Richard Hr Roberts, Stephen R Ali, Hayley A Hutchings, Thomas D Dobbs, Iain S Whitaker
{"title":"Comparative study of ChatGPT and human evaluators on the assessment of medical literature according to recognised reporting standards.","authors":"Richard Hr Roberts, Stephen R Ali, Hayley A Hutchings, Thomas D Dobbs, Iain S Whitaker","doi":"10.1136/bmjhci-2023-100830","DOIUrl":"10.1136/bmjhci-2023-100830","url":null,"abstract":"Introduction Amid clinicians’ challenges in staying updated with medical research, artificial intelligence (AI) tools like the large language model (LLM) ChatGPT could automate appraisal of research quality, saving time and reducing bias. This study compares the proficiency of ChatGPT3 against human evaluation in scoring abstracts to determine its potential as a tool for evidence synthesis. Methods We compared ChatGPT’s scoring of implant dentistry abstracts with human evaluators using the Consolidated Standards of Reporting Trials for Abstracts reporting standards checklist, yielding an overall compliance score (OCS). Bland-Altman analysis assessed agreement between human and AI-generated OCS percentages. Additional error analysis included mean difference of OCS subscores, Welch’s t-test and Pearson’s correlation coefficient. Results Bland-Altman analysis showed a mean difference of 4.92% (95% CI 0.62%, 0.37%) in OCS between human evaluation and ChatGPT. Error analysis displayed small mean differences in most domains, with the highest in ‘conclusion’ (0.764 (95% CI 0.186, 0.280)) and the lowest in ‘blinding’ (0.034 (95% CI 0.818, 0.895)). The strongest correlations between were in ‘harms’ (r=0.32, p<0.001) and ‘trial registration’ (r=0.34, p=0.002), whereas the weakest were in ‘intervention’ (r=0.02, p<0.001) and ‘objective’ (r=0.06, p<0.001). Conclusion LLMs like ChatGPT can help automate appraisal of medical literature, aiding in the identification of accurately reported research. Possible applications of ChatGPT include integration within medical databases for abstract evaluation. Current limitations include the token limit, restricting its usage to abstracts. As AI technology advances, future versions like GPT4 could offer more reliable, comprehensive evaluations, enhancing the identification of high-quality research and potentially improving patient outcomes.","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10583079/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41190771","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":"Time to treat the climate and nature crisis as one indivisible global health emergency.","authors":"Chris Zielinski","doi":"10.1136/bmjhci-2023-100938","DOIUrl":"10.1136/bmjhci-2023-100938","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10603532/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50160603","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}
Oscar Mosquera Dussan, Eduardo Tuta-Quintero, Daniel A Botero-Rosas
{"title":"Signal processing and machine learning algorithm to classify anaesthesia depth.","authors":"Oscar Mosquera Dussan, Eduardo Tuta-Quintero, Daniel A Botero-Rosas","doi":"10.1136/bmjhci-2023-100823","DOIUrl":"10.1136/bmjhci-2023-100823","url":null,"abstract":"<p><strong>Background: </strong>Poor assessment of anaesthetic depth (AD) has led to overdosing or underdosing of the anaesthetic agent, which requires continuous monitoring to avoid complications. The evaluation of the central nervous system activity and autonomic nervous system could provide additional information on the monitoring of AD during surgical procedures.</p><p><strong>Methods: </strong>Observational analytical single-centre study, information on biological signals was collected during a surgical procedure under general anaesthesia for signal preprocessing, processing and postprocessing to feed a pattern classifier and determine AD status of patients. The development of the electroencephalography index was carried out through data processing and algorithm development using MATLAB V.8.1.</p><p><strong>Results: </strong>A total of 25 men and 35 women were included, with a total time of procedure average of 109.62 min. The results show a high Pearson correlation between the Complexity Brainwave Index and the indices of the entropy module. A greater dispersion is observed in the state entropy and response entropy indices, a partial overlap can also be seen in the boxes associated with deep anaesthesia and general anaesthesia in these indices. A high Pearson correlation might be explained by the coinciding values corresponding to the awake and general anaesthesia states. A high Pearson correlation might be explained by the coinciding values corresponding to the awake and general anaesthesia states.</p><p><strong>Conclusion: </strong>Biological signal filtering and a machine learning algorithm may be used to classify AD during a surgical procedure. Further studies will be needed to confirm these results and improve the decision-making of anaesthesiologists in general anaesthesia.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/ed/86/bmjhci-2023-100823.PMC10551974.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41103815","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":"Digital health and care: emerging from pandemic times.","authors":"Niels Peek, Mark Sujan, Philip Scott","doi":"10.1136/bmjhci-2023-100861","DOIUrl":"10.1136/bmjhci-2023-100861","url":null,"abstract":"<p><p>In 2020, we published an editorial about the massive disruption of health and care services caused by the COVID-19 pandemic and the rapid changes in digital service delivery, artificial intelligence and data sharing that were taking place at the time. Now, 3 years later, we describe how these developments have progressed since, reflect on lessons learnt and consider key challenges and opportunities ahead by reviewing significant developments reported in the literature. As before, the three key areas we consider are digital transformation of services, realising the potential of artificial intelligence and wise data sharing to facilitate learning health systems. We conclude that the field of digital health has rapidly matured during the pandemic, but there are still major sociotechnical, evaluation and trust challenges in the development and deployment of new digital services.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/3f/35/bmjhci-2023-100861.PMC10583078.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41190772","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":"Integrating digital health technologies into complex clinical systems.","authors":"Mark Sujan","doi":"10.1136/bmjhci-2023-100885","DOIUrl":"10.1136/bmjhci-2023-100885","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/ba/18/bmjhci-2023-100885.PMC10583035.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41190773","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":"Mapping loneliness through social intelligence analysis: a step towards creating global loneliness map.","authors":"Hurmat Ali Shah, Mowafa Househ","doi":"10.1136/bmjhci-2022-100728","DOIUrl":"10.1136/bmjhci-2022-100728","url":null,"abstract":"<p><strong>Objectives: </strong>Loneliness is a prevalent global public health concern with complex dynamics requiring further exploration. This study aims to enhance understanding of loneliness dynamics through building towards a global loneliness map using social intelligence analysis.</p><p><strong>Settings and design: </strong>This paper presents a proof of concept for the global loneliness map, using data collected in October 2022. Twitter posts containing keywords such as 'lonely', 'loneliness', 'alone', 'solitude' and 'isolation' were gathered, resulting in 841 796 tweets from the USA. City-specific data were extracted from these tweets to construct a loneliness map for the country. Sentiment analysis using the valence aware dictionary for sentiment reasoning tool was employed to differentiate metaphorical expressions from meaningful correlations between loneliness and socioeconomic and emotional factors.</p><p><strong>Measures and results: </strong>The sentiment analysis encompassed the USA dataset and city-wise subsets, identifying negative sentiment tweets. Psychosocial linguistic features of these negative tweets were analysed to reveal significant connections between loneliness, socioeconomic aspects and emotional themes. Word clouds depicted topic variations between positively and negatively toned tweets. A frequency list of correlated topics within broader socioeconomic and emotional categories was generated from negative sentiment tweets. Additionally, a comprehensive table displayed top correlated topics for each city.</p><p><strong>Conclusions: </strong>Leveraging social media data provide insights into the multifaceted nature of loneliness. Given its subjectivity, loneliness experiences exhibit variability. This study serves as a proof of concept for an extensive global loneliness map, holding implications for global public health strategies and policy development. Understanding loneliness dynamics on a larger scale can facilitate targeted interventions and support.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/8a/b3/bmjhci-2022-100728.PMC10583034.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41190774","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}
Sana F Ali, Yarden Bornovski, Margaret Gopaul, Daniela Galluzzo, Joseph Goulet, Stephanie Argraves, Ebony Jackson-Shaheed, Kei-Hoi Cheung, Cynthia A Brandt, Hamada Hamid Altalib
{"title":"Implementer report: ICD-10 code F44.5 review for functional seizure disorder.","authors":"Sana F Ali, Yarden Bornovski, Margaret Gopaul, Daniela Galluzzo, Joseph Goulet, Stephanie Argraves, Ebony Jackson-Shaheed, Kei-Hoi Cheung, Cynthia A Brandt, Hamada Hamid Altalib","doi":"10.1136/bmjhci-2023-100746","DOIUrl":"10.1136/bmjhci-2023-100746","url":null,"abstract":"<p><strong>Objective: </strong>The study aimed to measure the validity of International Classification of Diseases, 10th Edition (ICD-10) code F44.5 for functional seizure disorder (FSD) in the Veterans Affairs Connecticut Healthcare System electronic health record (VA EHR).</p><p><strong>Methods: </strong>The study used an informatics search tool, a natural language processing algorithm and a chart review to validate FSD coding.</p><p><strong>Results: </strong>The positive predictive value (PPV) for code F44.5 was calculated to be 44%.</p><p><strong>Discussion: </strong>ICD-10 introduced a specific code for FSD to improve coding validity. However, results revealed a meager (44%) PPV for code F44.5. Evaluation of the low diagnostic precision of FSD identified inconsistencies in the ICD-10 and VA EHR systems.</p><p><strong>Conclusion: </strong>Information system improvements may increase the precision of diagnostic coding by clinicians. Specifically, the EHR problem list should include commonly used diagnostic codes and an appropriately curated ICD-10 term list for 'seizure disorder,' and a single ICD code for FSD should be classified under neurology and psychiatry.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/82/62/bmjhci-2023-100746.PMC10514602.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41102964","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":"Long short-term memory model identifies ARDS and in-hospital mortality in both non-COVID-19 and COVID-19 cohort.","authors":"Jen-Ting Chen, Rahil Mehrizi, Boudewijn Aasman, Michelle Ng Gong, Parsa Mirhaji","doi":"10.1136/bmjhci-2023-100782","DOIUrl":"https://doi.org/10.1136/bmjhci-2023-100782","url":null,"abstract":"<p><strong>Objective: </strong>To identify the risk of acute respiratory distress syndrome (ARDS) and in-hospital mortality using long short-term memory (LSTM) framework in a mechanically ventilated (MV) non-COVID-19 cohort and a COVID-19 cohort.</p><p><strong>Methods: </strong>We included MV ICU patients between 2017 and 2018 and reviewed patient records for ARDS and death. Using active learning, we enriched this cohort with MV patients from 2016 to 2019 (MV non-COVID-19, n=3905). We collected a second validation cohort of hospitalised patients with COVID-19 in 2020 (COVID+, n=5672). We trained an LSTM model using 132 structured features on the MV non-COVID-19 training cohort and validated on the MV non-COVID-19 validation and COVID-19 cohorts.</p><p><strong>Results: </strong>Applying LSTM (model score 0.9) on the MV non-COVID-19 validation cohort had a sensitivity of 86% and specificity of 57%. The model identified the risk of ARDS 10 hours before ARDS and 9.4 days before death. The sensitivity (70%) and specificity (84%) of the model on the COVID-19 cohort are lower than MV non-COVID-19 cohort. For the COVID-19 + cohort and MV COVID-19 + patients, the model identified the risk of in-hospital mortality 2.4 days and 1.54 days before death, respectively.</p><p><strong>Discussion: </strong>Our LSTM algorithm accurately and timely identified the risk of ARDS or death in MV non-COVID-19 and COVID+ patients. By alerting the risk of ARDS or death, we can improve the implementation of evidence-based ARDS management and facilitate goals-of-care discussions in high-risk patients.</p><p><strong>Conclusion: </strong>Using the LSTM algorithm in hospitalised patients identifies the risk of ARDS or death.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/9d/16/bmjhci-2023-100782.PMC10503386.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10336909","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}
Agner Russo Parra Sanchez, Max G Grimberg, Myrthe Hanssen, Moon Aben, Elianne Jairth, Prishent Dhoeme, Michel W P Tsang-A-Sjoe, Alexandre Voskuyl, Hendrik Jan Jansen, Ronald van Vollenhoven
{"title":"Web-based eHealth Clinical Decision Support System as a tool for the treat-to-target management of patients with systemic lupus erythematosus: <i>development and initial usability evaluation</i>.","authors":"Agner Russo Parra Sanchez, Max G Grimberg, Myrthe Hanssen, Moon Aben, Elianne Jairth, Prishent Dhoeme, Michel W P Tsang-A-Sjoe, Alexandre Voskuyl, Hendrik Jan Jansen, Ronald van Vollenhoven","doi":"10.1136/bmjhci-2023-100811","DOIUrl":"https://doi.org/10.1136/bmjhci-2023-100811","url":null,"abstract":"<p><strong>Background: </strong>Treat-to-target (T2T) is a therapeutic strategy currently being studied for its application in systemic lupus erythematosus (SLE). Patients and rheumatologists have little support in making the best treatment decision in the context of a T2T strategy, thus, the use of information technology for systematically processing data and supporting information and knowledge may improve routine decision-making practices, helping to deliver value-based care.</p><p><strong>Objective: </strong>To design and develop an online Clinical Decision Support Systems (CDSS) tool \"SLE-T2T\", and test its usability for the implementation of a T2T strategy in the management of patients with SLE.</p><p><strong>Methods: </strong>A prototype of a CDSS was conceived as a web-based application with the task of generating appropriate treatment advice based on entered patients' data. Once developed, a System Usability Score (SUS) questionnaire was implemented to test whether the eHealth tool was user-friendly, comprehensible, easy-to-deliver and workflow-oriented. Data from the participants' comments were synthesised, and the elements in need for improvement were identified.</p><p><strong>Results: </strong>The beta version web-based system was developed based on the interim usability and acceptance evaluation. 7 participants completed the SUS survey. The median SUS score of SLE-T2T was 79 (scale 0 to 100), categorising the application as 'good' and indicating the need for minor improvements to the design.</p><p><strong>Conclusions: </strong>SLE-T2T is the first eHealth tool to be designed for the management of SLE patients in a T2T context. The SUS score and unstructured feedback showed high acceptance of this digital instrument for its future use in a clinical trial.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/ba/70/bmjhci-2023-100811.PMC10533702.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41102965","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}