Pub Date : 2023-11-10DOI: 10.55976/jdh.22023119882-87
Pablo Millares Martin
Background: Problem-oriented medical records are the standard among electronic health records (EHR) but after 50 years of use, problem lists (PL) do not seem to be the solution to clinicians' information needs. Objectives: To perform a quality improvement evaluation of PL content, considering available guidelines on its characteristics (accuracy, clarity, concision, currency) when transferring patients from one primary care organisation in England to another in Leeds. The standard should simply be the need to confirm currency. PL should be ready to be used safely after a brief check-up. Methods: During six months, all patients registering at a primary care setting in Leeds had their PL updated when they were transferred with an existing English electronic medical record. The content of the PL was later analysed by looking for the number of items in both lists (active and inactive), for the presence of duplicates and synonyms, and for items that needed to be added. It is normal practice to review the records at the time of transfer, usually by a nurse or healthcare assistant, but it was done by a general practitioner (GP) aiming to maximise the quality of the final PL. Results: Of the 175 newly registered patients studied, 3077 PL items were collected. Active PL included an average of 5.7 entries per patient, while inactive PL had an average of 11.8 entries. The number of duplicates per patient was about 1.8, while the number of synonyms was around 1.2. Unnecessary items were common. When records were reconciled, there was a 66.7% reduction in active PL entries and an 86.4% reduction in inactive entries. Discussion: Handover of PL among family physicians fails to transfer high-quality data. Different organisations follow distinct patterns in the use of PL. Major changes may be required to improve the flow of accurate, concise and up-to-date information. It could be argued that without further training, the use of clear guidelines or better support from health informatics, the PL will not provide the important summary information that clinicians need, which will affect clinicians' decision-making and to the detriment of patients.
{"title":"An audit on problem lists transfers in general practice in Leeds, United Kingdom","authors":"Pablo Millares Martin","doi":"10.55976/jdh.22023119882-87","DOIUrl":"https://doi.org/10.55976/jdh.22023119882-87","url":null,"abstract":"Background: Problem-oriented medical records are the standard among electronic health records (EHR) but after 50 years of use, problem lists (PL) do not seem to be the solution to clinicians' information needs. Objectives: To perform a quality improvement evaluation of PL content, considering available guidelines on its characteristics (accuracy, clarity, concision, currency) when transferring patients from one primary care organisation in England to another in Leeds. The standard should simply be the need to confirm currency. PL should be ready to be used safely after a brief check-up. Methods: During six months, all patients registering at a primary care setting in Leeds had their PL updated when they were transferred with an existing English electronic medical record. The content of the PL was later analysed by looking for the number of items in both lists (active and inactive), for the presence of duplicates and synonyms, and for items that needed to be added. It is normal practice to review the records at the time of transfer, usually by a nurse or healthcare assistant, but it was done by a general practitioner (GP) aiming to maximise the quality of the final PL. Results: Of the 175 newly registered patients studied, 3077 PL items were collected. Active PL included an average of 5.7 entries per patient, while inactive PL had an average of 11.8 entries. The number of duplicates per patient was about 1.8, while the number of synonyms was around 1.2. Unnecessary items were common. When records were reconciled, there was a 66.7% reduction in active PL entries and an 86.4% reduction in inactive entries. Discussion: Handover of PL among family physicians fails to transfer high-quality data. Different organisations follow distinct patterns in the use of PL. Major changes may be required to improve the flow of accurate, concise and up-to-date information. It could be argued that without further training, the use of clear guidelines or better support from health informatics, the PL will not provide the important summary information that clinicians need, which will affect clinicians' decision-making and to the detriment of patients.","PeriodicalId":131334,"journal":{"name":"Journal of Digital Health","volume":"109 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135138273","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}
Pub Date : 2023-10-30DOI: 10.55976/jdh.22023119463-81
Jessica Jha, Mario Almagro, Hegler Tissot
Financial costs are a major concern in the healthcare system, with medical billing and coding playing a key role in facilitating transactions and financing procedures. Billing involves filing claims with insurance companies and requires scrutiny of clinical summaries and electronic health records to correctly match diagnoses, prescriptions, and procedures to standardized codes. Accuracy in assigning International Classification of Diseases (ICD) codes is critical to proper reimbursement of care. Incorrect codes waste time and resources, and cause administrative and financial problems for hospitals, insurance companies and patients. Manual medical coding is a labor-intensive and error-prone process that creates additional administrative burden and inconvenience for hospitals, insurance companies, and patients. To simplify the process, clinical records are often processed to automatically identify and extract clinical concepts and corresponding ICD codes. Deep learning and natural language processing techniques have shown promise in a variety of tasks but applying them to medical coding has been challenging. Accurate coding requires a deep understanding of medical terminology, context, and guidelines that may be difficult to capture with traditional deep learning methods. Although deep learning shows promise in healthcare, its specific impact on ICD coding is not fully understood, and translating scalable deep learning methods into practical improvements in ICD coding remains a challenge. Evaluating deep learning models under the scenarios of real-world coding and comparing them to established practice is critical to determining their true effectiveness. In this work, we address the automation of ICD coding by highlighting pitfalls and contrasting different perspectives. We investigated automatic ICD coding using baseline machine learning models, with a focus on identifying ICD-9 codes in discharge notes from Medical Information Mart for Intensive Care (MIMIC) database. A thorough evaluation of different models and approaches is crucial to avoid over-reliance on any method. Our findings show that simpler methods can achieve comparable results to deep learning models while still requiring fewer computational resources.
{"title":"Designing NLP applications to support ICD coding: an impact analysis and guidelines to enhance baseline performance when processing patient discharge notes","authors":"Jessica Jha, Mario Almagro, Hegler Tissot","doi":"10.55976/jdh.22023119463-81","DOIUrl":"https://doi.org/10.55976/jdh.22023119463-81","url":null,"abstract":"Financial costs are a major concern in the healthcare system, with medical billing and coding playing a key role in facilitating transactions and financing procedures. Billing involves filing claims with insurance companies and requires scrutiny of clinical summaries and electronic health records to correctly match diagnoses, prescriptions, and procedures to standardized codes. Accuracy in assigning International Classification of Diseases (ICD) codes is critical to proper reimbursement of care. Incorrect codes waste time and resources, and cause administrative and financial problems for hospitals, insurance companies and patients. Manual medical coding is a labor-intensive and error-prone process that creates additional administrative burden and inconvenience for hospitals, insurance companies, and patients. To simplify the process, clinical records are often processed to automatically identify and extract clinical concepts and corresponding ICD codes. Deep learning and natural language processing techniques have shown promise in a variety of tasks but applying them to medical coding has been challenging. Accurate coding requires a deep understanding of medical terminology, context, and guidelines that may be difficult to capture with traditional deep learning methods. Although deep learning shows promise in healthcare, its specific impact on ICD coding is not fully understood, and translating scalable deep learning methods into practical improvements in ICD coding remains a challenge. Evaluating deep learning models under the scenarios of real-world coding and comparing them to established practice is critical to determining their true effectiveness. In this work, we address the automation of ICD coding by highlighting pitfalls and contrasting different perspectives. We investigated automatic ICD coding using baseline machine learning models, with a focus on identifying ICD-9 codes in discharge notes from Medical Information Mart for Intensive Care (MIMIC) database. A thorough evaluation of different models and approaches is crucial to avoid over-reliance on any method. Our findings show that simpler methods can achieve comparable results to deep learning models while still requiring fewer computational resources.","PeriodicalId":131334,"journal":{"name":"Journal of Digital Health","volume":"25 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136068125","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}
Pub Date : 2023-06-28DOI: 10.55976/jdh.22023116330-62
C. Ejiyi, Zhen Qin, M. B. Ejiyi, G. Nneji, H. Monday, Favour Amarachi Agu, Thomas Ugochukwu Ejiyi, Chidinma N. Diokpo, C. Orakwue
The widespread adoption of Internet of Things (IoT) technologies across various domains has given rise to the Internet of Medical Things (IoMT), which has significantly enhanced the accuracy and capabilities of electronic devices in producing reliable results applicable to the healthcare industry. To leverage the potential of IoMT in healthcare, a series of interconnected events must take place, starting with edge devices collecting data, followed by data aggregation, processing, and informed decision-making based on data analysis. This review article stems from a collaborative and innovative project conducted by participants in the digital economy, organized by the Department of Software Engineering at Tsinghua University in 2021. The project focused on implementing technologies in various fields, with specific teams dedicated to healthcare. During this project, several gaps were identified, and solutions centered around the IoT were proposed. In this comprehensive review, we extensively investigated IoMT services and applications and emphasized how these applications can be optimally implemented to unlock their potentials. Our survey encompassed over 300 research papers, that examined the implementation of IoMT in domains such as Pharmacy Management and Health Insurance Management. Additionally, we analyzed the key enablers and barriers to the successful implementation of IoMT in recent times. To provide a practical perspective, we presented a feasible case study that applied deep learning to IoMT, considering the security concerns associated with its implementation. Furthermore, we identified future research directions and potential areas of improvement based on the gaps identified from the reviewed literatures. By undertaking this review, we aim to contribute to a deeper understanding of IoMT services and applications, shedding light on their optimal utilization within the healthcare industry. Ultimately, our goal is to facilitate advancements in IoMT implementation and to pave the way for enhanced healthcare delivery and improved patient outcomes.
{"title":"The internet of medical things in healthcare management: a review","authors":"C. Ejiyi, Zhen Qin, M. B. Ejiyi, G. Nneji, H. Monday, Favour Amarachi Agu, Thomas Ugochukwu Ejiyi, Chidinma N. Diokpo, C. Orakwue","doi":"10.55976/jdh.22023116330-62","DOIUrl":"https://doi.org/10.55976/jdh.22023116330-62","url":null,"abstract":"The widespread adoption of Internet of Things (IoT) technologies across various domains has given rise to the Internet of Medical Things (IoMT), which has significantly enhanced the accuracy and capabilities of electronic devices in producing reliable results applicable to the healthcare industry. To leverage the potential of IoMT in healthcare, a series of interconnected events must take place, starting with edge devices collecting data, followed by data aggregation, processing, and informed decision-making based on data analysis. This review article stems from a collaborative and innovative project conducted by participants in the digital economy, organized by the Department of Software Engineering at Tsinghua University in 2021. The project focused on implementing technologies in various fields, with specific teams dedicated to healthcare. During this project, several gaps were identified, and solutions centered around the IoT were proposed. In this comprehensive review, we extensively investigated IoMT services and applications and emphasized how these applications can be optimally implemented to unlock their potentials. Our survey encompassed over 300 research papers, that examined the implementation of IoMT in domains such as Pharmacy Management and Health Insurance Management. Additionally, we analyzed the key enablers and barriers to the successful implementation of IoMT in recent times. To provide a practical perspective, we presented a feasible case study that applied deep learning to IoMT, considering the security concerns associated with its implementation. Furthermore, we identified future research directions and potential areas of improvement based on the gaps identified from the reviewed literatures. By undertaking this review, we aim to contribute to a deeper understanding of IoMT services and applications, shedding light on their optimal utilization within the healthcare industry. Ultimately, our goal is to facilitate advancements in IoMT implementation and to pave the way for enhanced healthcare delivery and improved patient outcomes.","PeriodicalId":131334,"journal":{"name":"Journal of Digital Health","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131928038","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}
Pub Date : 2023-06-21DOI: 10.55976/jdh.22023114022-29
Anish Patial, Aravind Gandhi Periyasamy, S. Rajavel, S. Kathirvel
Purpose: To assess the features/functionalities and quality of the (open access) COVID-19 specific mobile application for India using the Mobile Application Rating Scale (MARS) and the quality of the reported COVID-19 data using the COVID-19 Data Reporting System (CDRS). Methods: We used an analytical, cross-sectional study in which we reviewed all open access (free) mobile phone-based applications across the application stores, namely Google Android Play Store, iTunes and Google search engine. We used MARS and CDRS to assess the mobile applications applicable to India. Results: We found a total of 247 applications through the iTunes store (n=176), android store (n=70) and Google search (n=1). Out of 247, 70 applications matched the inclusion criteria, and only 42 applications were accessible for detailed evaluation using MARS. The overall mean (SD) MARS score was 3.27 (0.59). The mean (SD) score for application mean quality, app subjective quality and app-specific quality domains were 3.43 (0.43), 2.95 (0.71), and 3.44 (0.82), respectively. Of the 20 applications evaluated using CDRS, Aarogya (Agra) Sarvam Setu and Odisha COVID had the highest normalized score (0.9), whereas Madhya Pradesh COVID response app and WHO Academy COVID-19 had the lowest (0.1). Conclusion: Though the overall quality of the mobile applications is good, the engagement aspect of the mobile application quality needs improvement. Applications providing comprehensive COVID-19 related services are still lacking. The necessity of the hour is to assess the user’s perspective and the impact of application features on COVID-19 prevention and control, either individually or in groups.
目的:使用移动应用程序评级量表(MARS)评估印度COVID-19特定(开放获取)移动应用程序的特性/功能和质量，并使用COVID-19数据报告系统(CDRS)评估报告的COVID-19数据的质量。方法:我们采用了一项分析性的横断面研究，在该研究中，我们审查了应用商店中所有开放访问(免费)的基于手机的应用程序，即Google Android Play Store、iTunes和Google搜索引擎。我们使用MARS和CDRS来评估适用于印度的移动应用程序。结果:我们通过iTunes store (n=176)、android store (n=70)和Google search (n=1)共找到247个应用程序。在247个应用程序中，有70个应用程序符合纳入标准，只有42个应用程序可以使用MARS进行详细评估。总平均(SD) MARS评分为3.27(0.59)。应用程序平均质量、应用程序主观质量和应用程序特定质量域的平均(SD)得分分别为3.43(0.43)、2.95(0.71)和3.44(0.82)。在使用CDRS评估的20个应用程序中，阿罗吉亚(阿格拉)萨瓦姆塞图和奥里萨邦COVID的标准化得分最高(0.9)，而中央邦COVID响应应用程序和世卫组织COVID-19学院的标准化得分最低(0.1)。结论:虽然手机应用的整体质量良好，但用户粘性方面的质量有待提高。提供新型冠状病毒综合服务的应用程序仍然缺乏。这一小时的必要性是评估用户的观点和应用程序功能对COVID-19防控的影响，无论是个人还是群体。
{"title":"Evaluation of open access COVID-19 related mobile applications in India: An application store-based quantitative analysis","authors":"Anish Patial, Aravind Gandhi Periyasamy, S. Rajavel, S. Kathirvel","doi":"10.55976/jdh.22023114022-29","DOIUrl":"https://doi.org/10.55976/jdh.22023114022-29","url":null,"abstract":"Purpose: To assess the features/functionalities and quality of the (open access) COVID-19 specific mobile application for India using the Mobile Application Rating Scale (MARS) and the quality of the reported COVID-19 data using the COVID-19 Data Reporting System (CDRS).\u0000Methods: We used an analytical, cross-sectional study in which we reviewed all open access (free) mobile phone-based applications across the application stores, namely Google Android Play Store, iTunes and Google search engine. We used MARS and CDRS to assess the mobile applications applicable to India.\u0000Results: We found a total of 247 applications through the iTunes store (n=176), android store (n=70) and Google search (n=1). Out of 247, 70 applications matched the inclusion criteria, and only 42 applications were accessible for detailed evaluation using MARS. The overall mean (SD) MARS score was 3.27 (0.59). The mean (SD) score for application mean quality, app subjective quality and app-specific quality domains were 3.43 (0.43), 2.95 (0.71), and 3.44 (0.82), respectively. Of the 20 applications evaluated using CDRS, Aarogya (Agra) Sarvam Setu and Odisha COVID had the highest normalized score (0.9), whereas Madhya Pradesh COVID response app and WHO Academy COVID-19 had the lowest (0.1).\u0000Conclusion: Though the overall quality of the mobile applications is good, the engagement aspect of the mobile application quality needs improvement. Applications providing comprehensive COVID-19 related services are still lacking. The necessity of the hour is to assess the user’s perspective and the impact of application features on COVID-19 prevention and control, either individually or in groups.","PeriodicalId":131334,"journal":{"name":"Journal of Digital Health","volume":"39 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120906063","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}
Pub Date : 2023-06-20DOI: 10.55976/jdh.22023113912-21
Ablameyko Maria, S. Ablameyko
Artificial intelligence (AI) is starting to be widely used in the medical field and has great potential benefits to help doctors and patients. However, it also raises new challenges and problems. This paper analyzed the existing capacities of AI to make a diagnosis and assessed the legal consequences. We present AI medical image analysis systems developed in Belarus. International practice on how AI-systems are implemented in medicine is analyzed. Russian experience in developing standards to test and use AI systems in hospitals is described. Finally, the paper put forward some suggestions on how to improve the legal framework of AI systems using in medicine.
{"title":"AI image-based diagnosis systems: how to implement them?","authors":"Ablameyko Maria, S. Ablameyko","doi":"10.55976/jdh.22023113912-21","DOIUrl":"https://doi.org/10.55976/jdh.22023113912-21","url":null,"abstract":"Artificial intelligence (AI) is starting to be widely used in the medical field and has great potential benefits to help doctors and patients. However, it also raises new challenges and problems. This paper analyzed the existing capacities of AI to make a diagnosis and assessed the legal consequences. We present AI medical image analysis systems developed in Belarus. International practice on how AI-systems are implemented in medicine is analyzed. Russian experience in developing standards to test and use AI systems in hospitals is described. Finally, the paper put forward some suggestions on how to improve the legal framework of AI systems using in medicine.","PeriodicalId":131334,"journal":{"name":"Journal of Digital Health","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117129862","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}
Pub Date : 2023-03-24DOI: 10.55976/jdh.2202311501-11
P. Fritz, R. Raoufi, P. Dalquen, A. Sediqi, S. Müller, J. Mollin, S. Goletz, J. Dippon, M. Hubler, T. Aeppel, B. Soudah, H. Firooz, M. Weinhara, I. Fabian de Barreto, C. Aichmüller, G. Stauch
Abstract: Purpose: Since 2010, physicians from Afghanistan have been uploading images of histological and cytological specimens to a telemedicine internet platform (iPath network) for expert evaluation. From this collective work, all cases with fine-needle aspirations (FNA) of mammary gland diseases were extracted and analyzed. The aim of the present retrospective feasibility study is to investigate the utility of artificial intelligence assisted diagnoses in fine-needle aspiration (FNA) of breast diseases.Material and Methods: A total of 3304 microphotographic images from 438 patients of smears from FNA of the mammary gland were available for this study. Telemedical expert diagnoses from 4 experienced cytopathologists were available in all 438 cases. Their diagnosis (malignant tumor of the mammary gland or benign mammary gland disease) was set as the gold standard. AI analysis was performed using i) clinical context data and ii) two different image recognition methods to determine the probability values for the presence of malignant breast tumor. Youden index and AUC (area under the curve) were used to evaluate test performance. Results: A score for invasive breast cancer (IBC) calculated from contextual variables agreed with the expert diagnosis (accuracy) in 85.2% and with the two image recognition systems in 78.4% and 65.2%. This simplifies health healthcare management of breast diseases in low income countries as in many patients the less expensive and less time-consuming technique of FNA may replace a histological examination.Conclusion: Image classification and analysis of context variables can be used to test the validity and plausibility of cytologic diagnoses, especially when cytologic interpretation has to be performed by people who are inexperienced in cytopathology.
{"title":"Artificial intelligence assisted diagnoses of fine-needle aspiration of breast diseases: a single-center experience","authors":"P. Fritz, R. Raoufi, P. Dalquen, A. Sediqi, S. Müller, J. Mollin, S. Goletz, J. Dippon, M. Hubler, T. Aeppel, B. Soudah, H. Firooz, M. Weinhara, I. Fabian de Barreto, C. Aichmüller, G. Stauch","doi":"10.55976/jdh.2202311501-11","DOIUrl":"https://doi.org/10.55976/jdh.2202311501-11","url":null,"abstract":"Abstract: Purpose: Since 2010, physicians from Afghanistan have been uploading images of histological and cytological specimens to a telemedicine internet platform (iPath network) for expert evaluation. From this collective work, all cases with fine-needle aspirations (FNA) of mammary gland diseases were extracted and analyzed. The aim of the present retrospective feasibility study is to investigate the utility of artificial intelligence assisted diagnoses in fine-needle aspiration (FNA) of breast diseases.Material and Methods: A total of 3304 microphotographic images from 438 patients of smears from FNA of the mammary gland were available for this study. Telemedical expert diagnoses from 4 experienced cytopathologists were available in all 438 cases. Their diagnosis (malignant tumor of the mammary gland or benign mammary gland disease) was set as the gold standard. AI analysis was performed using i) clinical context data and ii) two different image recognition methods to determine the probability values for the presence of malignant breast tumor. Youden index and AUC (area under the curve) were used to evaluate test performance. Results: A score for invasive breast cancer (IBC) calculated from contextual variables agreed with the expert diagnosis (accuracy) in 85.2% and with the two image recognition systems in 78.4% and 65.2%. This simplifies health healthcare management of breast diseases in low income countries as in many patients the less expensive and less time-consuming technique of FNA may replace a histological examination.Conclusion: Image classification and analysis of context variables can be used to test the validity and plausibility of cytologic diagnoses, especially when cytologic interpretation has to be performed by people who are inexperienced in cytopathology.","PeriodicalId":131334,"journal":{"name":"Journal of Digital Health","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122270551","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}
In recent years, thanks to the dawn of big data, the substantial improvement in computing power, and breakthroughs in algorithm research, artificial intelligence has developed rapidly, and remarkable progress has also been made in its application in medicine. In the field of respiratory medicine, the auxiliary diagnosis of lung cancer is currently the topic on which medical artificial intelligence is the most studied. Therefore, this paper mainly focuses on the diagnosis procedure of lung cancer, and comprehensively summarizes the application of artificial intelligence in the segmentation and detection of pulmonary nodules, classification of benign/malignant pulmonary nodules and intrathoracic lymph nodes, classification of lung cancer pathological images, and lung cancer prognosis analysis. In addition, the application of artificial intelligence in other respiratory diseases such as COVID-19, pneumothorax and pleural effusion is briefly introduced. In summary, artificial intelligence is widely used in the auxiliary diagnosis of respiratory diseases, and has a great potential to become a valuable assistant to respiratory physicians in the near future.
{"title":"Application of artificial intelligence in respiratory medicine","authors":"Chunxi Zhang, Weijin Wu, Jia Yang, Jiayuan Sun","doi":"10.55976/jdh.20221153","DOIUrl":"https://doi.org/10.55976/jdh.20221153","url":null,"abstract":"In recent years, thanks to the dawn of big data, the substantial improvement in computing power, and breakthroughs in algorithm research, artificial intelligence has developed rapidly, and remarkable progress has also been made in its application in medicine. In the field of respiratory medicine, the auxiliary diagnosis of lung cancer is currently the topic on which medical artificial intelligence is the most studied. Therefore, this paper mainly focuses on the diagnosis procedure of lung cancer, and comprehensively summarizes the application of artificial intelligence in the segmentation and detection of pulmonary nodules, classification of benign/malignant pulmonary nodules and intrathoracic lymph nodes, classification of lung cancer pathological images, and lung cancer prognosis analysis.\u0000In addition, the application of artificial intelligence in other respiratory diseases such as COVID-19, pneumothorax and pleural effusion is briefly introduced. In summary, artificial intelligence is widely used in the auxiliary diagnosis of respiratory diseases, and has a great potential to become a valuable assistant to respiratory physicians in the near future.","PeriodicalId":131334,"journal":{"name":"Journal of Digital Health","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114828844","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: The mucosal changes of early gastric cancers (EGC) are slight and difficult to be recognized, leading to a high miss rate. Artificial intelligence (AI) systems have the potential to improve the detection rate of EGC. Here, we reported a case of EGC discovered by an endoscopist with the assistance of an AI system. Case presentation: A 67-year-old male patient came to our hospital for Esophagogastroduodenoscopy (EGD) due to a routine physical examination. He had previously been healthy but was treated for a Helicobacter pylori infection two years ago. In the process of EGD, the AI system flagged a tiny mucosal lesion that was far away and was not detected by the endoscopist, and this lesion attracted the endoscopist's additional attention. After the close observation of the lesion, the AI system immediately gave a red prompt box, suggesting that the endoscopist further observe it. Under magnifying endoscopy with narrow-band imaging (ME-NBI), the mucosal glands and blood vessels of the lesion were found to be irregular, and this patient was diagnosed with suspicious gastric carcinoma by AI. Biopsy pathology showed that it was high-grade intraepithelial neoplasia, and after endoscopic mucosal dissection (ESD), post-ESD histology confirmed that the lesion was a highly differentiated adenocarcinoma confined to the mucosa, with a lesion range of 1.1 cm × 1.0 cm. The patient was discharged from the hospital without any postoperative complications. Conclusion: AI has been widely applied in the field of gastrointestinal endoscopy and has the potential to help improve the detection rate of early gastrointestinal cancers. We reported a case of early gastric cancer discovered by the endoscopist with the assistance of AI.
背景:早期胃癌(EGC)的粘膜变化轻微且难以识别，导致高漏诊率。人工智能(AI)系统有可能提高EGC的检出率。在这里，我们报告了一个由内窥镜医生在人工智能系统的帮助下发现的EGC病例。病例介绍:一名67岁男性患者因常规体检来我院行食管胃十二指肠镜检查。他之前一直很健康，但两年前因幽门螺杆菌感染接受了治疗。在EGD的过程中，AI系统发现了一个很小的粘膜病变，这个病变很远，内镜医生没有发现，这个病变引起了内镜医生的额外关注。近距离观察病变后，AI系统立即给出红色提示框，提示内镜医师进一步观察。在狭窄带放大内镜(ME-NBI)下，病变处粘膜腺体及血管不规则，经AI诊断为可疑胃癌。活检病理显示为高级别上皮内瘤变，内镜下粘膜剥离(ESD)后组织学证实病变为局限于粘膜的高分化腺癌，病变范围1.1 cm × 1.0 cm。患者出院，无术后并发症。结论:人工智能在胃肠道内镜领域已得到广泛应用，具有提高早期胃肠道肿瘤检出率的潜力。我们报告了一例由内镜医师在人工智能辅助下发现的早期胃癌。
{"title":"An artificial intelligence-based system assisted endoscopists to detect early gastric cancer: a case report","authors":"Jiejun Lin, Xiao Tao, Jie Pan","doi":"10.55976/jdh.20221145","DOIUrl":"https://doi.org/10.55976/jdh.20221145","url":null,"abstract":"Background: The mucosal changes of early gastric cancers (EGC) are slight and difficult to be recognized, leading to a high miss rate. Artificial intelligence (AI) systems have the potential to improve the detection rate of EGC. Here, we reported a case of EGC discovered by an endoscopist with the assistance of an AI system.\u0000 \u0000Case presentation: A 67-year-old male patient came to our hospital for Esophagogastroduodenoscopy (EGD) due to a routine physical examination. He had previously been healthy but was treated for a Helicobacter pylori infection two years ago. In the process of EGD, the AI system flagged a tiny mucosal lesion that was far away and was not detected by the endoscopist, and this lesion attracted the endoscopist's additional attention. After the close observation of the lesion, the AI system immediately gave a red prompt box, suggesting that the endoscopist further observe it. Under magnifying endoscopy with narrow-band imaging (ME-NBI), the mucosal glands and blood vessels of the lesion were found to be irregular, and this patient was diagnosed with suspicious gastric carcinoma by AI. Biopsy pathology showed that it was high-grade intraepithelial neoplasia, and after endoscopic mucosal dissection (ESD), post-ESD histology confirmed that the lesion was a highly differentiated adenocarcinoma confined to the mucosa, with a lesion range of 1.1 cm × 1.0 cm. The patient was discharged from the hospital without any postoperative complications.\u0000 \u0000Conclusion: AI has been widely applied in the field of gastrointestinal endoscopy and has the potential to help improve the detection rate of early gastrointestinal cancers. We reported a case of early gastric cancer discovered by the endoscopist with the assistance of AI.\u0000 ","PeriodicalId":131334,"journal":{"name":"Journal of Digital Health","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128589194","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}
Pub Date : 2022-02-21DOI: 10.55976/jdh.1202214319-24
Conghui Shi, Jia Li, Lianlian Wu
Aims: This study aimed to explore the effect of training set diversity on the performance of deep learning models for predicting early gastric cancer (EGC) under endoscopy. Methods: Images of EGC and non-cancerous lesions under narrow-band imaging (ME-NBI) and magnifying blue laser imaging (ME-BLI) were retrospectively collected. Training set 1 was composed of 150 non-cancerous and 309 EGC ME-NBI images, training set 2 was composed of 1505 non-cancerous and 309 EGC ME-BLI images, and training set 3 was the combination of training set 1 and 2. Test set 1 was composed of 376 non-cancerous and 1052 EGC ME-NBI images, test set 2 consisted of 529 non-cancerous and 71 EGC ME-BLI images, and test set 3 was the combination of test set 1 and test set 2. Three deep learning models, convolutional neural network (CNN) 1, CNN 2 and CNN 3 (CNN 1, CNN 2 and CNN 3 were independently trained using training set 1, training set 2 and training set 3, respectively), were constructed, and their performances on each test set were respectively evaluated. One hundred and thirty-eight ME-NBI videos and 17 ME-BLI videos were further collected to evaluate and compare the performance of each model in real time. Results: On the whole, the performance of CNN 3 was the best. The accuracy (Acc), sensitivity (Sn), specificity (Sp) and area under the curve (AUC) of test set 1 in CNN 3 were 87.89% (1255/1428), 90.96% (342/376), 86.79% (913/1052) and 94.60%, respectively. The Acc, Sn, Sp and AUC of test set 2 in CNN 3 were 95% (570/600), 97.92% (518/529), 73.24% (52/71) and 90.93% respectively. The Acc, Sn, Sp and AUC of test set 3 in CNN 3 were 89.99% (1825/2028), 95.03% (860/905), 85.93% (965/1123) and 94.89%, respectively. The performance of CNN 3 was also the best in videos test set. The Acc, Sn and Sp of videos test set in CNN 3 were 91.03% (142/156), 90.58% (125/138) and 94.44% (17/18), respectively. Conclusions: The deep learning model with the most diverse training data has the best diagnostic effect.
{"title":"The effect of data diversity on the performance of deep learning models for predicting early gastric cancer under endoscopy","authors":"Conghui Shi, Jia Li, Lianlian Wu","doi":"10.55976/jdh.1202214319-24","DOIUrl":"https://doi.org/10.55976/jdh.1202214319-24","url":null,"abstract":" \u0000Aims: This study aimed to explore the effect of training set diversity on the performance of deep learning models for predicting early gastric cancer (EGC) under endoscopy.\u0000Methods: Images of EGC and non-cancerous lesions under narrow-band imaging (ME-NBI) and magnifying blue laser imaging (ME-BLI) were retrospectively collected. Training set 1 was composed of 150 non-cancerous and 309 EGC ME-NBI images, training set 2 was composed of 1505 non-cancerous and 309 EGC ME-BLI images, and training set 3 was the combination of training set 1 and 2. Test set 1 was composed of 376 non-cancerous and 1052 EGC ME-NBI images, test set 2 consisted of 529 non-cancerous and 71 EGC ME-BLI images, and test set 3 was the combination of test set 1 and test set 2. Three deep learning models, convolutional neural network (CNN) 1, CNN 2 and CNN 3 (CNN 1, CNN 2 and CNN 3 were independently trained using training set 1, training set 2 and training set 3, respectively), were constructed, and their performances on each test set were respectively evaluated. One hundred and thirty-eight ME-NBI videos and 17 ME-BLI videos were further collected to evaluate and compare the performance of each model in real time.\u0000Results: On the whole, the performance of CNN 3 was the best. The accuracy (Acc), sensitivity (Sn), specificity (Sp) and area under the curve (AUC) of test set 1 in CNN 3 were 87.89% (1255/1428), 90.96% (342/376), 86.79% (913/1052) and 94.60%, respectively. The Acc, Sn, Sp and AUC of test set 2 in CNN 3 were 95% (570/600), 97.92% (518/529), 73.24% (52/71) and 90.93% respectively. The Acc, Sn, Sp and AUC of test set 3 in CNN 3 were 89.99% (1825/2028), 95.03% (860/905), 85.93% (965/1123) and 94.89%, respectively. The performance of CNN 3 was also the best in videos test set. The Acc, Sn and Sp of videos test set in CNN 3 were 91.03% (142/156), 90.58% (125/138) and 94.44% (17/18), respectively.\u0000Conclusions: The deep learning model with the most diverse training data has the best diagnostic effect.","PeriodicalId":131334,"journal":{"name":"Journal of Digital Health","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127197009","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}
Pub Date : 2022-02-18DOI: 10.55976/jdh.120221521-2
Honggang Yu
As the Editor-in-Chief of the newly founded journal the Journal of Digital Health (JDH), I am honored to introduce this journal to you on behalf of Luminescience Press Ltd. JDH is an open access and peer-reviewed journal that publishes high-quality original articles from a wide variety of interdisciplinary perspectives concerning the theory and practice of artificial intelligence (AI), big data and informatics in the medical and healthcare industries to improve the quality and efficiency of healthcare. The journal publishes original articles, reviews, perspectives, research highlights and case reports that present the application of digital technologies in medical diagnostics and treatment, medical devices, machine learning-based decision support, medical record database and intelligent and process-aware information system in healthcare and medicine. We are committed to promoting the interdisciplinary research among clinicians, basic scientists and industrial experts and facilitating the clinical transformation of industrial technologies. Our ultimate mission is to enable the frontiers of science and technology better serve medicine and ultimately contribute to the healthcare of patients.
作为新创办的期刊《journal of Digital Health》(JDH)的总编辑，我很荣幸代表Luminescience Press ltd .向大家介绍这本杂志。JDH是一本开放获取、同行评议的期刊，从各种跨学科的角度发表关于人工智能(AI)的理论和实践的高质量原创文章。大数据和信息学应用于医疗保健行业，提高医疗保健质量和效率。该杂志发表原创文章、评论、观点、研究亮点和案例报告，介绍数字技术在医疗诊断和治疗、医疗设备、基于机器学习的决策支持、病历数据库和智能和流程感知信息系统等方面的应用。我们致力于推动临床医生、基础科学家和产业专家之间的跨学科研究，促进产业技术的临床转化。我们的终极使命是让前沿科技更好地服务于医学，最终为患者的健康做出贡献。
{"title":"Inauguration of a unique journal the Journal of Digital Health: a new beginning seeking innovative technology and research for digital health","authors":"Honggang Yu","doi":"10.55976/jdh.120221521-2","DOIUrl":"https://doi.org/10.55976/jdh.120221521-2","url":null,"abstract":"As the Editor-in-Chief of the newly founded journal the Journal of Digital Health (JDH), I am honored to introduce this journal to you on behalf of Luminescience Press Ltd.\u0000JDH is an open access and peer-reviewed journal that publishes high-quality original articles from a wide variety of interdisciplinary perspectives concerning the theory and practice of artificial intelligence (AI), big data and informatics in the medical and healthcare industries to improve the quality and efficiency of healthcare. The journal publishes original articles, reviews, perspectives, research highlights and case reports that present the application of digital technologies in medical diagnostics and treatment, medical devices, machine learning-based decision support, medical record database and intelligent and process-aware information system in healthcare and medicine. We are committed to promoting the interdisciplinary research among clinicians, basic scientists and industrial experts and facilitating the clinical transformation of industrial technologies. Our ultimate mission is to enable the frontiers of science and technology better serve medicine and ultimately contribute to the healthcare of patients. ","PeriodicalId":131334,"journal":{"name":"Journal of Digital Health","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127961945","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：