Pub Date : 2024-06-19DOI: 10.1016/S2589-7500(24)00091-8
Senjuti Saha PhD , Yogesh Hooda PhD , Prof Gathsaurie Neelika Malavige , Muhammad Imran Nisar PhD
Historical legacies of colonialism affect the distribution and control of scientific knowledge today, including within the pathogen genomics field, which remains dominated by high-income countries (HICs). We discuss the imperatives for decolonising pathogen genomics, including the need for more equitable representation, collaboration, and capacity-strengthening, and the shared responsibilities that both low-income and middle-income countries (LMICs) and HICs have in this endeavour. By highlighting examples from LMICs, we illuminate the pathways and challenges that researchers in LMICs face in the bid to gain autonomy in this crucial domain. Recognising the inherent value of local expertise and resources, we argue for a more inclusive, globally collaborative approach to pathogen genomics. Such an approach not only fosters scientific growth and innovation, but also strengthens global health security by equipping all nations with the tools needed to respond to health crises.
{"title":"Overcoming colonialism in pathogen genomics","authors":"Senjuti Saha PhD , Yogesh Hooda PhD , Prof Gathsaurie Neelika Malavige , Muhammad Imran Nisar PhD","doi":"10.1016/S2589-7500(24)00091-8","DOIUrl":"https://doi.org/10.1016/S2589-7500(24)00091-8","url":null,"abstract":"<div><p>Historical legacies of colonialism affect the distribution and control of scientific knowledge today, including within the pathogen genomics field, which remains dominated by high-income countries (HICs). We discuss the imperatives for decolonising pathogen genomics, including the need for more equitable representation, collaboration, and capacity-strengthening, and the shared responsibilities that both low-income and middle-income countries (LMICs) and HICs have in this endeavour. By highlighting examples from LMICs, we illuminate the pathways and challenges that researchers in LMICs face in the bid to gain autonomy in this crucial domain. Recognising the inherent value of local expertise and resources, we argue for a more inclusive, globally collaborative approach to pathogen genomics. Such an approach not only fosters scientific growth and innovation, but also strengthens global health security by equipping all nations with the tools needed to respond to health crises.</p></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 7","pages":"Pages e520-e525"},"PeriodicalIF":30.8,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024000918/pdfft?md5=24f9700527d676215fa2525fe30d09a3&pid=1-s2.0-S2589750024000918-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141428728","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 : 2024-06-19DOI: 10.1016/S2589-7500(24)00120-1
{"title":"Correction to Lancet Digit Health 2024; 6: e12–22","authors":"","doi":"10.1016/S2589-7500(24)00120-1","DOIUrl":"https://doi.org/10.1016/S2589-7500(24)00120-1","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 7","pages":"Page e445"},"PeriodicalIF":30.8,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001201/pdfft?md5=d2295e6ba64d5fd4dfd92760021259ec&pid=1-s2.0-S2589750024001201-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141428954","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}
<div><h3>Background</h3><p>Broad-capture proteomic technologies have the potential to improve disease prediction, enabling targeted prevention and management, but studies have so far been limited to very few selected diseases and have not evaluated predictive performance across multiple conditions. We aimed to evaluate the potential of serum proteins to improve risk prediction over and above health-derived information and polygenic risk scores across a diverse set of 24 outcomes.</p></div><div><h3>Methods</h3><p>We designed multiple case-cohorts nested in the <span>EPIC-Norfolk</span><svg><path></path></svg> prospective study, from participants with available serum samples and genome-wide genotype data, with more than 32 974 person-years of follow-up. Participants were middle-aged individuals (aged 40–79 years at baseline) of European ancestry who were recruited from the general population of Norfolk, England, between March, 1993 and December, 1997. We selected participants who developed one of ten less common diseases within 10 years of follow-up; we also subsampled a randomly drawn control subcohort, which also served to investigate 14 more common outcomes (n>70), including all-cause premature mortality (death before the age of 75 years; case numbers 71–437; controls 608–1556). Individuals were excluded from the current study owing to failed genotyping or proteomic quality control, relatedness, or missing information on age, sex, BMI, or smoking status. We used a machine learning framework to derive sparse predictive protein models for the onset of the the 23 individual diseases and all-cause premature mortality, and to derive a single common sparse multimorbidity signature that was predictive across multiple diseases from 2923 serum proteins.</p></div><div><h3>Findings</h3><p>Participants who developed one of ten less common diseases within 10 years of follow-up included 482 women and 507 men, with a mean age at baseline of 64·56 years (8·08). The random subcohort included 990 women and 769 men, with a mean age of 58·79 years (9·31). As few as five proteins alone outperformed polygenic risk scores for 17 of 23 outcomes (median dfference in concordance index [C-index] 0·13 [0·10–0·17]) and improved predictive performance when added over basic patient-derived information models for seven outcomes, achieving a median C-index of 0·82 (IQR 0·77–0·82). This included diseases with poor prognosis such as lung cancer (C-index 0·85 [+/− cross-validation error 0·83–0·87]), for which we identified unreported biomarkers such as C-X-C motif chemokine ligand 17. A sparse multimorbidity signature of ten proteins improved prediction across seven outcomes over patient-derived information models, achieving performances (median C-index 0·81 [IQR 0·80–0·82]) similar to those of disease-specific signatures.</p></div><div><h3>Interpretation</h3><p>We show the value of broad-capture proteomic biomarker discovery studies across multiple diseases of diverse causes,
{"title":"Proteomic prediction of diverse incident diseases: a machine learning-guided biomarker discovery study using data from a prospective cohort study","authors":"Julia Carrasco-Zanini PhD , Prof Maik Pietzner PhD , Mine Koprulu MPhil , Eleanor Wheeler PhD , Nicola D Kerrison MSci , Prof Nicholas J Wareham FMedSci , Prof Claudia Langenberg FFPH","doi":"10.1016/S2589-7500(24)00087-6","DOIUrl":"https://doi.org/10.1016/S2589-7500(24)00087-6","url":null,"abstract":"<div><h3>Background</h3><p>Broad-capture proteomic technologies have the potential to improve disease prediction, enabling targeted prevention and management, but studies have so far been limited to very few selected diseases and have not evaluated predictive performance across multiple conditions. We aimed to evaluate the potential of serum proteins to improve risk prediction over and above health-derived information and polygenic risk scores across a diverse set of 24 outcomes.</p></div><div><h3>Methods</h3><p>We designed multiple case-cohorts nested in the <span>EPIC-Norfolk</span><svg><path></path></svg> prospective study, from participants with available serum samples and genome-wide genotype data, with more than 32 974 person-years of follow-up. Participants were middle-aged individuals (aged 40–79 years at baseline) of European ancestry who were recruited from the general population of Norfolk, England, between March, 1993 and December, 1997. We selected participants who developed one of ten less common diseases within 10 years of follow-up; we also subsampled a randomly drawn control subcohort, which also served to investigate 14 more common outcomes (n>70), including all-cause premature mortality (death before the age of 75 years; case numbers 71–437; controls 608–1556). Individuals were excluded from the current study owing to failed genotyping or proteomic quality control, relatedness, or missing information on age, sex, BMI, or smoking status. We used a machine learning framework to derive sparse predictive protein models for the onset of the the 23 individual diseases and all-cause premature mortality, and to derive a single common sparse multimorbidity signature that was predictive across multiple diseases from 2923 serum proteins.</p></div><div><h3>Findings</h3><p>Participants who developed one of ten less common diseases within 10 years of follow-up included 482 women and 507 men, with a mean age at baseline of 64·56 years (8·08). The random subcohort included 990 women and 769 men, with a mean age of 58·79 years (9·31). As few as five proteins alone outperformed polygenic risk scores for 17 of 23 outcomes (median dfference in concordance index [C-index] 0·13 [0·10–0·17]) and improved predictive performance when added over basic patient-derived information models for seven outcomes, achieving a median C-index of 0·82 (IQR 0·77–0·82). This included diseases with poor prognosis such as lung cancer (C-index 0·85 [+/− cross-validation error 0·83–0·87]), for which we identified unreported biomarkers such as C-X-C motif chemokine ligand 17. A sparse multimorbidity signature of ten proteins improved prediction across seven outcomes over patient-derived information models, achieving performances (median C-index 0·81 [IQR 0·80–0·82]) similar to those of disease-specific signatures.</p></div><div><h3>Interpretation</h3><p>We show the value of broad-capture proteomic biomarker discovery studies across multiple diseases of diverse causes, ","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 7","pages":"Pages e470-e479"},"PeriodicalIF":30.8,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024000876/pdfft?md5=9d290cd7cb2425fe7ad24b8faf81109c&pid=1-s2.0-S2589750024000876-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141428957","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 : 2024-06-19DOI: 10.1016/S2589-7500(24)00092-X
Elisa Cohen MSc , Michael A Tsoukas MD , Laurent Legault MD , Michael Vallis PhD , Julia E Von Oettingen MD , Emilie Palisaitis MEng , Madison Odabassian BSc , Jean-François Yale MD , Natasha Garfield MD , Nikita Gouchie-Provencher RN , Joanna Rutkowski Eng , Adnan Jafar PhD , Milad Ghanbari MEng , Ahmad Haidar PhD
<div><h3>Background</h3><p>In type 1 diabetes, carbohydrate counting is the standard of care to determine prandial insulin needs, but it can negatively affect quality of life. We developed a novel insulin-and-pramlintide closed-loop system that replaces carbohydrate counting with simple meal announcements.</p></div><div><h3>Methods</h3><p>We performed a randomised crossover trial assessing 14 days of (1) insulin-and-pramlintide closed-loop system with simple meal announcements, (2) insulin-and-placebo closed-loop system with carbohydrate counting, and (3) insulin-and-placebo closed-loop system with simple meal announcements. Participants were recruited at McGill University Health Centre (Montreal, QC, Canada). Eligible participants were adults (aged ≥18 years) and adolescents (aged 12–17 years) with type 1 diabetes for at least 1 year. Participants were randomly assigned in a 1:1:1:1:1:1 ratio to a sequence of the three interventions, with faster insulin aspart used in all interventions. Each intervention was separated by a 14–45-day wash-out period, during which participants reverted to their usual insulin. During simple meal announcement interventions, participants triggered a prandial bolus at mealtimes based on a programmed fixed meal size, whereas during carbohydrate counting interventions, participants manually entered the carbohydrate content of the meal and an algorithm calculated the prandial bolus based on insulin-to-carbohydrate ratio. Two primary comparisons were predefined: the percentage of time in range (glucose 3·9–10·0 mmol/L) with a non-inferiority margin of 6·25% (non-inferiority comparison); and the mean Emotional Burden subscale score of the Diabetes Distress Scale (superiority comparison), comparing the insulin-and-placebo system with carbohydrate counting minus the insulin-and-pramlintide system with simple meal announcements. Analyses were performed on a modified intention-to-treat basis, excluding participants who did not complete all interventions. Serious adverse events were assessed in all participants. This trial is registered on <span>ClinicalTrials.gov</span><svg><path></path></svg>, <span>NCT04163874</span><svg><path></path></svg>.</p></div><div><h3>Findings</h3><p>32 participants were enrolled between Feb 14, 2020, and Oct 5, 2021; two participants withdrew before study completion. 30 participants were analysed, including 15 adults (nine female, mean age 39·4 years [SD 13·8]) and 15 adolescents (eight female, mean age 15·7 years [1·3]). Non-inferiority of the insulin-and-pramlintide system with simple meal announcements relative to the insulin-and-placebo system with carbohydrate counting was reached (difference –5% [95% CI –9·0 to –0·7], non-inferiority p<0·0001). No statistically significant difference was found in the mean Emotional Burden score between the insulin-and-pramlintide system with simple meal announcements and the insulin-and-placebo system with carbohydrate counting (difference 0·01 [SD 0·82], p
{"title":"Simple meal announcements and pramlintide delivery versus carbohydrate counting in type 1 diabetes with automated fast-acting insulin aspart delivery: a randomised crossover trial in Montreal, Canada","authors":"Elisa Cohen MSc , Michael A Tsoukas MD , Laurent Legault MD , Michael Vallis PhD , Julia E Von Oettingen MD , Emilie Palisaitis MEng , Madison Odabassian BSc , Jean-François Yale MD , Natasha Garfield MD , Nikita Gouchie-Provencher RN , Joanna Rutkowski Eng , Adnan Jafar PhD , Milad Ghanbari MEng , Ahmad Haidar PhD","doi":"10.1016/S2589-7500(24)00092-X","DOIUrl":"https://doi.org/10.1016/S2589-7500(24)00092-X","url":null,"abstract":"<div><h3>Background</h3><p>In type 1 diabetes, carbohydrate counting is the standard of care to determine prandial insulin needs, but it can negatively affect quality of life. We developed a novel insulin-and-pramlintide closed-loop system that replaces carbohydrate counting with simple meal announcements.</p></div><div><h3>Methods</h3><p>We performed a randomised crossover trial assessing 14 days of (1) insulin-and-pramlintide closed-loop system with simple meal announcements, (2) insulin-and-placebo closed-loop system with carbohydrate counting, and (3) insulin-and-placebo closed-loop system with simple meal announcements. Participants were recruited at McGill University Health Centre (Montreal, QC, Canada). Eligible participants were adults (aged ≥18 years) and adolescents (aged 12–17 years) with type 1 diabetes for at least 1 year. Participants were randomly assigned in a 1:1:1:1:1:1 ratio to a sequence of the three interventions, with faster insulin aspart used in all interventions. Each intervention was separated by a 14–45-day wash-out period, during which participants reverted to their usual insulin. During simple meal announcement interventions, participants triggered a prandial bolus at mealtimes based on a programmed fixed meal size, whereas during carbohydrate counting interventions, participants manually entered the carbohydrate content of the meal and an algorithm calculated the prandial bolus based on insulin-to-carbohydrate ratio. Two primary comparisons were predefined: the percentage of time in range (glucose 3·9–10·0 mmol/L) with a non-inferiority margin of 6·25% (non-inferiority comparison); and the mean Emotional Burden subscale score of the Diabetes Distress Scale (superiority comparison), comparing the insulin-and-placebo system with carbohydrate counting minus the insulin-and-pramlintide system with simple meal announcements. Analyses were performed on a modified intention-to-treat basis, excluding participants who did not complete all interventions. Serious adverse events were assessed in all participants. This trial is registered on <span>ClinicalTrials.gov</span><svg><path></path></svg>, <span>NCT04163874</span><svg><path></path></svg>.</p></div><div><h3>Findings</h3><p>32 participants were enrolled between Feb 14, 2020, and Oct 5, 2021; two participants withdrew before study completion. 30 participants were analysed, including 15 adults (nine female, mean age 39·4 years [SD 13·8]) and 15 adolescents (eight female, mean age 15·7 years [1·3]). Non-inferiority of the insulin-and-pramlintide system with simple meal announcements relative to the insulin-and-placebo system with carbohydrate counting was reached (difference –5% [95% CI –9·0 to –0·7], non-inferiority p<0·0001). No statistically significant difference was found in the mean Emotional Burden score between the insulin-and-pramlintide system with simple meal announcements and the insulin-and-placebo system with carbohydrate counting (difference 0·01 [SD 0·82], p","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 7","pages":"Pages e489-e499"},"PeriodicalIF":30.8,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S258975002400092X/pdfft?md5=8b2c8b64973057003ec92d8c1378b912&pid=1-s2.0-S258975002400092X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141428959","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 : 2024-06-19DOI: 10.1016/S2589-7500(24)00065-7
<div><h3>Background</h3><p>Pulmonary complications are the most common cause of death after surgery. This study aimed to derive and externally validate a novel prognostic model that can be used before elective surgery to estimate the risk of postoperative pulmonary complications and to support resource allocation and prioritisation during pandemic recovery.</p></div><div><h3>Methods</h3><p>Data from an international, prospective cohort study were used to develop a novel prognostic risk model for pulmonary complications after elective surgery in adult patients (aged ≥18 years) across all operation and disease types. The primary outcome measure was postoperative pulmonary complications at 30 days after surgery, which was a composite of pneumonia, acute respiratory distress syndrome, and unexpected mechanical ventilation. Model development with candidate predictor variables was done in the GlobalSurg-CovidSurg Week dataset (global; October, 2020). Two structured machine learning techniques were explored (XGBoost and the least absolute shrinkage and selection operator [LASSO]), and the model with the best performance (GSU-Pulmonary Score) underwent internal validation using bootstrap resampling. The discrimination and calibration of the score were externally validated in two further prospective cohorts: CovidSurg-Cancer (worldwide; February to August, 2020, during the COVID-19 pandemic) and RECON (UK and Australasia; January to October, 2019, before the COVID-19 pandemic). The model was deployed as an online web application. The GlobalSurg-CovidSurg Week and CovidSurg-Cancer studies were registered with <span>ClinicalTrials.gov</span><svg><path></path></svg>, <span>NCT04509986</span><svg><path></path></svg> and <span>NCT04384926</span><svg><path></path></svg>.</p></div><div><h3>Findings</h3><p>Prognostic models were developed from 13 candidate predictor variables in data from 86 231 patients (1158 hospitals in 114 countries). External validation included 30 492 patients from CovidSurg-Cancer (726 hospitals in 75 countries) and 6789 from RECON (150 hospitals in three countries). The overall rates of pulmonary complications were 2·0% in derivation data, and 3·9% (CovidSurg-Cancer) and 4·7% (RECON) in the validation datasets. Penalised regression using LASSO had similar discrimination to XGBoost (area under the receiver operating curve [AUROC] 0·786, 95% CI 0·774–0·798 <em>vs</em> 0·785, 0·772–0·797), was more explainable, and required fewer covariables. The final GSU-Pulmonary Score included ten predictor variables and showed good discrimination and calibration upon internal validation (AUROC 0·773, 95% CI 0·751–0·795; Brier score 0·020, calibration in the large [CITL] 0·034, slope 0·954). The model performance was acceptable on external validation in CovidSurg-Cancer (AUROC 0·746, 95% CI 0·733–0·760; Brier score 0·036, CITL 0·109, slope 1·056), but with some miscalibration in RECON data (AUROC 0·716, 95% CI 0·689–0·744; Brier score 0·045, CITL 1·040,
背景肺部并发症是手术后最常见的死亡原因。本研究旨在推导并从外部验证一种新型预后模型,该模型可在择期手术前用于估计术后肺部并发症的风险,并支持大流行病恢复期间的资源分配和优先级排序。方法:利用一项国际前瞻性队列研究的数据,为所有手术和疾病类型的成年患者(年龄≥18 岁)的择期手术后肺部并发症建立一种新型预后风险模型。主要结果指标是术后 30 天的术后肺部并发症,即肺炎、急性呼吸窘迫综合征和意外机械通气的综合结果。在 GlobalSurg-CovidSurg Week 数据集(全球;2020 年 10 月)中使用候选预测变量进行了模型开发。研究人员探索了两种结构化机器学习技术(XGBoost 和最小绝对收缩和选择算子 [LASSO]),并使用引导重采样对性能最佳的模型(GSU-肺部评分)进行了内部验证。在另外两个前瞻性队列中对该评分的判别和校准进行了外部验证:CovidSurg-Cancer(全球;2020 年 2 月至 8 月,COVID-19 大流行期间)和 RECON(英国和澳大拉西亚;2019 年 1 月至 10 月,COVID-19 大流行之前)。该模型以在线网络应用程序的形式部署。GlobalSurg-CovidSurg Week和CovidSurg-Cancer研究已在ClinicalTrials.gov(NCT04509986和NCT04384926)上注册。研究结果根据来自86231名患者(114个国家的1158家医院)的数据中的13个候选预测变量建立了诊断模型。外部验证包括来自CovidSurg-Cancer(75个国家的726家医院)的30 492名患者和来自RECON(3个国家的150家医院)的6 789名患者。在推导数据中,肺部并发症的总发生率为2-0%,而在验证数据集中,肺部并发症的发生率分别为3-9%(CovidSurg-Cancer)和4-7%(RECON)。使用 LASSO 进行的惩罚回归与 XGBoost 具有相似的区分度(接收器工作曲线下面积 [AUROC] 0-786, 95% CI 0-774-0-798 vs 0-785, 0-772-0-797),可解释性更高,所需的协变量更少。最终的 GSU-Pulmonary Score 包括 10 个预测变量,在内部验证中显示出良好的区分度和校准性(AUROC 0-773,95% CI 0-751-0-795;Brier score 0-020,calibration in the large [CITL] 0-034,斜率 0-954)。该模型在 CovidSurg-Cancer 的外部验证中表现尚可(AUROC 0-746,95% CI 0-733-0-760;Brier 评分 0-036,CITL 0-109,斜率 1-056),但在 RECON 数据中存在一些校准误差(AUROC 0-716,95% CI 0-689-0-744;Brier 评分 0-045,CITL 1-040,斜率 1-009)。解释:这一新颖的预后风险评分使用了在决定进行择期手术时可用的简单预测变量,可以准确地对患者术后肺部并发症的风险进行分层,包括在 SARS-CoV-2 爆发期间。随着择期手术规模的扩大,它可以为手术同意、资源分配和医院层面的优先次序提供信息,以解决全球积压的问题。
{"title":"A prognostic model for use before elective surgery to estimate the risk of postoperative pulmonary complications (GSU-Pulmonary Score): a development and validation study in three international cohorts","authors":"","doi":"10.1016/S2589-7500(24)00065-7","DOIUrl":"https://doi.org/10.1016/S2589-7500(24)00065-7","url":null,"abstract":"<div><h3>Background</h3><p>Pulmonary complications are the most common cause of death after surgery. This study aimed to derive and externally validate a novel prognostic model that can be used before elective surgery to estimate the risk of postoperative pulmonary complications and to support resource allocation and prioritisation during pandemic recovery.</p></div><div><h3>Methods</h3><p>Data from an international, prospective cohort study were used to develop a novel prognostic risk model for pulmonary complications after elective surgery in adult patients (aged ≥18 years) across all operation and disease types. The primary outcome measure was postoperative pulmonary complications at 30 days after surgery, which was a composite of pneumonia, acute respiratory distress syndrome, and unexpected mechanical ventilation. Model development with candidate predictor variables was done in the GlobalSurg-CovidSurg Week dataset (global; October, 2020). Two structured machine learning techniques were explored (XGBoost and the least absolute shrinkage and selection operator [LASSO]), and the model with the best performance (GSU-Pulmonary Score) underwent internal validation using bootstrap resampling. The discrimination and calibration of the score were externally validated in two further prospective cohorts: CovidSurg-Cancer (worldwide; February to August, 2020, during the COVID-19 pandemic) and RECON (UK and Australasia; January to October, 2019, before the COVID-19 pandemic). The model was deployed as an online web application. The GlobalSurg-CovidSurg Week and CovidSurg-Cancer studies were registered with <span>ClinicalTrials.gov</span><svg><path></path></svg>, <span>NCT04509986</span><svg><path></path></svg> and <span>NCT04384926</span><svg><path></path></svg>.</p></div><div><h3>Findings</h3><p>Prognostic models were developed from 13 candidate predictor variables in data from 86 231 patients (1158 hospitals in 114 countries). External validation included 30 492 patients from CovidSurg-Cancer (726 hospitals in 75 countries) and 6789 from RECON (150 hospitals in three countries). The overall rates of pulmonary complications were 2·0% in derivation data, and 3·9% (CovidSurg-Cancer) and 4·7% (RECON) in the validation datasets. Penalised regression using LASSO had similar discrimination to XGBoost (area under the receiver operating curve [AUROC] 0·786, 95% CI 0·774–0·798 <em>vs</em> 0·785, 0·772–0·797), was more explainable, and required fewer covariables. The final GSU-Pulmonary Score included ten predictor variables and showed good discrimination and calibration upon internal validation (AUROC 0·773, 95% CI 0·751–0·795; Brier score 0·020, calibration in the large [CITL] 0·034, slope 0·954). The model performance was acceptable on external validation in CovidSurg-Cancer (AUROC 0·746, 95% CI 0·733–0·760; Brier score 0·036, CITL 0·109, slope 1·056), but with some miscalibration in RECON data (AUROC 0·716, 95% CI 0·689–0·744; Brier score 0·045, CITL 1·040, ","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 7","pages":"Pages e507-e519"},"PeriodicalIF":30.8,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024000657/pdfft?md5=c58dbf488b0d666ef9df60c4c61a0bb4&pid=1-s2.0-S2589750024000657-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141429094","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 : 2024-06-19DOI: 10.1016/S2589-7500(24)00069-4
Kathrin Giehl PhD , Henk-Jan Mutsaerts PhD , Kristien Aarts PhD , Prof Frederik Barkhof MD , Prof Svenja Caspers PhD , Gaël Chetelat PhD , Marie-Elisabeth Colin MSc , Prof Emrah Düzel MD , Prof Giovanni B Frisoni MD , Prof M Arfan Ikram PhD , Prof Jorge Jovicich PhD , Prof Silvia Morbelli PhD , Prof Wolfgang Oertel MD , Christian Paret PhD , Prof Daniela Perani MD , Prof Petra Ritter PhD , Bàrbara Segura PhD , Laura E M Wisse PhD , Elke De Witte PhD , Prof Stefano F Cappa MD , Prof Thilo van Eimeren MD
The sharing of human neuroimaging data has great potential to accelerate the development of imaging biomarkers in neurological and psychiatric disorders; however, major obstacles remain in terms of how and why to share data in the Open Science context. In this Health Policy by the European Cluster for Imaging Biomarkers, we outline the current main opportunities and challenges based on the results of an online survey disseminated among senior scientists in the field. Although the scientific community fully recognises the importance of data sharing, technical, legal, and motivational aspects often prevent active adoption. Therefore, we provide practical advice on how to overcome the technical barriers. We also call for a harmonised application of the General Data Protection Regulation across EU countries. Finally, we suggest the development of a system that makes data count by recognising the generation and sharing of data as a highly valuable contribution to the community.
人类神经成像数据的共享在加速神经和精神疾病成像生物标记物的开发方面具有巨大潜力;然而,在开放科学背景下如何以及为何共享数据方面仍存在重大障碍。在这份由欧洲成像生物标记物集群(European Cluster for Imaging Biomarkers)制定的健康政策中,我们根据在该领域资深科学家中进行的在线调查结果,概述了当前的主要机遇和挑战。尽管科学界充分认识到数据共享的重要性,但技术、法律和动机方面的问题往往阻碍了数据共享的积极采用。因此,我们就如何克服技术障碍提供了实用建议。我们还呼吁欧盟各国统一适用《通用数据保护条例》。最后,我们建议开发一种系统,通过承认数据的生成和共享是对社会的一种极有价值的贡献,使数据变得有价值。
{"title":"Sharing brain imaging data in the Open Science era: how and why?","authors":"Kathrin Giehl PhD , Henk-Jan Mutsaerts PhD , Kristien Aarts PhD , Prof Frederik Barkhof MD , Prof Svenja Caspers PhD , Gaël Chetelat PhD , Marie-Elisabeth Colin MSc , Prof Emrah Düzel MD , Prof Giovanni B Frisoni MD , Prof M Arfan Ikram PhD , Prof Jorge Jovicich PhD , Prof Silvia Morbelli PhD , Prof Wolfgang Oertel MD , Christian Paret PhD , Prof Daniela Perani MD , Prof Petra Ritter PhD , Bàrbara Segura PhD , Laura E M Wisse PhD , Elke De Witte PhD , Prof Stefano F Cappa MD , Prof Thilo van Eimeren MD","doi":"10.1016/S2589-7500(24)00069-4","DOIUrl":"https://doi.org/10.1016/S2589-7500(24)00069-4","url":null,"abstract":"<div><p>The sharing of human neuroimaging data has great potential to accelerate the development of imaging biomarkers in neurological and psychiatric disorders; however, major obstacles remain in terms of how and why to share data in the Open Science context. In this Health Policy by the European Cluster for Imaging Biomarkers, we outline the current main opportunities and challenges based on the results of an online survey disseminated among senior scientists in the field. Although the scientific community fully recognises the importance of data sharing, technical, legal, and motivational aspects often prevent active adoption. Therefore, we provide practical advice on how to overcome the technical barriers. We also call for a harmonised application of the General Data Protection Regulation across EU countries. Finally, we suggest the development of a system that makes data count by recognising the generation and sharing of data as a highly valuable contribution to the community.</p></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 7","pages":"Pages e526-e535"},"PeriodicalIF":30.8,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024000694/pdfft?md5=1216633de2e712a8504b7713070a8c8a&pid=1-s2.0-S2589750024000694-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141428729","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 : 2024-06-19DOI: 10.1016/S2589-7500(24)00111-0
Anne de Hond , Tuur Leeuwenberg , Richard Bartels , Marieke van Buchem , Ilse Kant , Karel GM Moons , Maarten van Smeden
{"title":"From text to treatment: the crucial role of validation for generative large language models in health care","authors":"Anne de Hond , Tuur Leeuwenberg , Richard Bartels , Marieke van Buchem , Ilse Kant , Karel GM Moons , Maarten van Smeden","doi":"10.1016/S2589-7500(24)00111-0","DOIUrl":"https://doi.org/10.1016/S2589-7500(24)00111-0","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 7","pages":"Pages e441-e443"},"PeriodicalIF":30.8,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001110/pdfft?md5=02c157b66b011a5c49f259665b8a3a7c&pid=1-s2.0-S2589750024001110-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141429093","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 : 2024-06-19DOI: 10.1016/S2589-7500(24)00086-4
Adrienne K Scott , Michelle L Oyen
{"title":"Virtual pregnancies: predicting and preventing pregnancy complications with digital twins","authors":"Adrienne K Scott , Michelle L Oyen","doi":"10.1016/S2589-7500(24)00086-4","DOIUrl":"https://doi.org/10.1016/S2589-7500(24)00086-4","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 7","pages":"Pages e436-e437"},"PeriodicalIF":30.8,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024000864/pdfft?md5=4c537f02b6a0b5de364d1829924f9aa5&pid=1-s2.0-S2589750024000864-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141429102","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 : 2024-06-19DOI: 10.1016/S2589-7500(24)00121-3
{"title":"Correction to Lancet Digit Health 2024; 6: e33–43","authors":"","doi":"10.1016/S2589-7500(24)00121-3","DOIUrl":"https://doi.org/10.1016/S2589-7500(24)00121-3","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 7","pages":"Page e445"},"PeriodicalIF":30.8,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001213/pdfft?md5=73e788169a1247c34b3f5649a47fbc2d&pid=1-s2.0-S2589750024001213-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141428955","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 : 2024-06-19DOI: 10.1016/S2589-7500(24)00094-3
Karen K Wong MD , Thaddeus Segura MIDS , Gunnar Mein MIDS , Jia Lu PhD , Elizabeth J Hannapel MPH , Jasen M Kunz MPH , Troy Ritter PhD , Jessica C Smith MPH , Alberto Todeschini PhD , Fred Nugen PhD , Chris Edens PhD
Background
Cooling towers containing Legionella spp are a high-risk source of Legionnaires’ disease outbreaks. Manually locating cooling towers from aerial imagery during outbreak investigations requires expertise, is labour intensive, and can be prone to errors. We aimed to train a deep learning computer vision model to automatically detect cooling towers that are aerially visible.
Methods
Between Jan 1 and 31, 2021, we extracted satellite view images of Philadelphia (PN, USA) and New York state (NY, USA) from Google Maps and annotated cooling towers to create training datasets. We augmented training data with synthetic data and model-assisted labelling of additional cities. Using 2051 images containing 7292 cooling towers, we trained a two-stage model using YOLOv5, a model that detects objects in images, and EfficientNet-b5, a model that classifies images. We assessed the primary outcomes of sensitivity and positive predictive value (PPV) of the model against manual labelling on test datasets of 548 images, including from two cities not seen in training (Boston [MA, USA] and Athens [GA, USA]). We compared the search speed of the model with that of manual searching by four epidemiologists.
Findings
The model identified visible cooling towers with 95·1% sensitivity (95% CI 94·0–96·1) and a PPV of 90·1% (95% CI 90·0–90·2) in New York City and Philadelphia. In Boston, sensitivity was 91·6% (89·2–93·7) and PPV was 80·8% (80·5–81·2). In Athens, sensitivity was 86·9% (75·8–94·2) and PPV was 85·5% (84·2–86·7). For an area of New York City encompassing 45 blocks (0·26 square miles), the model searched more than 600 times faster (7·6 s; 351 potential cooling towers identified) than did human investigators (mean 83·75 min [SD 29·5]; mean 310·8 cooling towers [42·2]).
Interpretation
The model could be used to accelerate investigation and source control during outbreaks of Legionnaires’ disease through the identification of cooling towers from aerial imagery, potentially preventing additional disease spread. The model has already been used by public health teams for outbreak investigations and to initialise cooling tower registries, which are considered best practice for preventing and responding to outbreaks of Legionnaires’ disease.
{"title":"Automated cooling tower detection through deep learning for Legionnaires’ disease outbreak investigations: a model development and validation study","authors":"Karen K Wong MD , Thaddeus Segura MIDS , Gunnar Mein MIDS , Jia Lu PhD , Elizabeth J Hannapel MPH , Jasen M Kunz MPH , Troy Ritter PhD , Jessica C Smith MPH , Alberto Todeschini PhD , Fred Nugen PhD , Chris Edens PhD","doi":"10.1016/S2589-7500(24)00094-3","DOIUrl":"https://doi.org/10.1016/S2589-7500(24)00094-3","url":null,"abstract":"<div><h3>Background</h3><p>Cooling towers containing <em>Legionella</em> spp are a high-risk source of Legionnaires’ disease outbreaks. Manually locating cooling towers from aerial imagery during outbreak investigations requires expertise, is labour intensive, and can be prone to errors. We aimed to train a deep learning computer vision model to automatically detect cooling towers that are aerially visible.</p></div><div><h3>Methods</h3><p>Between Jan 1 and 31, 2021, we extracted satellite view images of Philadelphia (PN, USA) and New York state (NY, USA) from Google Maps and annotated cooling towers to create training datasets. We augmented training data with synthetic data and model-assisted labelling of additional cities. Using 2051 images containing 7292 cooling towers, we trained a two-stage model using YOLOv5, a model that detects objects in images, and EfficientNet-b5, a model that classifies images. We assessed the primary outcomes of sensitivity and positive predictive value (PPV) of the model against manual labelling on test datasets of 548 images, including from two cities not seen in training (Boston [MA, USA] and Athens [GA, USA]). We compared the search speed of the model with that of manual searching by four epidemiologists.</p></div><div><h3>Findings</h3><p>The model identified visible cooling towers with 95·1% sensitivity (95% CI 94·0–96·1) and a PPV of 90·1% (95% CI 90·0–90·2) in New York City and Philadelphia. In Boston, sensitivity was 91·6% (89·2–93·7) and PPV was 80·8% (80·5–81·2). In Athens, sensitivity was 86·9% (75·8–94·2) and PPV was 85·5% (84·2–86·7). For an area of New York City encompassing 45 blocks (0·26 square miles), the model searched more than 600 times faster (7·6 s; 351 potential cooling towers identified) than did human investigators (mean 83·75 min [SD 29·5]; mean 310·8 cooling towers [42·2]).</p></div><div><h3>Interpretation</h3><p>The model could be used to accelerate investigation and source control during outbreaks of Legionnaires’ disease through the identification of cooling towers from aerial imagery, potentially preventing additional disease spread. The model has already been used by public health teams for outbreak investigations and to initialise cooling tower registries, which are considered best practice for preventing and responding to outbreaks of Legionnaires’ disease.</p></div><div><h3>Funding</h3><p>None.</p></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 7","pages":"Pages e500-e506"},"PeriodicalIF":30.8,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024000943/pdfft?md5=134e7afec7443d66f0fb73e4c1e6aabb&pid=1-s2.0-S2589750024000943-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141428960","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}