J. P. Sosa, M. M. Caceres, Jennifer Ross-Comptis, D. Hathaway, Jayati Mehta, Krunal Pandav, R. Pakala, Maliha Butt, Zeryab Dogar, Marie-Pierre Belizaire, Nada El Mazboudi, M. K. Pormento, Madiha Zaidi, Harshitha Mergey Devender, Hanyou Loh, Radhika Garimella, Niran Brahmbhatt
When and where the first case of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) appeared, remains controversial. However, it has proven to be highly infectious and capable of rapid mutation. Within months, it spread to over 213 countries infecting 21.7 million people and causing 770,000 deaths. SARS-CoV-2 belongs to a virus family known as Coronaviridae. It is transmitted through minute respiratory droplets produced by coughing, sneezing, or talking in close proximity to one another. Another mode of transmission is by droplets, touching surfaces contaminated with the virus, and touching the face, eyes, or mouth with the contaminated hands. Symptoms of the viral infection appear in 1–14 days and include fever, cough, fatigue, general weakness, sore throat, and muscular pains, while in severe cases it can lead to acute respiratory distress syndrome (ARDS), severe pneumonia, and sepsis (1). Coronavirus Disease 2019 (COVID-19) was declared a pandemic by the World Health Organization (WHO) on March 11, 2020. Not much is known about the virus, but research is still ongoing, and the search for treatment is underway. Strict standard operating measures (SOPs) are being used in order to limit the spread of the virus until a vaccine is developed. The rapid spread of SARS-CoV-2 has resulted in several difficulties regarding accurate and timely information dissemination, controlling the spread rate, and public health planning. This pandemic has proven to be a unique situation since it was recommended to limit physical interactions to prevent infection (2,3). Due to the social distancing measures enforced by many countries, it is more difficult for people to receive medical attention quickly and safely. To overcome this problem, be more efficient, and be able to save more lives, the use of artificial intelligence (AI) has been introduced. This has helped promote telehealth and allow patients to receive care in the comfort of their homes and decrease the patient load on the already overflowing hospitals. SARS-CoV-2 is a highly contagious virus, and as health professionals are closely dealing with the affected people, the use of AI has helped to decrease inpatient visits, thereby decreasing the workload and exposure. Using applications (henceforth referred to as apps) has helped remotely monitor patients while keeping in mind doctor-patient confidentiality and secure communication between them. Contact tracing through the apps has helped identify the ‘hotspots’ for the virus, track the spread, and contain it (4). These apps can be used in population screening and getting day-to-day updates of the areas where new cases are emerging. The use of apps improves productivity and efficiency in studies with large samples (5). It is for this reason that web and mobile-based apps are being used during this pandemic situation. Several apps deployed in different areas of the world are being used to accelerate and aid the process of geographical mapping of case
{"title":"Web-Based Apps in the fight against COVID-19","authors":"J. P. Sosa, M. M. Caceres, Jennifer Ross-Comptis, D. Hathaway, Jayati Mehta, Krunal Pandav, R. Pakala, Maliha Butt, Zeryab Dogar, Marie-Pierre Belizaire, Nada El Mazboudi, M. K. Pormento, Madiha Zaidi, Harshitha Mergey Devender, Hanyou Loh, Radhika Garimella, Niran Brahmbhatt","doi":"10.21037/JMAI-20-61","DOIUrl":"https://doi.org/10.21037/JMAI-20-61","url":null,"abstract":"When and where the first case of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) appeared, remains controversial. However, it has proven to be highly infectious and capable of rapid mutation. Within months, it spread to over 213 countries infecting 21.7 million people and causing 770,000 deaths. SARS-CoV-2 belongs to a virus family known as Coronaviridae. It is transmitted through minute respiratory droplets produced by coughing, sneezing, or talking in close proximity to one another. Another mode of transmission is by droplets, touching surfaces contaminated with the virus, and touching the face, eyes, or mouth with the contaminated hands. Symptoms of the viral infection appear in 1–14 days and include fever, cough, fatigue, general weakness, sore throat, and muscular pains, while in severe cases it can lead to acute respiratory distress syndrome (ARDS), severe pneumonia, and sepsis (1). Coronavirus Disease 2019 (COVID-19) was declared a pandemic by the World Health Organization (WHO) on March 11, 2020. Not much is known about the virus, but research is still ongoing, and the search for treatment is underway. Strict standard operating measures (SOPs) are being used in order to limit the spread of the virus until a vaccine is developed. The rapid spread of SARS-CoV-2 has resulted in several difficulties regarding accurate and timely information dissemination, controlling the spread rate, and public health planning. This pandemic has proven to be a unique situation since it was recommended to limit physical interactions to prevent infection (2,3). Due to the social distancing measures enforced by many countries, it is more difficult for people to receive medical attention quickly and safely. To overcome this problem, be more efficient, and be able to save more lives, the use of artificial intelligence (AI) has been introduced. This has helped promote telehealth and allow patients to receive care in the comfort of their homes and decrease the patient load on the already overflowing hospitals. SARS-CoV-2 is a highly contagious virus, and as health professionals are closely dealing with the affected people, the use of AI has helped to decrease inpatient visits, thereby decreasing the workload and exposure. Using applications (henceforth referred to as apps) has helped remotely monitor patients while keeping in mind doctor-patient confidentiality and secure communication between them. Contact tracing through the apps has helped identify the ‘hotspots’ for the virus, track the spread, and contain it (4). These apps can be used in population screening and getting day-to-day updates of the areas where new cases are emerging. The use of apps improves productivity and efficiency in studies with large samples (5). It is for this reason that web and mobile-based apps are being used during this pandemic situation. Several apps deployed in different areas of the world are being used to accelerate and aid the process of geographical mapping of case","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43330511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Tajerian, K. Pesce, J. Frangella, Ezequiel D. Quiroga, B. Boietti, M. Chico, M. Swiecicki, S. Benítez, M. Rabellino, D. Luna
Breast density is the terminology used in mammography to describe the proportion between fibroglandular tissue and adipose tissue. It is estimated that 50% of women who undergo mammography examinations have dense breast patterns (1). There is evidence that mammographic density is as strong a predictor of risk for breast cancer in African-American and Asian-American women as for white women (2). High breast density is an independent risk factor for breast cancer (3-6). Furthermore, it may link to higher percentages of interval cancers (7). Dense breast tissue can mask lesions and has a negative impact on the sensitivity of the mammography with rates ranging from 85.7% for the adipose patterns to 61% for the extremely dense patterns. It can also generate an increase in false positives from 11.2% for the non-dense patterns to 23% for dense breasts (8). Breast density can be measured through qualitative or quantitative methods. The American College of Radiology (ACR) has established a structured system for the visual Original Article
乳腺密度是乳房x光摄影中用来描述纤维腺组织和脂肪组织之间比例的术语。据估计，接受乳房x光检查的女性中有50%存在致密的乳房(1)。有证据表明，乳房x光检查密度与白人女性一样，是非裔美国人和亚裔美国女性患乳腺癌的风险预测因子(2)。高乳房密度是乳腺癌的独立危险因素(3-6)。此外，它可能与间隔期癌症的较高百分比有关(7)。致密的乳腺组织可以掩盖病变，并对乳房x光检查的敏感性产生负面影响，其比率从脂肪型的85.7%到极致密型的61%不等。它还会使假阳性从非致密模式的11.2%增加到致密乳房的23%(8)。乳房密度可以通过定性或定量方法测量。美国放射学会(American College of Radiology, ACR)为视觉原创文章建立了一个结构化的系统
{"title":"Artemisia: validation of a deep learning model for automatic breast density categorization","authors":"M. Tajerian, K. Pesce, J. Frangella, Ezequiel D. Quiroga, B. Boietti, M. Chico, M. Swiecicki, S. Benítez, M. Rabellino, D. Luna","doi":"10.21037/JMAI-20-43","DOIUrl":"https://doi.org/10.21037/JMAI-20-43","url":null,"abstract":"Breast density is the terminology used in mammography to describe the proportion between fibroglandular tissue and adipose tissue. It is estimated that 50% of women who undergo mammography examinations have dense breast patterns (1). There is evidence that mammographic density is as strong a predictor of risk for breast cancer in African-American and Asian-American women as for white women (2). High breast density is an independent risk factor for breast cancer (3-6). Furthermore, it may link to higher percentages of interval cancers (7). Dense breast tissue can mask lesions and has a negative impact on the sensitivity of the mammography with rates ranging from 85.7% for the adipose patterns to 61% for the extremely dense patterns. It can also generate an increase in false positives from 11.2% for the non-dense patterns to 23% for dense breasts (8). Breast density can be measured through qualitative or quantitative methods. The American College of Radiology (ACR) has established a structured system for the visual Original Article","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48183820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kai Lin, Roberto Sarnari, Ashitha Pathrose, Daniel Z. Gordon, M. Markl, J. Carr
{"title":"Deep learning for the identification of pre- and post-capillary pulmonary hypertension on cine MRI","authors":"Kai Lin, Roberto Sarnari, Ashitha Pathrose, Daniel Z. Gordon, M. Markl, J. Carr","doi":"10.21037/jmai-21-27","DOIUrl":"https://doi.org/10.21037/jmai-21-27","url":null,"abstract":"","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42119701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Objective: We performed a comprehensive review of the literature to better understand the trust dynamics between medical artificial intelligence (AI) and healthcare expert end-users. We explored the factors that influence trust in these technologies and how they compare to established concepts of trust in the engineering discipline. By identifying the qualitatively and quantitatively assessed factors that influence trust in medical AI, we gain insight into understanding how autonomous systems can be optimized during the development phase to improve decision-making support and clinician-machine teaming. This facilitates an enhanced understanding of the qualities that healthcare professional users seek in AI to consider it trustworthy. We also highlight key considerations for promoting on-going improvement of trust in autonomous medical systems to support the adoption of medical technologies into practice. Background: decision support systems introduces challenges and barriers to adoption and implementation into clinical practice. Methods: We searched databases including, Ovid MEDLINE, Ovid EMBASE, Clarivate Web of Science, and Google Scholar, as well as gray literature, for publications from 2000 to July 15, 2021, that reported features of AI-based diagnostic and clinical decision support systems that contribute to enhanced end-user trust. Papers discussing implications and applications of medical AI in clinical practice were also recorded. Results were based on the quantity of papers that discussed each trust concept, either quantitatively or qualitatively, using frequency of concept commentary as a proxy for importance of a respective concept. Conclusions: Explainability, transparency, interpretability, usability, and education are among the key identified factors thought to influence a healthcare professionals’ trust in medical AI and enhance clinician-machine teaming in critical decision-making healthcare environments. We also identified the need to better evaluate and incorporate other critical factors to promote trust by consulting medical professionals when developing AI systems for clinical decision-making and diagnostic support.
目的:我们对文献进行了全面的回顾，以更好地了解医疗人工智能(AI)和医疗保健专家最终用户之间的信任动态。我们探索了影响这些技术中信任的因素，以及它们与工程学科中已建立的信任概念的比较。通过确定影响医疗人工智能信任的定性和定量评估因素，我们深入了解如何在开发阶段优化自主系统，以改善决策支持和临床医生-机器团队。这有助于增强对医疗保健专业用户在人工智能中寻求的品质的理解，从而认为它值得信赖。我们还强调了促进持续改善对自主医疗系统的信任的关键考虑因素，以支持将医疗技术应用于实践。背景:决策支持系统为临床实践的采用和实施带来了挑战和障碍。方法:我们检索了包括Ovid MEDLINE、Ovid EMBASE、Clarivate Web of Science和谷歌Scholar在内的数据库以及灰色文献，检索了2000年至2021年7月15日期间的出版物，这些出版物报道了基于人工智能的诊断和临床决策支持系统有助于增强终端用户信任的特征。还记录了讨论医疗人工智能在临床实践中的影响和应用的论文。结果基于讨论每个信任概念的论文数量，无论是定量的还是定性的，使用概念评论的频率作为各自概念重要性的代理。结论:可解释性、透明度、可解释性、可用性和教育是影响医疗专业人员对医疗人工智能信任的关键因素，并在关键的医疗决策环境中增强临床医生与机器的合作。我们还发现，在开发用于临床决策和诊断支持的人工智能系统时，需要更好地评估和纳入其他关键因素，通过咨询医疗专业人员来促进信任。
{"title":"Factors influencing trust in medical artificial intelligence for healthcare professionals: a narrative review","authors":"Victoria Tucci, J. Saary, Thomas E. Doyle","doi":"10.21037/jmai-21-25","DOIUrl":"https://doi.org/10.21037/jmai-21-25","url":null,"abstract":"Objective: We performed a comprehensive review of the literature to better understand the trust dynamics between medical artificial intelligence (AI) and healthcare expert end-users. We explored the factors that influence trust in these technologies and how they compare to established concepts of trust in the engineering discipline. By identifying the qualitatively and quantitatively assessed factors that influence trust in medical AI, we gain insight into understanding how autonomous systems can be optimized during the development phase to improve decision-making support and clinician-machine teaming. This facilitates an enhanced understanding of the qualities that healthcare professional users seek in AI to consider it trustworthy. We also highlight key considerations for promoting on-going improvement of trust in autonomous medical systems to support the adoption of medical technologies into practice. Background: decision support systems introduces challenges and barriers to adoption and implementation into clinical practice. Methods: We searched databases including, Ovid MEDLINE, Ovid EMBASE, Clarivate Web of Science, and Google Scholar, as well as gray literature, for publications from 2000 to July 15, 2021, that reported features of AI-based diagnostic and clinical decision support systems that contribute to enhanced end-user trust. Papers discussing implications and applications of medical AI in clinical practice were also recorded. Results were based on the quantity of papers that discussed each trust concept, either quantitatively or qualitatively, using frequency of concept commentary as a proxy for importance of a respective concept. Conclusions: Explainability, transparency, interpretability, usability, and education are among the key identified factors thought to influence a healthcare professionals’ trust in medical AI and enhance clinician-machine teaming in critical decision-making healthcare environments. We also identified the need to better evaluate and incorporate other critical factors to promote trust by consulting medical professionals when developing AI systems for clinical decision-making and diagnostic support.","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41440959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Christina Guerrier, S. D'Acunto, Guillaume Labilloy, Rhemar Esma, H. Kendall, Daniel A. Norez, J. Fishe
{"title":"MONITOR: a multi-domain machine learning approach to predicting in-hospital mortality","authors":"Christina Guerrier, S. D'Acunto, Guillaume Labilloy, Rhemar Esma, H. Kendall, Daniel A. Norez, J. Fishe","doi":"10.21037/jmai-21-28","DOIUrl":"https://doi.org/10.21037/jmai-21-28","url":null,"abstract":"","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45580879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: Cardiovascular disease (CVD) is among the most common chronic diseases in the US. Adequate controlling CVD risk factors with medications can have a significant impact on patients’ long-term outcome. Early identification of patients with low adherence to medications using predictive models through machine learning (ML) may enhance outcomes of patients with CVD. The objective of the current review was to systematically identify and summarize published predictive models that used ML to assess medication adherence (MA) among patients with chronic CVD [heart failure (HF) and coronary artery disease (CAD)] or their main risk factors [hypertension (HTN) and hypercholesterolemia (HCL)]. Methods: A targeted review of English literature was undertaken in PubMed and Google Scholar from January 1, 2000 to August 9, 2021. All studies that used ML to predict MA among patients with chronic CVD or their main risk factors were eligible for this review. Risk of bias was assessed based on the studies’ sample size, data analysis methods, variables in each model, and validation methods used. Characteristics and outcomes of each study were summarized in tables. Results: A total of 12 studies met the eligibility criteria. Selected studies evaluated MA among patients with HF (n=2), CAD (n=3), HTN (n=5), and HCL (n=2). The most used ML algorithms used were random forest (RF) (n=5), support vector machine (SVM) (n=4), and neural network (NN) (n=4). The accuracy of the models ranged from 0.53 to 0.97. Discussion: Most studies used cross-validation to evaluate the internal validation of the model. However, none of the models were externally validated using a different dataset. Using ML to predict MA among patients with CVD and their risk factors is relatively new with only a few studies identified. Compared to conventional statistical methods, fewer restrictions for inclusion of variables in ML models, may enhance the model performance. More research is required to predict MA with higher accuracy and external validity.
{"title":"Application of machine learning in predicting medication adherence of patients with cardiovascular diseases: a systematic review of the literature","authors":"M. Zakeri, S. Sansgiry, S. Abughosh","doi":"10.21037/jmai-21-26","DOIUrl":"https://doi.org/10.21037/jmai-21-26","url":null,"abstract":"Background: Cardiovascular disease (CVD) is among the most common chronic diseases in the US. Adequate controlling CVD risk factors with medications can have a significant impact on patients’ long-term outcome. Early identification of patients with low adherence to medications using predictive models through machine learning (ML) may enhance outcomes of patients with CVD. The objective of the current review was to systematically identify and summarize published predictive models that used ML to assess medication adherence (MA) among patients with chronic CVD [heart failure (HF) and coronary artery disease (CAD)] or their main risk factors [hypertension (HTN) and hypercholesterolemia (HCL)]. Methods: A targeted review of English literature was undertaken in PubMed and Google Scholar from January 1, 2000 to August 9, 2021. All studies that used ML to predict MA among patients with chronic CVD or their main risk factors were eligible for this review. Risk of bias was assessed based on the studies’ sample size, data analysis methods, variables in each model, and validation methods used. Characteristics and outcomes of each study were summarized in tables. Results: A total of 12 studies met the eligibility criteria. Selected studies evaluated MA among patients with HF (n=2), CAD (n=3), HTN (n=5), and HCL (n=2). The most used ML algorithms used were random forest (RF) (n=5), support vector machine (SVM) (n=4), and neural network (NN) (n=4). The accuracy of the models ranged from 0.53 to 0.97. Discussion: Most studies used cross-validation to evaluate the internal validation of the model. However, none of the models were externally validated using a different dataset. Using ML to predict MA among patients with CVD and their risk factors is relatively new with only a few studies identified. Compared to conventional statistical methods, fewer restrictions for inclusion of variables in ML models, may enhance the model performance. More research is required to predict MA with higher accuracy and external validity.","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42016485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Ghali, Sarah S. Lam, K. D. Carpini, Chad Ezzell, A. Friedman, S. Yoon, Daehan Won
Organ scarcity is a pressing matter that requires serious attention. According to the US Department of Health and Human Services, a patient is added to the transplant waiting list every 10 minutes (1). As of December 2019, 73,934 people were waiting for a lifesaving organ (2). Although many people are registered on the organ waiting lists, available organs do not meet the need. In 2019, there was a national daily average of 95 transplants, meaning about Original Article
{"title":"Neural network-based prediction of consented organs utilization","authors":"H. Ghali, Sarah S. Lam, K. D. Carpini, Chad Ezzell, A. Friedman, S. Yoon, Daehan Won","doi":"10.21037/jmai-21-9","DOIUrl":"https://doi.org/10.21037/jmai-21-9","url":null,"abstract":"Organ scarcity is a pressing matter that requires serious attention. According to the US Department of Health and Human Services, a patient is added to the transplant waiting list every 10 minutes (1). As of December 2019, 73,934 people were waiting for a lifesaving organ (2). Although many people are registered on the organ waiting lists, available organs do not meet the need. In 2019, there was a national daily average of 95 transplants, meaning about Original Article","PeriodicalId":73815,"journal":{"name":"Journal of medical artificial intelligence","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43826781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：