Pub Date : 2024-08-21DOI: 10.1016/S2589-7500(24)00176-6
{"title":"Correction to Lancet Digit Health 2024; 6: e605–13","authors":"","doi":"10.1016/S2589-7500(24)00176-6","DOIUrl":"10.1016/S2589-7500(24)00176-6","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 9","pages":"Page e604"},"PeriodicalIF":23.8,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001766/pdfft?md5=11bd2424e9355f76c22900c4a010ada2&pid=1-s2.0-S2589750024001766-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142040581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-21DOI: 10.1016/S2589-7500(24)00171-7
Jamie Elvidge , Dalia Dawoud
{"title":"Reporting standards to support cost-effectiveness evaluations of AI-driven health care","authors":"Jamie Elvidge , Dalia Dawoud","doi":"10.1016/S2589-7500(24)00171-7","DOIUrl":"10.1016/S2589-7500(24)00171-7","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 9","pages":"Pages e602-e603"},"PeriodicalIF":23.8,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001717/pdfft?md5=38bf3554f6e2ebc110a0128fd57b4837&pid=1-s2.0-S2589750024001717-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-12DOI: 10.1016/S2589-7500(24)00140-7
Callum Stewart PhD , Yatharth Ranjan MSc , Pauline Conde MSc , Shaoxiong Sun PhD , Yuezhou Zhang PhD , Zulqarnain Rashid PhD , Heet Sankesara BSc , Nicholas Cummins PhD , Petroula Laiou PhD , Xi Bai PhD , Prof Richard J B Dobson PhD , Amos A Folarin PhD
<div><h3>Background</h3><p>The emergence of long COVID as a COVID-19 sequela was largely syndromic in characterisation. Digital health technologies such as wearable devices open the possibility to study this condition with passive, objective data in addition to self-reported symptoms. We aimed to quantify the prevalence and severity of symptoms across collected mobile health metrics over 12 weeks following COVID-19 diagnosis and to identify risk factors for the development of post-COVID-19 condition (also known as long COVID).</p></div><div><h3>Methods</h3><p>The Covid Collab study was a longitudinal, self-enrolled, community, case–control study. We recruited participants from the UK through a smartphone app, media publications, and promotion within the Fitbit app between Aug 28, 2020, and May 31, 2021. Adults (aged ≥18 years) who reported a COVID-19 diagnosis with a positive antigen or PCR test before Feb 1, 2022, were eligible for inclusion. We compared a cohort of 1200 patients who tested positive for COVID-19 with a cohort of 3600 sex-matched and age-matched controls without a COVID-19 diagnosis. Participants could provide information on COVID-19 symptoms and mental health through self-reported questionnaires (active data) and commercial wearable fitness devices (passive data). Data were compared between cohorts at three periods following diagnosis: acute COVID-19 (0–4 weeks), ongoing COVID-19 (4–12 weeks), and post-COVID-19 (12–16 weeks). We assessed sociodemographic and mobile health risk factors for the development of long COVID (defined as either a persistent change in a physiological signal or self-reported symptoms for ≥12 weeks after COVID-19 diagnosis).</p></div><div><h3>Findings</h3><p>By Aug 1, 2022, 17 667 participants had enrolled into the study, of whom 1200 (6·8%) cases and 3600 (20·4%) controls were included in the analyses. Compared with baseline (65 beats per min), resting heart rate increased significantly during the acute (0·47 beats per min; odds ratio [OR] 1·06 [95% CI 1·03–1·09]; p<0·0001), ongoing (0·99 beats per min; 1·11 [1·08–1·14]; p<0·0001), and post-COVID-19 (0·52 beats per min; 1·04 [1·02–1·07]; p=0·0017) phases. An increased level of historical activity in the period from 24 months to 6 months preceding COVID-19 diagnosis was protective against long COVID (coefficient –0·017 [95% CI –0·030 to –0·003]; p=0·015). Depressive symptoms were persistently elevated following COVID-19 (OR 1·03 [95% CI 1·01–1·06]; p=0·0033) and were a potential risk factor for developing long COVID (1·14 [1·07–1·22]; p<0·0001).</p></div><div><h3>Interpretation</h3><p>Mobile health technologies and commercial wearable devices might prove to be a useful resource for tracking recovery from COVID-19 and the prevalence of its long-term sequelae, as well as representing an abundant source of historical data. Mental wellbeing can be impacted negatively for an extended period following COVID-19.</p></div><div><h3>Funding</h3><p>National
{"title":"Physiological presentation and risk factors of long COVID in the UK using smartphones and wearable devices: a longitudinal, citizen science, case–control study","authors":"Callum Stewart PhD , Yatharth Ranjan MSc , Pauline Conde MSc , Shaoxiong Sun PhD , Yuezhou Zhang PhD , Zulqarnain Rashid PhD , Heet Sankesara BSc , Nicholas Cummins PhD , Petroula Laiou PhD , Xi Bai PhD , Prof Richard J B Dobson PhD , Amos A Folarin PhD","doi":"10.1016/S2589-7500(24)00140-7","DOIUrl":"10.1016/S2589-7500(24)00140-7","url":null,"abstract":"<div><h3>Background</h3><p>The emergence of long COVID as a COVID-19 sequela was largely syndromic in characterisation. Digital health technologies such as wearable devices open the possibility to study this condition with passive, objective data in addition to self-reported symptoms. We aimed to quantify the prevalence and severity of symptoms across collected mobile health metrics over 12 weeks following COVID-19 diagnosis and to identify risk factors for the development of post-COVID-19 condition (also known as long COVID).</p></div><div><h3>Methods</h3><p>The Covid Collab study was a longitudinal, self-enrolled, community, case–control study. We recruited participants from the UK through a smartphone app, media publications, and promotion within the Fitbit app between Aug 28, 2020, and May 31, 2021. Adults (aged ≥18 years) who reported a COVID-19 diagnosis with a positive antigen or PCR test before Feb 1, 2022, were eligible for inclusion. We compared a cohort of 1200 patients who tested positive for COVID-19 with a cohort of 3600 sex-matched and age-matched controls without a COVID-19 diagnosis. Participants could provide information on COVID-19 symptoms and mental health through self-reported questionnaires (active data) and commercial wearable fitness devices (passive data). Data were compared between cohorts at three periods following diagnosis: acute COVID-19 (0–4 weeks), ongoing COVID-19 (4–12 weeks), and post-COVID-19 (12–16 weeks). We assessed sociodemographic and mobile health risk factors for the development of long COVID (defined as either a persistent change in a physiological signal or self-reported symptoms for ≥12 weeks after COVID-19 diagnosis).</p></div><div><h3>Findings</h3><p>By Aug 1, 2022, 17 667 participants had enrolled into the study, of whom 1200 (6·8%) cases and 3600 (20·4%) controls were included in the analyses. Compared with baseline (65 beats per min), resting heart rate increased significantly during the acute (0·47 beats per min; odds ratio [OR] 1·06 [95% CI 1·03–1·09]; p<0·0001), ongoing (0·99 beats per min; 1·11 [1·08–1·14]; p<0·0001), and post-COVID-19 (0·52 beats per min; 1·04 [1·02–1·07]; p=0·0017) phases. An increased level of historical activity in the period from 24 months to 6 months preceding COVID-19 diagnosis was protective against long COVID (coefficient –0·017 [95% CI –0·030 to –0·003]; p=0·015). Depressive symptoms were persistently elevated following COVID-19 (OR 1·03 [95% CI 1·01–1·06]; p=0·0033) and were a potential risk factor for developing long COVID (1·14 [1·07–1·22]; p<0·0001).</p></div><div><h3>Interpretation</h3><p>Mobile health technologies and commercial wearable devices might prove to be a useful resource for tracking recovery from COVID-19 and the prevalence of its long-term sequelae, as well as representing an abundant source of historical data. Mental wellbeing can be impacted negatively for an extended period following COVID-19.</p></div><div><h3>Funding</h3><p>National ","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 9","pages":"Pages e640-e650"},"PeriodicalIF":23.8,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001407/pdfft?md5=41fde3576005e91fa40bb70d2e644041&pid=1-s2.0-S2589750024001407-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141976944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-12DOI: 10.1016/S2589-7500(24)00141-9
L Nelson Sanchez-Pinto MD , María del Pilar Arias López MD , Halden Scott MD , Kristen Gibbons PhD , Michael Moor PhD , Prof R Scott Watson MD , Matthew O Wiens PhD , Prof Luregn J Schlapbach MD , Tellen D Bennett MD
The digitisation of health care is offering the promise of transforming the management of paediatric sepsis, which is a major source of morbidity and mortality in children worldwide. Digital technology is already making an impact in paediatric sepsis, but is almost exclusively benefiting patients in high-resource health-care settings. However, digital tools can be highly scalable and cost-effective, and—with the right planning—have the potential to reduce global health disparities. Novel digital solutions, from wearable devices and mobile apps, to electronic health record-embedded decision support tools, have an unprecedented opportunity to transform paediatric sepsis research and care. In this Series paper, we describe the current state of digital solutions in paediatric sepsis around the world, the advances in digital technology that are enabling the development of novel applications, and the potential effect of advances in artificial intelligence in paediatric sepsis research and clinical care.
{"title":"Digital solutions in paediatric sepsis: current state, challenges, and opportunities to improve care around the world","authors":"L Nelson Sanchez-Pinto MD , María del Pilar Arias López MD , Halden Scott MD , Kristen Gibbons PhD , Michael Moor PhD , Prof R Scott Watson MD , Matthew O Wiens PhD , Prof Luregn J Schlapbach MD , Tellen D Bennett MD","doi":"10.1016/S2589-7500(24)00141-9","DOIUrl":"10.1016/S2589-7500(24)00141-9","url":null,"abstract":"<div><p>The digitisation of health care is offering the promise of transforming the management of paediatric sepsis, which is a major source of morbidity and mortality in children worldwide. Digital technology is already making an impact in paediatric sepsis, but is almost exclusively benefiting patients in high-resource health-care settings. However, digital tools can be highly scalable and cost-effective, and—with the right planning—have the potential to reduce global health disparities. Novel digital solutions, from wearable devices and mobile apps, to electronic health record-embedded decision support tools, have an unprecedented opportunity to transform paediatric sepsis research and care. In this Series paper, we describe the current state of digital solutions in paediatric sepsis around the world, the advances in digital technology that are enabling the development of novel applications, and the potential effect of advances in artificial intelligence in paediatric sepsis research and clinical care.</p></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 9","pages":"Pages e651-e661"},"PeriodicalIF":23.8,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001419/pdfft?md5=31f8722a8d750546a71029215e4dfdf0&pid=1-s2.0-S2589750024001419-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141976943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-06DOI: 10.1016/S2589-7500(24)00139-0
Whitney W Au BBiomedSc , Francesco Recchia MSc , Daniel Y Fong PhD , Prof Stephen H S Wong PhD , Derwin K C Chan PhD , Catherine M Capio PhD , Clare C W Yu PhD , Sam W S Wong DPT , Prof Cindy H P Sit PhD , Prof Patrick Ip MD , Prof Ya-Jun Chen PhD , Prof Walter R Thompson PhD , Prof Parco M Siu PhD
<div><h3>Background</h3><p>Physical inactivity in children and adolescents has become a pressing public health concern. Wearable activity trackers can allow self-monitoring of physical activity behaviour and promote autonomous motivation for exercise. However, the effects of wearable trackers on physical activity in young populations remain uncertain.</p></div><div><h3>Methods</h3><p>In this systematic review and meta-analysis, we searched PubMed, Embase, SPORTDiscus, and Web of Science for publications from database inception up to Aug 30, 2023, without restrictions on language. Studies were eligible if they were randomised controlled trials or clustered randomised controlled trials that examined the use of wearable activity trackers to promote physical activity, reduce sedentary behaviours, or promote overall health in participants with a mean age of 19 years or younger, with no restrictions on health condition or study settings. Studies were excluded if children or adolescents were not the primary intervention cohort, or wearable activity trackers were not worn on users’ bodies to objectively track users’ physical activity levels. Two independent reviewers (WWA and FR) assessed eligibility of studies and contacted authors of studies if more information was needed to assess eligibility. We also searched reference lists from relevant systematic reviews and meta-analyses. Systematic review software Covidence was used for study screening and data extraction. Study characteristics including study setting, participant characteristics, intervention characteristics, comparator, and outcome measurements were extracted from eligible studies. The two primary outcomes were objectively measured daily steps and moderate-to-vigorous physical activity. We used a random-effects model with Hartung–Knapp adjustments to calculate standardised mean differences. Between-study heterogeneity was examined using Higgins <em>I</em><sup>2</sup> and Cochran Q statistic. Publication bias was assessed using Egger's regression test. This systematic review was registered with PROSPERO, CRD42023397248.</p></div><div><h3>Findings</h3><p>We identified 9619 studies from our database research and 174 studies from searching relevant systematic reviews and meta-analyses, of which 105 were subjected to full text screening. We included 21 eligible studies, involving 3676 children and adolescents (1618 [44%] were female and 2058 [56%] were male, mean age was 13·7 years [SD 2·7]) in our systematic review and meta-analysis. Ten studies were included in the estimation of the effect of wearable activity trackers on objectively measured daily steps and 11 were included for objectively measured moderate-to-vigorous physical activity. Compared with controls, we found a significant increase in objectively measured daily steps (standardised mean difference 0·37 [95% CI 0·09 to 0·65; p=0·013]; Q 47·60 [p<0·0001]; <em>I</em><sup>2</sup> 72·7% [95% CI 53·4 to 84·0]), but not for moderate-to-vig
{"title":"Effect of wearable activity trackers on physical activity in children and adolescents: a systematic review and meta-analysis","authors":"Whitney W Au BBiomedSc , Francesco Recchia MSc , Daniel Y Fong PhD , Prof Stephen H S Wong PhD , Derwin K C Chan PhD , Catherine M Capio PhD , Clare C W Yu PhD , Sam W S Wong DPT , Prof Cindy H P Sit PhD , Prof Patrick Ip MD , Prof Ya-Jun Chen PhD , Prof Walter R Thompson PhD , Prof Parco M Siu PhD","doi":"10.1016/S2589-7500(24)00139-0","DOIUrl":"10.1016/S2589-7500(24)00139-0","url":null,"abstract":"<div><h3>Background</h3><p>Physical inactivity in children and adolescents has become a pressing public health concern. Wearable activity trackers can allow self-monitoring of physical activity behaviour and promote autonomous motivation for exercise. However, the effects of wearable trackers on physical activity in young populations remain uncertain.</p></div><div><h3>Methods</h3><p>In this systematic review and meta-analysis, we searched PubMed, Embase, SPORTDiscus, and Web of Science for publications from database inception up to Aug 30, 2023, without restrictions on language. Studies were eligible if they were randomised controlled trials or clustered randomised controlled trials that examined the use of wearable activity trackers to promote physical activity, reduce sedentary behaviours, or promote overall health in participants with a mean age of 19 years or younger, with no restrictions on health condition or study settings. Studies were excluded if children or adolescents were not the primary intervention cohort, or wearable activity trackers were not worn on users’ bodies to objectively track users’ physical activity levels. Two independent reviewers (WWA and FR) assessed eligibility of studies and contacted authors of studies if more information was needed to assess eligibility. We also searched reference lists from relevant systematic reviews and meta-analyses. Systematic review software Covidence was used for study screening and data extraction. Study characteristics including study setting, participant characteristics, intervention characteristics, comparator, and outcome measurements were extracted from eligible studies. The two primary outcomes were objectively measured daily steps and moderate-to-vigorous physical activity. We used a random-effects model with Hartung–Knapp adjustments to calculate standardised mean differences. Between-study heterogeneity was examined using Higgins <em>I</em><sup>2</sup> and Cochran Q statistic. Publication bias was assessed using Egger's regression test. This systematic review was registered with PROSPERO, CRD42023397248.</p></div><div><h3>Findings</h3><p>We identified 9619 studies from our database research and 174 studies from searching relevant systematic reviews and meta-analyses, of which 105 were subjected to full text screening. We included 21 eligible studies, involving 3676 children and adolescents (1618 [44%] were female and 2058 [56%] were male, mean age was 13·7 years [SD 2·7]) in our systematic review and meta-analysis. Ten studies were included in the estimation of the effect of wearable activity trackers on objectively measured daily steps and 11 were included for objectively measured moderate-to-vigorous physical activity. Compared with controls, we found a significant increase in objectively measured daily steps (standardised mean difference 0·37 [95% CI 0·09 to 0·65; p=0·013]; Q 47·60 [p<0·0001]; <em>I</em><sup>2</sup> 72·7% [95% CI 53·4 to 84·0]), but not for moderate-to-vig","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 9","pages":"Pages e625-e639"},"PeriodicalIF":23.8,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001390/pdfft?md5=36380a4a62a32c50449fd9f8bf44ceca&pid=1-s2.0-S2589750024001390-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141903278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1016/S2589-7500(24)00099-2
Juliane F Oliveira PhD , Prof Andrêza L Alencar PhD , Maria Célia L S Cunha PhD , Adriano O Vasconcelos PhD , Gerson G Cunha PhD , Ray B Miranda BSc , Fábio M H S Filho BSc , Corbiniano Silva PhD , Emanuele Gustani-Buss PhD , Ricardo Khouri PhD , Thiago Cerqueira-Silva PhD , Prof Luiz Landau PhD , Prof Manoel Barral-Netto MD , Pablo Ivan P Ramos PhD
<div><h3>Background</h3><p>Detecting and foreseeing pathogen dispersion is crucial in preventing widespread disease transmission. Human mobility is a fundamental issue in human transmission of infectious agents. Through a mobility data-driven approach, we aimed to identify municipalities in Brazil that could comprise an advanced sentinel network, allowing for early detection of circulating pathogens and their associated transmission routes.</p></div><div><h3>Methods</h3><p>In this modelling and validation study, we compiled a comprehensive dataset on intercity mobility spanning air, road, and waterway transport from the Brazilian Institute of Geography and Statistics (2016 data), National Transport Confederation (2022), and National Civil Aviation Agency (2017–23). We constructed a graph-based representation of Brazil's mobility network. The Ford–Fulkerson algorithm was used to rank the 5570 Brazilian cities according to their suitability as sentinel locations, allowing us to predict the most suitable locations for early detection and to track the most likely trajectory of a newly emerged pathogen. We also obtained SARS-CoV-2 genetic data from Brazilian municipalities during the early stage (Feb 25–April 30, 2020) of the virus's introduction and the gamma (P.1) variant emergence in Manaus (Jan 6–March 1, 2021), for the purposes of model validation.</p></div><div><h3>Findings</h3><p>We found that flights alone transported 79·9 million (95% CI 58·3–101·4 million) passengers annually within Brazil during 2017–22, with seasonal peaks occurring in late spring and summer, and road and river networks had a maximum capacity of 78·3 million passengers weekly in 2016. By analysing the 7 746 479 most probable paths originating from source nodes, we found that 3857 cities fully cover the mobility pattern of all 5570 cities in Brazil, 557 (10·0%) of which cover 6 313 380 (81·5%) of the mobility patterns in our study. By strategically incorporating mobility patterns into Brazil's existing influenza-like illness surveillance network (ie, by switching the location of 111 of 199 sentinel sites to different municipalities), our model predicted that mobility coverage would have a 33·6% improvement from 4 059 155 (52·4%) mobility patterns to 5 422 535 (70·0%) without expanding the number of sentinel sites. Our findings are validated with genomic data collected during the SARS-CoV-2 pandemic period. Our model accurately mapped 22 (51%) of 43 clade 1-affected cities and 28 (60%) of 47 clade 2-affected cities spread from São Paulo city, and 20 (49%) of 41 clade 1-affected cities and 28 (58%) of 48 clade 2-affected cities spread from Rio de Janeiro city, Feb 25–April 30, 2020. Additionally, 224 (73%) of the 307 suggested early-detection locations for pathogens emerging in Manaus corresponded with the first cities affected by the transmission of the gamma variant, Jan 6–16, 2021.</p></div><div><h3>Interpretation</h3><p>By providing essential clues for effective pathogen
{"title":"Human mobility patterns in Brazil to inform sampling sites for early pathogen detection and routes of spread: a network modelling and validation study","authors":"Juliane F Oliveira PhD , Prof Andrêza L Alencar PhD , Maria Célia L S Cunha PhD , Adriano O Vasconcelos PhD , Gerson G Cunha PhD , Ray B Miranda BSc , Fábio M H S Filho BSc , Corbiniano Silva PhD , Emanuele Gustani-Buss PhD , Ricardo Khouri PhD , Thiago Cerqueira-Silva PhD , Prof Luiz Landau PhD , Prof Manoel Barral-Netto MD , Pablo Ivan P Ramos PhD","doi":"10.1016/S2589-7500(24)00099-2","DOIUrl":"10.1016/S2589-7500(24)00099-2","url":null,"abstract":"<div><h3>Background</h3><p>Detecting and foreseeing pathogen dispersion is crucial in preventing widespread disease transmission. Human mobility is a fundamental issue in human transmission of infectious agents. Through a mobility data-driven approach, we aimed to identify municipalities in Brazil that could comprise an advanced sentinel network, allowing for early detection of circulating pathogens and their associated transmission routes.</p></div><div><h3>Methods</h3><p>In this modelling and validation study, we compiled a comprehensive dataset on intercity mobility spanning air, road, and waterway transport from the Brazilian Institute of Geography and Statistics (2016 data), National Transport Confederation (2022), and National Civil Aviation Agency (2017–23). We constructed a graph-based representation of Brazil's mobility network. The Ford–Fulkerson algorithm was used to rank the 5570 Brazilian cities according to their suitability as sentinel locations, allowing us to predict the most suitable locations for early detection and to track the most likely trajectory of a newly emerged pathogen. We also obtained SARS-CoV-2 genetic data from Brazilian municipalities during the early stage (Feb 25–April 30, 2020) of the virus's introduction and the gamma (P.1) variant emergence in Manaus (Jan 6–March 1, 2021), for the purposes of model validation.</p></div><div><h3>Findings</h3><p>We found that flights alone transported 79·9 million (95% CI 58·3–101·4 million) passengers annually within Brazil during 2017–22, with seasonal peaks occurring in late spring and summer, and road and river networks had a maximum capacity of 78·3 million passengers weekly in 2016. By analysing the 7 746 479 most probable paths originating from source nodes, we found that 3857 cities fully cover the mobility pattern of all 5570 cities in Brazil, 557 (10·0%) of which cover 6 313 380 (81·5%) of the mobility patterns in our study. By strategically incorporating mobility patterns into Brazil's existing influenza-like illness surveillance network (ie, by switching the location of 111 of 199 sentinel sites to different municipalities), our model predicted that mobility coverage would have a 33·6% improvement from 4 059 155 (52·4%) mobility patterns to 5 422 535 (70·0%) without expanding the number of sentinel sites. Our findings are validated with genomic data collected during the SARS-CoV-2 pandemic period. Our model accurately mapped 22 (51%) of 43 clade 1-affected cities and 28 (60%) of 47 clade 2-affected cities spread from São Paulo city, and 20 (49%) of 41 clade 1-affected cities and 28 (58%) of 48 clade 2-affected cities spread from Rio de Janeiro city, Feb 25–April 30, 2020. Additionally, 224 (73%) of the 307 suggested early-detection locations for pathogens emerging in Manaus corresponded with the first cities affected by the transmission of the gamma variant, Jan 6–16, 2021.</p></div><div><h3>Interpretation</h3><p>By providing essential clues for effective pathogen ","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 8","pages":"Pages e570-e579"},"PeriodicalIF":23.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024000992/pdfft?md5=b74d298dd27f122d3107c7fb202b0a16&pid=1-s2.0-S2589750024000992-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141767679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1016/S2589-7500(24)00145-6
Benjamin L Smarr
{"title":"Remote illness detection faces a trust barrier","authors":"Benjamin L Smarr","doi":"10.1016/S2589-7500(24)00145-6","DOIUrl":"10.1016/S2589-7500(24)00145-6","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 8","pages":"Pages e537-e538"},"PeriodicalIF":23.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001456/pdfft?md5=9f1b7ea2d874e81511d0a2671601c363&pid=1-s2.0-S2589750024001456-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141767683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1016/S2589-7500(24)00115-8
{"title":"The next generation of evidence synthesis for diagnostic accuracy studies in artificial intelligence","authors":"","doi":"10.1016/S2589-7500(24)00115-8","DOIUrl":"10.1016/S2589-7500(24)00115-8","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 8","pages":"Pages e541-e542"},"PeriodicalIF":23.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001158/pdfft?md5=63d2ae9f56a06a00c10c7d09f23c13cb&pid=1-s2.0-S2589750024001158-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141460002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1016/S2589-7500(24)00113-4
<div><h3>Background</h3><p>Chest x-ray is a basic, cost-effective, and widely available imaging method that is used for static assessments of organic diseases and anatomical abnormalities, but its ability to estimate dynamic measurements such as pulmonary function is unknown. We aimed to estimate two major pulmonary functions from chest x-rays.</p></div><div><h3>Methods</h3><p>In this retrospective model development and validation study, we trained, validated, and externally tested a deep learning-based artificial intelligence (AI) model to estimate forced vital capacity (FVC) and forced expiratory volume in 1 s (FEV<sub>1</sub>) from chest x-rays. We included consecutively collected results of spirometry and any associated chest x-rays that had been obtained between July 1, 2003, and Dec 31, 2021, from five institutions in Japan (labelled institutions A–E). Eligible x-rays had been acquired within 14 days of spirometry and were labelled with the FVC and FEV<sub>1</sub>. X-rays from three institutions (A–C) were used for training, validation, and internal testing, with the testing dataset being independent of the training and validation datasets, and then x-rays from the two other institutions (D and E) were used for independent external testing. Performance for estimating FVC and FEV<sub>1</sub> was evaluated by calculating the Pearson's correlation coefficient (<em>r</em>), intraclass correlation coefficient (ICC), mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) compared with the results of spirometry.</p></div><div><h3>Findings</h3><p>We included 141 734 x-ray and spirometry pairs from 81 902 patients from the five institutions. The training, validation, and internal test datasets included 134 307 x-rays from 75 768 patients (37 718 [50%] female, 38 050 [50%] male; mean age 56 years [SD 18]), and the external test datasets included 2137 x-rays from 1861 patients (742 [40%] female, 1119 [60%] male; mean age 65 years [SD 17]) from institution D and 5290 x-rays from 4273 patients (1972 [46%] female, 2301 [54%] male; mean age 63 years [SD 17]) from institution E. External testing for FVC yielded <em>r</em> values of 0·91 (99% CI 0·90–0·92) for institution D and 0·90 (0·89–0·91) for institution E, ICC of 0·91 (99% CI 0·90–0·92) and 0·89 (0·88–0·90), MSE of 0·17 L<sup>2</sup> (99% CI 0·15–0·19) and 0·17 L<sup>2</sup> (0·16–0·19), RMSE of 0·41 L (99% CI 0·39–0·43) and 0·41 L (0·39–0·43), and MAE of 0·31 L (99% CI 0·29–0·32) and 0·31 L (0·30–0·32). External testing for FEV<sub>1</sub> yielded <em>r</em> values of 0·91 (99% CI 0·90–0·92) for institution D and 0·91 (0·90–0·91) for institution E, ICC of 0·90 (99% CI 0·89–0·91) and 0·90 (0·90–0·91), MSE of 0·13 L<sup>2</sup> (99% CI 0·12–0·15) and 0·11 L<sup>2</sup> (0·10–0·12), RMSE of 0·37 L (99% CI 0·35–0·38) and 0·33 L (0·32–0·35), and MAE of 0·28 L (99% CI 0·27–0·29) and 0·25 L (0·25–0·26).</p></div><div><h3>Interpretation</h3><p>This deep learning model allowed
背景：胸部 X 光片是一种基本、经济、广泛使用的成像方法，可用于器质性疾病和解剖异常的静态评估，但其估算肺功能等动态测量值的能力尚不清楚。我们的目的是通过胸部 X 光片估测两种主要的肺功能：在这项回顾性模型开发和验证研究中，我们对基于深度学习的人工智能（AI）模型进行了训练、验证和外部测试，以便从胸部 X 光片中估算出用力肺活量（FVC）和 1 秒用力呼气容积（FEV1）。我们纳入了从 2003 年 7 月 1 日到 2021 年 12 月 31 日期间从日本五家机构（标注为机构 A-E）连续收集的肺活量测定结果和任何相关的胸部 X 光片。符合条件的 X 光片是在肺活量测定后 14 天内获得的，并标有 FVC 和 FEV1。来自三个机构（A-C）的 X 光片被用于训练、验证和内部测试，测试数据集独立于训练和验证数据集，然后来自其他两个机构（D 和 E）的 X 光片被用于独立的外部测试。通过计算与肺活量测定结果相比的皮尔逊相关系数（r）、类内相关系数（ICC）、均方误差（MSE）、均方根误差（RMSE）和平均绝对误差（MAE）来评估 FVC 和 FEV1 的估算结果：我们纳入了五家机构 81 902 名患者的 141 734 对 X 光片和肺活量测定结果。训练、验证和内部测试数据集包括 75 768 名患者的 134 307 张 X 光片（女性 37 718 [50%]，男性 38 050 [50%]；平均年龄 56 岁 [SD 18]），外部测试数据集包括 1861 名患者的 2137 张 X 光片（女性 742 [40%]，男性 1119 [60%]；平均年龄 65 岁 [SD 17]）；外部检测数据集包括 D 机构 1861 名患者（女性 742 人 [40%]，男性 1119 人 [60%]；平均年龄 65 岁 [SD 17]）的 2137 张 X 光片和 E 机构 4273 名患者（女性 1972 人 [46%]，男性 2301 人 [54%]；平均年龄 63 岁 [SD 17]）的 5290 张 X 光片。对 FVC 的外部测试结果显示，D 机构的 r 值为 0-91（99% CI 0-90-0-92），E 机构为 0-90（0-89-0-91），ICC 为 0-91（99% CI 0-90-0-92）和 0-89（0-88-0-90）、MSE为 0-17 L2 (99% CI 0-15-0-19) 和 0-17 L2 (0-16-0-19)，RMSE为 0-41 L (99% CI 0-39-0-43) 和 0-41 L (0-39-0-43)，MAE为 0-31 L (99% CI 0-29-0-32) 和 0-31 L (0-30-0-32)。对 FEV1 的外部测试结果显示，D 机构的 r 值为 0-91（99% CI 0-90-0-92），E 机构为 0-91（0-90-0-91），ICC 为 0-90（99% CI 0-89-0-91）和 0-90（0-90-0-91）、MSE 为 0-13 L2 (99% CI 0-12-0-15) 和 0-11 L2 (0-10-0-12)，RMSE 为 0-37 L (99% CI 0-35-0-38) 和 0-33 L (0-32-0-35)，MAE 为 0-28 L (99% CI 0-27-0-29) 和 0-25 L (0-25-0-26)。解释：该深度学习模型可通过胸部 X 光片估算出 FVC 和 FEV1，与肺活量测量法显示出很高的一致性。该模型为肺活量测定提供了一种评估肺功能的替代方法，尤其适用于无法进行肺活量测定的患者，并可根据从胸部X光片中获得的信息加强CT成像方案的定制，从而改善肺部疾病的诊断和管理。未来的研究应调查该人工智能模型与临床信息相结合的性能，以便更恰当、更有针对性地使用：无。
{"title":"A deep learning-based model to estimate pulmonary function from chest x-rays: multi-institutional model development and validation study in Japan","authors":"","doi":"10.1016/S2589-7500(24)00113-4","DOIUrl":"10.1016/S2589-7500(24)00113-4","url":null,"abstract":"<div><h3>Background</h3><p>Chest x-ray is a basic, cost-effective, and widely available imaging method that is used for static assessments of organic diseases and anatomical abnormalities, but its ability to estimate dynamic measurements such as pulmonary function is unknown. We aimed to estimate two major pulmonary functions from chest x-rays.</p></div><div><h3>Methods</h3><p>In this retrospective model development and validation study, we trained, validated, and externally tested a deep learning-based artificial intelligence (AI) model to estimate forced vital capacity (FVC) and forced expiratory volume in 1 s (FEV<sub>1</sub>) from chest x-rays. We included consecutively collected results of spirometry and any associated chest x-rays that had been obtained between July 1, 2003, and Dec 31, 2021, from five institutions in Japan (labelled institutions A–E). Eligible x-rays had been acquired within 14 days of spirometry and were labelled with the FVC and FEV<sub>1</sub>. X-rays from three institutions (A–C) were used for training, validation, and internal testing, with the testing dataset being independent of the training and validation datasets, and then x-rays from the two other institutions (D and E) were used for independent external testing. Performance for estimating FVC and FEV<sub>1</sub> was evaluated by calculating the Pearson's correlation coefficient (<em>r</em>), intraclass correlation coefficient (ICC), mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) compared with the results of spirometry.</p></div><div><h3>Findings</h3><p>We included 141 734 x-ray and spirometry pairs from 81 902 patients from the five institutions. The training, validation, and internal test datasets included 134 307 x-rays from 75 768 patients (37 718 [50%] female, 38 050 [50%] male; mean age 56 years [SD 18]), and the external test datasets included 2137 x-rays from 1861 patients (742 [40%] female, 1119 [60%] male; mean age 65 years [SD 17]) from institution D and 5290 x-rays from 4273 patients (1972 [46%] female, 2301 [54%] male; mean age 63 years [SD 17]) from institution E. External testing for FVC yielded <em>r</em> values of 0·91 (99% CI 0·90–0·92) for institution D and 0·90 (0·89–0·91) for institution E, ICC of 0·91 (99% CI 0·90–0·92) and 0·89 (0·88–0·90), MSE of 0·17 L<sup>2</sup> (99% CI 0·15–0·19) and 0·17 L<sup>2</sup> (0·16–0·19), RMSE of 0·41 L (99% CI 0·39–0·43) and 0·41 L (0·39–0·43), and MAE of 0·31 L (99% CI 0·29–0·32) and 0·31 L (0·30–0·32). External testing for FEV<sub>1</sub> yielded <em>r</em> values of 0·91 (99% CI 0·90–0·92) for institution D and 0·91 (0·90–0·91) for institution E, ICC of 0·90 (99% CI 0·89–0·91) and 0·90 (0·90–0·91), MSE of 0·13 L<sup>2</sup> (99% CI 0·12–0·15) and 0·11 L<sup>2</sup> (0·10–0·12), RMSE of 0·37 L (99% CI 0·35–0·38) and 0·33 L (0·32–0·35), and MAE of 0·28 L (99% CI 0·27–0·29) and 0·25 L (0·25–0·26).</p></div><div><h3>Interpretation</h3><p>This deep learning model allowed ","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 8","pages":"Pages e580-e588"},"PeriodicalIF":23.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001134/pdfft?md5=d7024a15c05d0bb8522e24f48c3cce86&pid=1-s2.0-S2589750024001134-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141564862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The development and commercialisation of medical decision systems based on artificial intelligence (AI) far outpaces our understanding of their value for clinicians. Although applicable across many forms of medicine, we focus on characterising the diagnostic decisions of radiologists through the concept of ecologically bounded reasoning, review the differences between clinician decision making and medical AI model decision making, and reveal how these differences pose fundamental challenges for integrating AI into radiology. We argue that clinicians are contextually motivated, mentally resourceful decision makers, whereas AI models are contextually stripped, correlational decision makers, and discuss misconceptions about clinician–AI interaction stemming from this misalignment of capabilities. We outline how future research on clinician–AI interaction could better address the cognitive considerations of decision making and be used to enhance the safety and usability of AI models in high-risk medical decision-making contexts.
{"title":"Medical artificial intelligence for clinicians: the lost cognitive perspective","authors":"Lana Tikhomirov BPsych [Hons] , Prof Carolyn Semmler PhD , Melissa McCradden PhD , Rachel Searston PhD , Marzyeh Ghassemi PhD , Lauren Oakden-Rayner MD PhD","doi":"10.1016/S2589-7500(24)00095-5","DOIUrl":"10.1016/S2589-7500(24)00095-5","url":null,"abstract":"<div><p>The development and commercialisation of medical decision systems based on artificial intelligence (AI) far outpaces our understanding of their value for clinicians. Although applicable across many forms of medicine, we focus on characterising the diagnostic decisions of radiologists through the concept of ecologically bounded reasoning, review the differences between clinician decision making and medical AI model decision making, and reveal how these differences pose fundamental challenges for integrating AI into radiology. We argue that clinicians are contextually motivated, mentally resourceful decision makers, whereas AI models are contextually stripped, correlational decision makers, and discuss misconceptions about clinician–AI interaction stemming from this misalignment of capabilities. We outline how future research on clinician–AI interaction could better address the cognitive considerations of decision making and be used to enhance the safety and usability of AI models in high-risk medical decision-making contexts.</p></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 8","pages":"Pages e589-e594"},"PeriodicalIF":23.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024000955/pdfft?md5=c4262279ee0696247e86b8dc47f4a153&pid=1-s2.0-S2589750024000955-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141767680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：