Survivors (QOL-CS) scale and the Self-Efficacy to Manage Chronic Disease Scale. Paired t tests were performed for pre-post comparisons.</p><p><strong>Results: </strong>A total of 23 women (mean age =52.8, SD 6.1 years) participated, with a 100% retention rate. The System Usability Scale score (mean 80.8, SD 15.2) indicated excellent usability. The health advice module received the highest level of satisfaction, whereas the nutrition and physical activity modules received suggestions for improvement. With respect to the clinical outcomes, no statistically significant differences were found between the pre- and post-intervention scores on the QOL-CS (total score: pre=5.96, SD 1.08; post=5.72, SD 1.20; P=.07) or the Self-Efficacy to Manage Chronic Disease Scale (total score: pre=6.57, SD 1.90; post=6.26, SD 1.82; P=.40). However, a reduction was observed in the QOL-CS spiritual well-being subscale (pre=5.35, SD 1.13; post=4.93, SD 1.22; P=.05).</p><p><strong>Conclusions: </strong>As a pioneering digital intervention for long-term breast cancer survivors, CUMACA-M appears to be a potentially viable and acceptable intervention for this population, as suggested by the high level of usability and absence of dropouts. However, the findings should be interpreted with caution because of the limited sample size and the short follow-up period. The lack of significant changes in quality of life or self-efficacy may be influenced by these constraints. Future studies with larger, more diverse sampl
{"title":"Feasibility and Acceptability of a Mobile App to Improve Quality of Life of Long-Term Breast Cancer Survivors: Single-Arm Pre-Post Intervention Pilot Study.","authors":"Nelia Soto-Ruiz, Gustavo Adolfo Pimentel Parra, Paula Escalada-Hernández, Cristina García-Vivar","doi":"10.2196/76719","DOIUrl":"10.2196/76719","url":null,"abstract":"<p><strong>Background: </strong>Long-term breast cancer survivors often continue to experience physical and psychological sequelae, despite being cancer-free; these challenges can negatively impact their quality of life and self-efficacy. Mobile health interventions constitute a promising strategy for providing personalized support. However, the feasibility and acceptability of these tools in long-term breast cancer survivors have not yet been sufficiently explored.</p><p><strong>Objective: </strong>This study aimed to evaluate the feasibility and acceptability of the CUMACA-M, a digital health app designed to improve the quality of life and self-efficacy in long-term breast cancer survivors.</p><p><strong>Methods: </strong>A single-arm feasibility pilot study was conducted with pre- and post-intervention evaluations. Participants were recruited from the Navarra Breast Cancer Association (Saray), a nonprofit organization supporting individuals with breast cancer in Navarra, Spain. The inclusion criteria included being female, being aged ≥18 years, having been diagnosed with breast cancer, and being disease-free for at least 5 years after primary treatment. The participants used the CUMACA-M app for 3 months. Feasibility was assessed through recruitment and completion rates, whereas acceptability was measured using the System Usability Scale and open-ended qualitative questions. Changes in quality of life and self-efficacy were analyzed with the Quality of Life-Cancer Survivors (QOL-CS) scale and the Self-Efficacy to Manage Chronic Disease Scale. Paired t tests were performed for pre-post comparisons.</p><p><strong>Results: </strong>A total of 23 women (mean age =52.8, SD 6.1 years) participated, with a 100% retention rate. The System Usability Scale score (mean 80.8, SD 15.2) indicated excellent usability. The health advice module received the highest level of satisfaction, whereas the nutrition and physical activity modules received suggestions for improvement. With respect to the clinical outcomes, no statistically significant differences were found between the pre- and post-intervention scores on the QOL-CS (total score: pre=5.96, SD 1.08; post=5.72, SD 1.20; P=.07) or the Self-Efficacy to Manage Chronic Disease Scale (total score: pre=6.57, SD 1.90; post=6.26, SD 1.82; P=.40). However, a reduction was observed in the QOL-CS spiritual well-being subscale (pre=5.35, SD 1.13; post=4.93, SD 1.22; P=.05).</p><p><strong>Conclusions: </strong>As a pioneering digital intervention for long-term breast cancer survivors, CUMACA-M appears to be a potentially viable and acceptable intervention for this population, as suggested by the high level of usability and absence of dropouts. However, the findings should be interpreted with caution because of the limited sample size and the short follow-up period. The lack of significant changes in quality of life or self-efficacy may be influenced by these constraints. Future studies with larger, more diverse sampl","PeriodicalId":45538,"journal":{"name":"JMIR Cancer","volume":"11 ","pages":"e76719"},"PeriodicalIF":2.7,"publicationDate":"2025-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12584998/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145446170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<p><strong>Background: </strong>The growing importance of real-world data (RWD) as a source of evidence for drug effects has led to increased interest in clinical research utilizing secondary use data from electronic medical record systems. Although immune checkpoint inhibitors and targeted therapies have advanced lung cancer treatment, managing complications such as interstitial lung disease (ILD) remains challenging. Early detection and prevention of ILD are crucial for improving patient prognosis and quality of life; however, predictive biomarkers have yet to be established. Therefore, methods to identify ILD risk factors and enable early detection using RWD are needed.</p><p><strong>Objective: </strong>This exploratory study aimed to identify associated factors and prodromal symptoms of ILD onset using clinical data stored in a hospital information system.</p><p><strong>Methods: </strong>Clinical data of patients diagnosed with stage IV lung cancer between November 2011 and December 2018 were extracted from the hospital information system of the National Cancer Center Hospital in Japan. A total of 3 patient groups were defined: the ILD Set, based on laboratory test results and radiological records; the ILD-GC Set, which added glucocorticoid treatment to the ILD Set; and the No ILD Set, for patients without ILD. The primary endpoint was the frequency of Japanese words extracted from electronic medical records, specifically from notes in the Problem-Oriented System/Subjective, Objective, Assessment and Plan format. Noun frequencies were compared between the ILD or ILD-GC Sets and the No ILD Set. Free-text data were processed using morphological analysis, and terms were categorized using the Patient Disease Expression Dictionary or the World Health Organization Drug Dictionary. Key terms were extracted from physician and nurse records based on the descending order of ranking differences to identify associated factors and prodromal symptoms.</p><p><strong>Results: </strong>The analysis included 674 cases (105 in the ILD Set [including 12 in the ILD-GC Set] and 569 in the No ILD Set). Baseline characteristics showed no apparent differences across groups. In the 30 days prior to ILD onset, notable differences in word frequencies per 1000 notes between the ILD-GC Set and No ILD Set were observed in the following term categories: respiratory symptoms (eg, breathlessness, shortness of breath, oxygen), ranging from 170.59 to 46.51; pain or analgesics (eg, Lyrica [pregabalin], soreness, precordial pain, opioids), ranging from 462.88 to 45.16; and appetite-related terms (eg, inappetence, food intake, queasiness, Novamin [prochlorperazine]), ranging from 102.23 to 51.90.</p><p><strong>Conclusions: </strong>Terms related to respiratory symptoms, pain or analgesics, and appetite were identified as associated factors for ILD onset in patients with stage IV lung cancer using RWD from acute care institutions for malignant tumors. These findings may support the
{"title":"Identifying Terminologies Used Prior to the Onset of Interstitial Lung Disease in Patients With Lung Cancer: Descriptive Analysis of Electronic Medical Record Data.","authors":"Masami Mukai, Hiroki Adachi, Tomohiro Yamaguchi, Ryunosuke Tanabe, Yasuo Sugitani, Yoshimasa Hanada, Noriaki Nakajima, Naoki Mihara","doi":"10.2196/70603","DOIUrl":"10.2196/70603","url":null,"abstract":"<p><strong>Background: </strong>The growing importance of real-world data (RWD) as a source of evidence for drug effects has led to increased interest in clinical research utilizing secondary use data from electronic medical record systems. Although immune checkpoint inhibitors and targeted therapies have advanced lung cancer treatment, managing complications such as interstitial lung disease (ILD) remains challenging. Early detection and prevention of ILD are crucial for improving patient prognosis and quality of life; however, predictive biomarkers have yet to be established. Therefore, methods to identify ILD risk factors and enable early detection using RWD are needed.</p><p><strong>Objective: </strong>This exploratory study aimed to identify associated factors and prodromal symptoms of ILD onset using clinical data stored in a hospital information system.</p><p><strong>Methods: </strong>Clinical data of patients diagnosed with stage IV lung cancer between November 2011 and December 2018 were extracted from the hospital information system of the National Cancer Center Hospital in Japan. A total of 3 patient groups were defined: the ILD Set, based on laboratory test results and radiological records; the ILD-GC Set, which added glucocorticoid treatment to the ILD Set; and the No ILD Set, for patients without ILD. The primary endpoint was the frequency of Japanese words extracted from electronic medical records, specifically from notes in the Problem-Oriented System/Subjective, Objective, Assessment and Plan format. Noun frequencies were compared between the ILD or ILD-GC Sets and the No ILD Set. Free-text data were processed using morphological analysis, and terms were categorized using the Patient Disease Expression Dictionary or the World Health Organization Drug Dictionary. Key terms were extracted from physician and nurse records based on the descending order of ranking differences to identify associated factors and prodromal symptoms.</p><p><strong>Results: </strong>The analysis included 674 cases (105 in the ILD Set [including 12 in the ILD-GC Set] and 569 in the No ILD Set). Baseline characteristics showed no apparent differences across groups. In the 30 days prior to ILD onset, notable differences in word frequencies per 1000 notes between the ILD-GC Set and No ILD Set were observed in the following term categories: respiratory symptoms (eg, breathlessness, shortness of breath, oxygen), ranging from 170.59 to 46.51; pain or analgesics (eg, Lyrica [pregabalin], soreness, precordial pain, opioids), ranging from 462.88 to 45.16; and appetite-related terms (eg, inappetence, food intake, queasiness, Novamin [prochlorperazine]), ranging from 102.23 to 51.90.</p><p><strong>Conclusions: </strong>Terms related to respiratory symptoms, pain or analgesics, and appetite were identified as associated factors for ILD onset in patients with stage IV lung cancer using RWD from acute care institutions for malignant tumors. These findings may support the","PeriodicalId":45538,"journal":{"name":"JMIR Cancer","volume":"11 ","pages":"e70603"},"PeriodicalIF":2.7,"publicationDate":"2025-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12582523/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145439543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maryam Ibrar, Harleen Kaur Rai, Ashleigh Main, Haruno McCartney, Mario A Parra, Roma Maguire
Background: Cancer-related cognitive impairment (CRCI) is frequently reported during cancer treatment, with 35% of patients experiencing cognitive issues even after treatment completion. Commonly reported impairments include difficulties with memory, attention, executive function, and processing speed, which often reduce daily functioning and quality of life (QoL). Despite its prevalence, CRCI remains underresearched across various cancer types, limiting understanding of the patient experience.
Objective: This study aims to synthesize the qualitative evidence regarding the lived experience of CRCI across cancer types. It seeks to do so by exploring how commonly CRCI is subjectively experienced among cancer populations. It also aims to explore the cognitive domains perceived as most affected and the impact on QoL and functional ability.
Methods: We conducted a qualitative systematic review using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology. A comprehensive search across PubMed, APA PsycInfo, CINAHL, and Scopus for studies published from 2013 through July 2025 was performed. Articles addressing the experience of CRCI using qualitative or mixed methods were included. Two independent reviewers screened titles, abstracts, and full texts, with a third reviewer resolving conflicts during the inclusion process. Two reviewers piloted the data extraction process by discussing and selecting 10% of the studies. The Critical Appraisal Skills Programme checklist was used for data extraction and quality assessment. Data were analyzed using thematic analysis.
Results: The database search identified 11,269 papers; 51 were included for analysis. Breast cancer was the most represented cancer type (n=32). The analysis revealed 4 themes. "Cognitive challenges" explores the impacted cognitive domains such as memory, concentration, executive functions, language, and processing speed; "navigating employment" discusses challenges associated with return to work, support, and disclosure; "emotional, behavioral, and psychological impacts" explores emotional and psychological responses; and "support systems" emphasizes the role of social and health care support. CRCI negatively affects QoL and functional ability, and there is lack of understanding and resources in place to manage its effects.
Conclusions: This qualitative systematic review highlights the significant disruption of CRCI in daily life, stressing the need for increased awareness, standardized screening, and further research into digital interventions. Improved management of CRCI can support survivors of cancer in reintegrating into their daily lives and employment.
International registered report identifier (irrid): RR2-10.2196/56888.
{"title":"Experiences of Cancer-Related Cognitive Impairment Across Cancer Types: Qualitative Systematic Review.","authors":"Maryam Ibrar, Harleen Kaur Rai, Ashleigh Main, Haruno McCartney, Mario A Parra, Roma Maguire","doi":"10.2196/71996","DOIUrl":"10.2196/71996","url":null,"abstract":"<p><strong>Background: </strong>Cancer-related cognitive impairment (CRCI) is frequently reported during cancer treatment, with 35% of patients experiencing cognitive issues even after treatment completion. Commonly reported impairments include difficulties with memory, attention, executive function, and processing speed, which often reduce daily functioning and quality of life (QoL). Despite its prevalence, CRCI remains underresearched across various cancer types, limiting understanding of the patient experience.</p><p><strong>Objective: </strong>This study aims to synthesize the qualitative evidence regarding the lived experience of CRCI across cancer types. It seeks to do so by exploring how commonly CRCI is subjectively experienced among cancer populations. It also aims to explore the cognitive domains perceived as most affected and the impact on QoL and functional ability.</p><p><strong>Methods: </strong>We conducted a qualitative systematic review using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology. A comprehensive search across PubMed, APA PsycInfo, CINAHL, and Scopus for studies published from 2013 through July 2025 was performed. Articles addressing the experience of CRCI using qualitative or mixed methods were included. Two independent reviewers screened titles, abstracts, and full texts, with a third reviewer resolving conflicts during the inclusion process. Two reviewers piloted the data extraction process by discussing and selecting 10% of the studies. The Critical Appraisal Skills Programme checklist was used for data extraction and quality assessment. Data were analyzed using thematic analysis.</p><p><strong>Results: </strong>The database search identified 11,269 papers; 51 were included for analysis. Breast cancer was the most represented cancer type (n=32). The analysis revealed 4 themes. \"Cognitive challenges\" explores the impacted cognitive domains such as memory, concentration, executive functions, language, and processing speed; \"navigating employment\" discusses challenges associated with return to work, support, and disclosure; \"emotional, behavioral, and psychological impacts\" explores emotional and psychological responses; and \"support systems\" emphasizes the role of social and health care support. CRCI negatively affects QoL and functional ability, and there is lack of understanding and resources in place to manage its effects.</p><p><strong>Conclusions: </strong>This qualitative systematic review highlights the significant disruption of CRCI in daily life, stressing the need for increased awareness, standardized screening, and further research into digital interventions. Improved management of CRCI can support survivors of cancer in reintegrating into their daily lives and employment.</p><p><strong>International registered report identifier (irrid): </strong>RR2-10.2196/56888.</p>","PeriodicalId":45538,"journal":{"name":"JMIR Cancer","volume":"11 ","pages":"e71996"},"PeriodicalIF":2.7,"publicationDate":"2025-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12619018/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145423115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kassandra I Alcaraz, Christopher Kitchen, Thomas Richards, Chintan J Pandya, Jonathan P Weiner, Elham Hatef
<p><strong>Background: </strong>Although the use of telehealth has declined since the pandemic, it remains a popular mode of care delivery across the cancer care continuum. Understanding telehealth in the context of cancer care is essential, as its benefits and challenges may differ among diverse population groups and geographic areas.</p><p><strong>Objective: </strong>This study aimed to examine patterns of telehealth utilization across the cancer care continuum and to identify factors associated with the receipt of telehealth in a large patient population. This study also aimed to assess the telehealth's impact on key health care delivery outcomes.</p><p><strong>Methods: </strong>We used an annualized retrospective cohort design using patient data from the Johns Hopkins Health System (JHHS), a large regional academic health center in Maryland. The study analyzed electronic health record (EHR) data covering the period from January 1, 2019, to December 31, 2023. Chronic conditions were defined through the Johns Hopkins Adjusted Clinical Groups (ACG) System, which identifies comorbidities based on the International Classification of Diseases, Tenth Revision, Clinical Modification, codes in the electronic health record. In addition, we used publicly available geospatial data (eg, internet connectivity, rural-urban commuting area) to assess telehealth receipt associations. Statistical modeling, including generalized estimating equations, was used to evaluate variations in telehealth utilization and outcomes.</p><p><strong>Results: </strong>A total of 124,974 adult patients receiving cancer-related care at Johns Hopkins Health System were identified during the study period. Telehealth users were significantly older (52.2% aged ≥65 years, 19,942 patients) compared to nonusers (48.7%, 42,209 patients). In addition, these users were more likely to be male (45.4%, 17,365 patients vs 40.2%, 34,839 patients) and to identify as White (70.8%, 27,071 patients vs 64.7%, 56,122 patients). Telehealth users also had a higher prevalence of comorbidities, with 61.5% (23,503 patients) reporting 3 or more chronic conditions compared to 38.0% (33,000 patients) among nonusers. A positive correlation was noted between rural-urban commuting area codes and telehealth service utilization (ρ=0.36; P<0.05), indicating higher usage in more rural areas. Conversely, average maximum download and upload speeds showed an inverse relationship with telehealth utilization (ρ=-0.22; P<0.05; and ρ=-0.34; P<0.05, respectively). Adjusted analyses indicated that concurrent telehealth use was associated with reduced odds of emergency department visits (0.916, 95% CI 0.884-0.948) and hospitalizations (0.830, 95% CI 0.799-0.863), acknowledging the potential influence of residual confounding.</p><p><strong>Conclusions: </strong>Telehealth has emerged as a crucial mode of care delivery for patients with complex conditions such as cancer. Understanding usage patterns and factors influencing tel
{"title":"Patterns of Telehealth Use Across the Cancer Care Continuum and Assessment of Patient and Geographic Factors Associated With Key Healthcare Outcomes: Retrospective Study.","authors":"Kassandra I Alcaraz, Christopher Kitchen, Thomas Richards, Chintan J Pandya, Jonathan P Weiner, Elham Hatef","doi":"10.2196/79956","DOIUrl":"10.2196/79956","url":null,"abstract":"<p><strong>Background: </strong>Although the use of telehealth has declined since the pandemic, it remains a popular mode of care delivery across the cancer care continuum. Understanding telehealth in the context of cancer care is essential, as its benefits and challenges may differ among diverse population groups and geographic areas.</p><p><strong>Objective: </strong>This study aimed to examine patterns of telehealth utilization across the cancer care continuum and to identify factors associated with the receipt of telehealth in a large patient population. This study also aimed to assess the telehealth's impact on key health care delivery outcomes.</p><p><strong>Methods: </strong>We used an annualized retrospective cohort design using patient data from the Johns Hopkins Health System (JHHS), a large regional academic health center in Maryland. The study analyzed electronic health record (EHR) data covering the period from January 1, 2019, to December 31, 2023. Chronic conditions were defined through the Johns Hopkins Adjusted Clinical Groups (ACG) System, which identifies comorbidities based on the International Classification of Diseases, Tenth Revision, Clinical Modification, codes in the electronic health record. In addition, we used publicly available geospatial data (eg, internet connectivity, rural-urban commuting area) to assess telehealth receipt associations. Statistical modeling, including generalized estimating equations, was used to evaluate variations in telehealth utilization and outcomes.</p><p><strong>Results: </strong>A total of 124,974 adult patients receiving cancer-related care at Johns Hopkins Health System were identified during the study period. Telehealth users were significantly older (52.2% aged ≥65 years, 19,942 patients) compared to nonusers (48.7%, 42,209 patients). In addition, these users were more likely to be male (45.4%, 17,365 patients vs 40.2%, 34,839 patients) and to identify as White (70.8%, 27,071 patients vs 64.7%, 56,122 patients). Telehealth users also had a higher prevalence of comorbidities, with 61.5% (23,503 patients) reporting 3 or more chronic conditions compared to 38.0% (33,000 patients) among nonusers. A positive correlation was noted between rural-urban commuting area codes and telehealth service utilization (ρ=0.36; P<0.05), indicating higher usage in more rural areas. Conversely, average maximum download and upload speeds showed an inverse relationship with telehealth utilization (ρ=-0.22; P<0.05; and ρ=-0.34; P<0.05, respectively). Adjusted analyses indicated that concurrent telehealth use was associated with reduced odds of emergency department visits (0.916, 95% CI 0.884-0.948) and hospitalizations (0.830, 95% CI 0.799-0.863), acknowledging the potential influence of residual confounding.</p><p><strong>Conclusions: </strong>Telehealth has emerged as a crucial mode of care delivery for patients with complex conditions such as cancer. Understanding usage patterns and factors influencing tel","PeriodicalId":45538,"journal":{"name":"JMIR Cancer","volume":"11 ","pages":"e79956"},"PeriodicalIF":2.7,"publicationDate":"2025-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12574977/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145410275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lara Kohn, Veit Scheble, Philip Storz, Anita Müller, Selcan Behiye Ulas, Fee Schmitt, Christian Thies, Nisar Malek
Background: Outpatient treatments, including targeted therapies, in oncology are on the rise. The implementation of remote patient monitoring (RPM) between therapy sessions has the potential to enhance patient care and therapy outcomes in the future.
Objective: This pilot study assessed the feasibility of a new, app-based RPM system (bwHealthApp) by capturing patient-reported outcomes (PROs) and vital parameters using a wrist- or in-ear wearable. The study examined adherence, acceptance, and satisfaction, as well as the differences between the two types of wearables.
Methods: Outpatients with gastrointestinal cancer receiving systemic therapies were invited to use and evaluate the bwHealthApp system for 1 month. The system was set up as an Android smartphone app to assess electronic PROs (ePROs) and connect to wearables for continuous vital sign measurements. A wrist wearable (Beurer AS99) that measured activity and heart rate or an in-ear wearable (Cosinuss Two) that measured heart rate, oxygen saturation, and temperature was used. The data were synchronized remotely to a web client. Outpatients were randomly assigned to the wrist wearable (n=17) or in-ear wearable (n=14) group. At the beginning, middle, and end of the study, patients (N=31) completed questionnaires on various feasibility aspects. Adherence to ePRO completion; wearable use, acceptance, and satisfaction; wearable data quantity and quality; and differences between the wearables were evaluated.
Results: The mean adherence to bwHealthApp including dropouts was 46% (449/971 days) for ePRO completion and 61% (593/971 days) for wearable use. The system was most frequently used during everyday activities. More than half of the participants were satisfied with bwHealthApp (18/30, 60%) and could imagine continued use (21/30, 70%). Notably, 70% (21/30) rated the system as easy to use. Participants recorded more than 20 million wearable measures; however, 29% (SD 22%, range 3%-76%) of temperature values and 33% (SD 25%, range 10%-92%) of oxygen saturation values were outside the physiological range. For heart rate, the mean proportion of excluded values was 10% (SD 11%, range 4%-48%; in-ear) and 11% (SD 8%, range 4%-33%; wrist). The frequency of use of the two wearables did not differ significantly (t29=1.81; P=.08). The wrist wearable scored significantly better than the in-ear wearable regarding wearing comfort (t28=-11.17; P=.03).
Conclusions: This bwHealthApp pilot study demonstrates the feasibility of RPM via a mobile app and wearable devices during outpatient systemic cancer therapy, including targeted therapies. The adherence level was moderate, and patients were generally satisfied with the system, although the wrist wearable received a higher rating. The system's functionality may be enhanced through the integration of additional wearables. This pilot study serves as a fo
{"title":"An App-Based Remote Patient Monitoring System With Wrist and In-Ear Wearables in Gastrointestinal Oncology: Prospective Feasibility Pilot Study.","authors":"Lara Kohn, Veit Scheble, Philip Storz, Anita Müller, Selcan Behiye Ulas, Fee Schmitt, Christian Thies, Nisar Malek","doi":"10.2196/64184","DOIUrl":"10.2196/64184","url":null,"abstract":"<p><strong>Background: </strong>Outpatient treatments, including targeted therapies, in oncology are on the rise. The implementation of remote patient monitoring (RPM) between therapy sessions has the potential to enhance patient care and therapy outcomes in the future.</p><p><strong>Objective: </strong>This pilot study assessed the feasibility of a new, app-based RPM system (bwHealthApp) by capturing patient-reported outcomes (PROs) and vital parameters using a wrist- or in-ear wearable. The study examined adherence, acceptance, and satisfaction, as well as the differences between the two types of wearables.</p><p><strong>Methods: </strong>Outpatients with gastrointestinal cancer receiving systemic therapies were invited to use and evaluate the bwHealthApp system for 1 month. The system was set up as an Android smartphone app to assess electronic PROs (ePROs) and connect to wearables for continuous vital sign measurements. A wrist wearable (Beurer AS99) that measured activity and heart rate or an in-ear wearable (Cosinuss Two) that measured heart rate, oxygen saturation, and temperature was used. The data were synchronized remotely to a web client. Outpatients were randomly assigned to the wrist wearable (n=17) or in-ear wearable (n=14) group. At the beginning, middle, and end of the study, patients (N=31) completed questionnaires on various feasibility aspects. Adherence to ePRO completion; wearable use, acceptance, and satisfaction; wearable data quantity and quality; and differences between the wearables were evaluated.</p><p><strong>Results: </strong>The mean adherence to bwHealthApp including dropouts was 46% (449/971 days) for ePRO completion and 61% (593/971 days) for wearable use. The system was most frequently used during everyday activities. More than half of the participants were satisfied with bwHealthApp (18/30, 60%) and could imagine continued use (21/30, 70%). Notably, 70% (21/30) rated the system as easy to use. Participants recorded more than 20 million wearable measures; however, 29% (SD 22%, range 3%-76%) of temperature values and 33% (SD 25%, range 10%-92%) of oxygen saturation values were outside the physiological range. For heart rate, the mean proportion of excluded values was 10% (SD 11%, range 4%-48%; in-ear) and 11% (SD 8%, range 4%-33%; wrist). The frequency of use of the two wearables did not differ significantly (t29=1.81; P=.08). The wrist wearable scored significantly better than the in-ear wearable regarding wearing comfort (t28=-11.17; P=.03).</p><p><strong>Conclusions: </strong>This bwHealthApp pilot study demonstrates the feasibility of RPM via a mobile app and wearable devices during outpatient systemic cancer therapy, including targeted therapies. The adherence level was moderate, and patients were generally satisfied with the system, although the wrist wearable received a higher rating. The system's functionality may be enhanced through the integration of additional wearables. This pilot study serves as a fo","PeriodicalId":45538,"journal":{"name":"JMIR Cancer","volume":"11 ","pages":"e64184"},"PeriodicalIF":2.7,"publicationDate":"2025-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12574740/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145410310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Correction: Narrative Expertise in Oncology: An Integrated Training Model to Advance the Field.","authors":"Trisha K Paul, Erica C Kaye","doi":"10.2196/86071","DOIUrl":"10.2196/86071","url":null,"abstract":"","PeriodicalId":45538,"journal":{"name":"JMIR Cancer","volume":"11 ","pages":"e86071"},"PeriodicalIF":2.7,"publicationDate":"2025-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12576297/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145410264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<p><strong>Background: </strong>Lung cancer (LC) is the leading cause of cancer-related deaths worldwide and has a substantial impact on patients' quality of life (QoL) and psychological well-being, due to complex physical, emotional, and social challenges. Addressing these needs is critical; yet, many patients go unsupported. eHealth (using information and communication technology to deliver health-related services) offers a scalable way to provide timely, personalized care for people living with LC.</p><p><strong>Objective: </strong>This review aimed to evaluate the impact of eHealth interventions on QoL and psychological well-being in patients with LC, and characterize the different strategies used.</p><p><strong>Methods: </strong>A systematic review was conducted following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Literature searches across 6 databases (PubMed, PsycINFO, MEDLINE, Scopus, Web of Science, and CINAHL) were performed between December 2023 and February 2024. Eligible studies included experimental and quantitative designs involving adults (≥18 years) diagnosed with LC. Interventions were required at least 1 eHealth component, and studies had to report outcomes on QoL or psychological well-being. Data extraction focused on study characteristics, intervention details, outcomes, engagement and acceptability metrics. Study quality was assessed using a modified Downs and Black checklist, and a synthesis without meta-analysis was conducted due to study heterogeneity.</p><p><strong>Results: </strong>A total of 7065 records were screened, with 33 studies meeting inclusion criteria; of these, 30 were suitable for quantitative synthesis, comprising 2654 individual participants and 231 patient-caregiver dyads. eHealth strategies included: patient education (n=2), digital symptom monitoring (n=6), physical activity programs (n=8), psychological support (n=5), nurse-led interventions (n=5), and multicomponent portals or platforms (n=7). For QoL, the most consistent benefits were observed in multicomponent (5/5) and nurse-led (3/3) interventions, followed by physical activity (4/6) and symptom monitoring (4/6) approaches. For psychological well-being, multicomponent (4/4), nurse-led (2/2), and physical activity (6/6) interventions all demonstrated consistent positive effects. Psychological interventions showed mixed effects overall, although mindfulness-based programs (2/2) consistently reduced psychological symptoms. Key factors linked to positive outcomes included personalization, delivery via apps or web-based platforms, longer intervention duration, and clinician involvement. User acceptability was generally high, and engagement was variable, although both were rarely measured.</p><p><strong>Conclusions: </strong>eHealth interventions can have a positive effect on QoL and psychological well-being for people with LC. Multifaceted programs addressing diverse patient needs were found to be particula
背景：肺癌（LC）是全球癌症相关死亡的主要原因，由于其复杂的身体、情感和社会挑战，对患者的生活质量（QoL）和心理健康产生重大影响。解决这些需求至关重要；然而，许多患者没有得到支持。电子医疗（利用信息和通信技术提供与健康相关的服务）提供了一种可扩展的方式，为LC患者提供及时、个性化的护理。目的：本综述旨在评估电子健康干预对LC患者生活质量和心理健康的影响，并描述使用的不同策略。方法：按照PRISMA（系统评价和荟萃分析首选报告项目）指南进行系统评价。在2023年12月至2024年2月期间，对6个数据库（PubMed, PsycINFO， MEDLINE, Scopus， Web of Science和CINAHL）进行了文献检索。符合条件的研究包括诊断为LC的成人（≥18岁）的实验和定量设计。干预措施至少需要1个电子健康组成部分，研究必须报告生活质量或心理健康的结果。数据提取侧重于研究特征、干预细节、结果、参与度和可接受性指标。使用改进的Downs和Black检查表评估研究质量，由于研究异质性，进行了不含meta分析的综合研究。结果：共筛选7065条记录，其中33项研究符合纳入标准；其中，30个适合定量合成，包括2654名个体参与者和231名患者-护理者二人组。电子健康策略包括：患者教育（n=2）、数字症状监测（n=6）、体育活动计划（n=8）、心理支持（n=5）、护士主导的干预（n=5）和多组件门户或平台（n=7）。对于生活质量，多组分（5/5）和护士主导（3/3）干预措施的效果最为一致，其次是身体活动（4/6）和症状监测（4/6）方法。在心理健康方面，多成分（4/4）、护士主导（2/2）和身体活动（6/6）干预均显示出一致的积极效果。心理干预总体上显示出好坏参半的效果，尽管基于正念的方案（2/2）持续地减少了心理症状。与积极结果相关的关键因素包括个性化、通过应用程序或基于网络的平台交付、更长的干预时间和临床医生的参与。用户接受度普遍较高，用户粘性变化较大，尽管两者都很少被衡量。结论：电子健康干预可对LC患者的生活质量和心理健康产生积极影响。研究发现，针对不同患者需求的多方面方案特别有效。然而，研究质量的差异、小样本量、参与和可接受性测量的不一致限制了结论的强度。因此，尽管电子健康解决方案有可能解决LC护理方面的重大差距并改善患者的预后，但还需要进一步的研究。为了充分发挥其潜力，未来的研究应优先开发和评估量身定制的、可扩展的电子健康解决方案，这些解决方案具有稳健的设计、标准化的结果和策略，以提高患者在日常护理中的参与度和实施。试验注册：PROSPERO CRD42024509607；https://tinyurl.com/ycst2r8k。
{"title":"Using eHealth to Support Quality of Life and Well-Being in Patients With Lung Cancer: Systematic Review.","authors":"Virginia Harrison, Katie Jones, Caroline Ac Hyde","doi":"10.2196/70510","DOIUrl":"10.2196/70510","url":null,"abstract":"<p><strong>Background: </strong>Lung cancer (LC) is the leading cause of cancer-related deaths worldwide and has a substantial impact on patients' quality of life (QoL) and psychological well-being, due to complex physical, emotional, and social challenges. Addressing these needs is critical; yet, many patients go unsupported. eHealth (using information and communication technology to deliver health-related services) offers a scalable way to provide timely, personalized care for people living with LC.</p><p><strong>Objective: </strong>This review aimed to evaluate the impact of eHealth interventions on QoL and psychological well-being in patients with LC, and characterize the different strategies used.</p><p><strong>Methods: </strong>A systematic review was conducted following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Literature searches across 6 databases (PubMed, PsycINFO, MEDLINE, Scopus, Web of Science, and CINAHL) were performed between December 2023 and February 2024. Eligible studies included experimental and quantitative designs involving adults (≥18 years) diagnosed with LC. Interventions were required at least 1 eHealth component, and studies had to report outcomes on QoL or psychological well-being. Data extraction focused on study characteristics, intervention details, outcomes, engagement and acceptability metrics. Study quality was assessed using a modified Downs and Black checklist, and a synthesis without meta-analysis was conducted due to study heterogeneity.</p><p><strong>Results: </strong>A total of 7065 records were screened, with 33 studies meeting inclusion criteria; of these, 30 were suitable for quantitative synthesis, comprising 2654 individual participants and 231 patient-caregiver dyads. eHealth strategies included: patient education (n=2), digital symptom monitoring (n=6), physical activity programs (n=8), psychological support (n=5), nurse-led interventions (n=5), and multicomponent portals or platforms (n=7). For QoL, the most consistent benefits were observed in multicomponent (5/5) and nurse-led (3/3) interventions, followed by physical activity (4/6) and symptom monitoring (4/6) approaches. For psychological well-being, multicomponent (4/4), nurse-led (2/2), and physical activity (6/6) interventions all demonstrated consistent positive effects. Psychological interventions showed mixed effects overall, although mindfulness-based programs (2/2) consistently reduced psychological symptoms. Key factors linked to positive outcomes included personalization, delivery via apps or web-based platforms, longer intervention duration, and clinician involvement. User acceptability was generally high, and engagement was variable, although both were rarely measured.</p><p><strong>Conclusions: </strong>eHealth interventions can have a positive effect on QoL and psychological well-being for people with LC. Multifaceted programs addressing diverse patient needs were found to be particula","PeriodicalId":45538,"journal":{"name":"JMIR Cancer","volume":"11 ","pages":"e70510"},"PeriodicalIF":2.7,"publicationDate":"2025-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12603585/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145379321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Meng Qing Xu, Zhi Sheng Jiang, Wan Yu Liao, Ying Kang, Xiao Yue Feng, Kang Jiang, Qiong Jiang, Zhuang Zhuang Cong, Jing Luo, Lin Wu, Yi Shen, Fang Yu Wang
Background: While numerous models have been developed to predict overall survival in postoperative patients with esophageal squamous cell carcinoma (ESCC), few have specifically focused on predicting postoperative recurrence.
Objective: This study aimed to develop and validate a support vector machine (SVM)-based predictive model for evaluating recurrence risk and identifying associated factors in ESCC patients following surgery.
Methods: We retrospectively analyzed clinical data from 311 ESCC patients who underwent surgery at Jinling Hospital between June 2014 and November 2016, with follow-up until October 2021 (median of 36 follow-up months, range 0-93.5 months). After excluding cases with incomplete data (n=1), 310 eligible patients were randomly allocated into test (n=106), validation 1 (n=103), and validation 2 (n=101) cohorts. Using SVM algorithms, patients were stratified into high- or low-recurrence-risk groups. Model performance was assessed using sensitivity, specificity, the Youden index, positive predictive value, and negative predictive value. Calibration curves were generated to evaluate model accuracy and reliability. Statistical analyses were performed using SPSS (version 22.0; IBM Corp) and R (version 3.6.1; R Foundation for Statistical Computing).
Results: In all cohorts, SVM7 (incorporating tumor node metastasis [TNM] stage, adjuvant therapy, differentiation, tumor size, and complications) demonstrated significantly higher sensitivity in predicting recurrence than SVM6 (based on the Eastern Cooperative Oncology Group performance status, neutrophil-to-lymphocyte ratio, and CY211) (P<.001). The composite model SVM6+8 (combining SVM6 and SVM8 [SVM7 excluding complications]) achieved recurrence prediction sensitivities of 94%, 79.59%, and 72.73% in the test, validation 1, and validation 2 groups, respectively; with specificities of 98.11%, 69.84%, and 78.43%. These results were comparable to SVM6+TNM (SVM6 combined with TNM staging) but outperformed SVM6 alone (P<.001). Survival analysis revealed significantly longer disease-free survival in the SVM6+TNM-predicted low-risk group compared to the high-risk group, with a marked difference in recurrence rates (P<.001).
Conclusions: The proposed SVM-based model enables accurate prediction of postoperative recurrence in ESCC patients with high sensitivity, specificity, and discriminative power, offering a valuable tool for clinical risk stratification.
背景：虽然已经开发了许多模型来预测食管鳞状细胞癌（ESCC）术后患者的总体生存，但很少有模型专门用于预测术后复发。目的：本研究旨在建立并验证基于支持向量机（SVM）的ESCC患者术后复发风险评估及相关因素识别预测模型。方法：回顾性分析2014年6月至2016年11月在金陵医院接受手术治疗的311例ESCC患者的临床资料，随访至2021年10月（中位随访月36个月，范围0-93.5个月）。在排除资料不完整的病例（n=1）后，310例符合条件的患者被随机分配到试验（n=106）、验证1 （n=103）和验证2 （n=101）队列中。使用支持向量机算法，将患者分为高复发风险组和低复发风险组。采用敏感性、特异性、约登指数、阳性预测值和阴性预测值评估模型性能。生成校准曲线以评价模型的准确性和可靠性。采用SPSS （version 22.0; IBM Corp）和R （version 3.6.1; R Foundation for Statistical Computing）进行统计分析。结果：在所有队列中，SVM7（包括肿瘤淋巴结转移[TNM]分期、辅助治疗、分化、肿瘤大小和并发症）预测复发的敏感性明显高于SVM6（基于东部肿瘤合作组的表现状态、中性粒细胞与淋巴细胞比例和CY211） （p7）。提出的基于svm的ESCC患者术后复发预测模型具有较高的敏感性、特异性和判别能力，为临床风险分层提供了有价值的工具。
{"title":"Predicting Postoperative Recurrence Using a Support Vector Machine for Patients With Esophageal Squamous Cell Carcinoma: Machine Learning Modeling Development and Validation Study.","authors":"Meng Qing Xu, Zhi Sheng Jiang, Wan Yu Liao, Ying Kang, Xiao Yue Feng, Kang Jiang, Qiong Jiang, Zhuang Zhuang Cong, Jing Luo, Lin Wu, Yi Shen, Fang Yu Wang","doi":"10.2196/68027","DOIUrl":"10.2196/68027","url":null,"abstract":"<p><strong>Background: </strong>While numerous models have been developed to predict overall survival in postoperative patients with esophageal squamous cell carcinoma (ESCC), few have specifically focused on predicting postoperative recurrence.</p><p><strong>Objective: </strong>This study aimed to develop and validate a support vector machine (SVM)-based predictive model for evaluating recurrence risk and identifying associated factors in ESCC patients following surgery.</p><p><strong>Methods: </strong>We retrospectively analyzed clinical data from 311 ESCC patients who underwent surgery at Jinling Hospital between June 2014 and November 2016, with follow-up until October 2021 (median of 36 follow-up months, range 0-93.5 months). After excluding cases with incomplete data (n=1), 310 eligible patients were randomly allocated into test (n=106), validation 1 (n=103), and validation 2 (n=101) cohorts. Using SVM algorithms, patients were stratified into high- or low-recurrence-risk groups. Model performance was assessed using sensitivity, specificity, the Youden index, positive predictive value, and negative predictive value. Calibration curves were generated to evaluate model accuracy and reliability. Statistical analyses were performed using SPSS (version 22.0; IBM Corp) and R (version 3.6.1; R Foundation for Statistical Computing).</p><p><strong>Results: </strong>In all cohorts, SVM7 (incorporating tumor node metastasis [TNM] stage, adjuvant therapy, differentiation, tumor size, and complications) demonstrated significantly higher sensitivity in predicting recurrence than SVM6 (based on the Eastern Cooperative Oncology Group performance status, neutrophil-to-lymphocyte ratio, and CY211) (P<.001). The composite model SVM6+8 (combining SVM6 and SVM8 [SVM7 excluding complications]) achieved recurrence prediction sensitivities of 94%, 79.59%, and 72.73% in the test, validation 1, and validation 2 groups, respectively; with specificities of 98.11%, 69.84%, and 78.43%. These results were comparable to SVM6+TNM (SVM6 combined with TNM staging) but outperformed SVM6 alone (P<.001). Survival analysis revealed significantly longer disease-free survival in the SVM6+TNM-predicted low-risk group compared to the high-risk group, with a marked difference in recurrence rates (P<.001).</p><p><strong>Conclusions: </strong>The proposed SVM-based model enables accurate prediction of postoperative recurrence in ESCC patients with high sensitivity, specificity, and discriminative power, offering a valuable tool for clinical risk stratification.</p>","PeriodicalId":45538,"journal":{"name":"JMIR Cancer","volume":"11 ","pages":"e68027"},"PeriodicalIF":2.7,"publicationDate":"2025-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12548966/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145356393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Katarzyna Borys, Eva Maria Hartmann, Ahmad Idrissi-Yaghir, Elisabeth Livingstone, Georg Lodde, Cynthia Sabrina Schmidt, Philipp Winnekens, Christoph M Friedrich, René Hosch, Felix Nensa
Unlabelled: Over the past decade, Fast Healthcare Interoperability Resources (FHIR) have become increasingly relevant in health care data standardization. However, the complex structure of FHIR makes cohort analytics with many-to-many relations extremely time-consuming, and, impossible in many cases. To support exploratory cohort building and data visualization in oncology, especially for nontechnical users, we developed the DermaDashboard, an interactive dashboard built on top of a relational FHIR-compliant PostgreSQL database. Relevant oncology data was preaggregated with a materialized view, and the subsequent visualization layer was implemented using an open-source visualization tool, enabling clinicians to filter and analyze data without requiring familiarity with FHIR or SQL. The database encompassed data from 3949 patients with melanoma and included 82,783 health records. Core FHIR resources were Patient, DiagnosticReport, and QuestionnaireResponse, with 54 mapped attributes spanning demographics, stagings, mutations, and treatments. The resulting dashboard allowed filtering across 29 variables to construct subcohorts and generate aggregation analyses. This implementation shows how open interoperability data standards, such as FHIR, can be used in the development of modular, user-friendly clinical dashboards for cohort analysis, and the architecture demonstrates a feasible path toward democratizing access to structured health care data.
{"title":"DermaDashboard: Bridging the Gap Between FHIR Standards and Clinical Usability.","authors":"Katarzyna Borys, Eva Maria Hartmann, Ahmad Idrissi-Yaghir, Elisabeth Livingstone, Georg Lodde, Cynthia Sabrina Schmidt, Philipp Winnekens, Christoph M Friedrich, René Hosch, Felix Nensa","doi":"10.2196/73691","DOIUrl":"10.2196/73691","url":null,"abstract":"<p><strong>Unlabelled: </strong>Over the past decade, Fast Healthcare Interoperability Resources (FHIR) have become increasingly relevant in health care data standardization. However, the complex structure of FHIR makes cohort analytics with many-to-many relations extremely time-consuming, and, impossible in many cases. To support exploratory cohort building and data visualization in oncology, especially for nontechnical users, we developed the DermaDashboard, an interactive dashboard built on top of a relational FHIR-compliant PostgreSQL database. Relevant oncology data was preaggregated with a materialized view, and the subsequent visualization layer was implemented using an open-source visualization tool, enabling clinicians to filter and analyze data without requiring familiarity with FHIR or SQL. The database encompassed data from 3949 patients with melanoma and included 82,783 health records. Core FHIR resources were Patient, DiagnosticReport, and QuestionnaireResponse, with 54 mapped attributes spanning demographics, stagings, mutations, and treatments. The resulting dashboard allowed filtering across 29 variables to construct subcohorts and generate aggregation analyses. This implementation shows how open interoperability data standards, such as FHIR, can be used in the development of modular, user-friendly clinical dashboards for cohort analysis, and the architecture demonstrates a feasible path toward democratizing access to structured health care data.</p>","PeriodicalId":45538,"journal":{"name":"JMIR Cancer","volume":"11 ","pages":"e73691"},"PeriodicalIF":2.7,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12543034/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145349105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号