-
The Lancet. Digital Health Jul 2024The sharing of human neuroimaging data has great potential to accelerate the development of imaging biomarkers in neurological and psychiatric disorders; however, major... (Review)
Review
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.
Topics: Humans; Information Dissemination; Neuroimaging; Brain
PubMed: 38906618
DOI: 10.1016/S2589-7500(24)00069-4 -
The Lancet. Digital Health Jul 2024Historical legacies of colonialism affect the distribution and control of scientific knowledge today, including within the pathogen genomics field, which remains... (Review)
Review
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.
Topics: Colonialism; Genomics; Humans; Developing Countries; Global Health
PubMed: 38906617
DOI: 10.1016/S2589-7500(24)00091-8 -
The Lancet. Digital Health Jul 2024Pulmonary 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...
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.
BACKGROUND
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.
METHODS
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 ClinicalTrials.gov, NCT04509986 and NCT04384926.
FINDINGS
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 vs 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, slope 1·009).
INTERPRETATION
This novel prognostic risk score uses simple predictor variables available at the time of a decision for elective surgery that can accurately stratify patients' risk of postoperative pulmonary complications, including during SARS-CoV-2 outbreaks. It could inform surgical consent, resource allocation, and hospital-level prioritisation as elective surgery is upscaled to address global backlogs.
FUNDING
National Institute for Health Research.
Topics: Humans; Elective Surgical Procedures; Postoperative Complications; Female; Prognosis; Middle Aged; Male; Prospective Studies; Aged; COVID-19; Risk Assessment; Adult; Machine Learning; Risk Factors; Lung Diseases; Cohort Studies
PubMed: 38906616
DOI: 10.1016/S2589-7500(24)00065-7 -
The Lancet. Digital Health Jul 2024Cooling towers containing Legionella spp are a high-risk source of Legionnaires' disease outbreaks. Manually locating cooling towers from aerial imagery during outbreak...
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.
FUNDING
None.
Topics: Humans; Disease Outbreaks; Legionnaires' Disease; Deep Learning; Air Conditioning; Philadelphia; New York; Legionella; Satellite Imagery
PubMed: 38906615
DOI: 10.1016/S2589-7500(24)00094-3 -
The Lancet. Digital Health Jul 2024In 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... (Randomized Controlled Trial)
Randomized Controlled Trial
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.
BACKGROUND
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.
METHODS
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 ClinicalTrials.gov, NCT04163874.
FINDINGS
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=0·93). With the insulin-and-pramlintide system with simple meal announcements, 14 (47%) participants reported mild gastrointestinal symptoms and two (7%) reported moderate symptoms, compared with two (7%) participants reporting mild gastrointestinal symptoms on the insulin-and-placebo system with carbohydrate counting. No serious adverse events occurred.
INTERPRETATION
The insulin-and-pramlintide system with simple meal announcements alleviated carbohydrate counting without degrading glucose control, although quality of life as measured by the Emotional Burden score was not improved. Longer and larger studies with this novel approach are warranted.
FUNDING
Juvenile Diabetes Research Foundation.
Topics: Humans; Diabetes Mellitus, Type 1; Cross-Over Studies; Female; Male; Adolescent; Hypoglycemic Agents; Islet Amyloid Polypeptide; Child; Adult; Insulin Aspart; Meals; Blood Glucose; Insulin Infusion Systems; Canada; Young Adult; Insulin; Dietary Carbohydrates; Quebec; Middle Aged
PubMed: 38906614
DOI: 10.1016/S2589-7500(24)00092-X -
The Lancet. Digital Health Jul 2024The myocardial-ischaemic-injury-index (MI) is a novel machine learning algorithm for the early diagnosis of type 1 non-ST-segment elevation myocardial infarction...
BACKGROUND
The myocardial-ischaemic-injury-index (MI) is a novel machine learning algorithm for the early diagnosis of type 1 non-ST-segment elevation myocardial infarction (NSTEMI). The performance of MI, both when using early serial blood draws (eg, at 1 h or 2 h) and in direct comparison with guideline-recommended algorithms, remains unknown. Our aim was to externally validate MI and compare its performance with that of the European Society of Cardiology (ESC) 0/1h-algorithm.
METHODS
In this secondary analysis of a multicentre international diagnostic cohort study, adult patients (age >18 years) presenting to the emergency department with symptoms suggestive of myocardial infarction were prospectively enrolled from April 21, 2006, to Feb 27, 2019 in 12 centres from five European countries (Switzerland, Spain, Italy, Poland, and Czech Republic). Patients were excluded if they presented with ST-segment-elevation myocardial infarction, did not have at least two serial high-sensitivity cardiac troponin I (hs-cTnI) measurements, or if the final diagnosis remained unclear. The final diagnosis was centrally adjudicated by two independent cardiologists using all available medical records, including serial hs-cTnI measurements and cardiac imaging. The primary outcome was type 1 NSTEMI. The performance of MI was directly compared with that of the ESC 0/1h-algorithm.
FINDINGS
Among 6487 patients, (median age 61·0 years [IQR 49·0-73·0]; 2122 [33%] female and 4365 [67%] male), 882 (13·6%) patients had type 1 NSTEMI. The median time difference between the first and second hs-cTnI measurement was 60·0 mins (IQR 57·0-70·0). MI performance was very good, with an area under the receiver-operating-characteristic curve of 0·961 (95% CI 0·957 to 0·965) and a good overall calibration (intercept -0·09 [-0·2 to 0·02]; slope 1·02 [0·97 to 1·08]). The originally defined MI score of less than 1·6 identified 4186 (64·5%) patients as low probability of having a type 1 NSTEMI (sensitivity 99·1% [95% CI 98·2 to 99·5]; negative predictive value [NPV] 99·8% [95% CI 99·6 to 99·9]) and an MI score of 49·7 or more identified 915 (14·1%) patients as high probability of having a type 1 NSTEMI (specificity 95·0% [94·3 to 95·5]; positive predictive value [PPV] 69·1% [66·0-72·0]). The sensitivity and NPV of the ESC 0/1h-algorithm were higher than that of MI (difference for sensitivity 0·88% [0·19 to 1·60], p=0·0082; difference for NPV 0·18% [0·05 to 0·32], p=0·016), and the rule-out efficacy was higher for MI (11% difference, p<0·0001). Specificity and PPV for MI were superior (difference for specificity 3·80% [3·24 to 4·36], p<0·0001; difference for PPV 7·84% [5·86 to 9·97], p<0·0001), and the rule-in efficacy was higher for the ESC 0/1h-algorithm (5·4% difference, p<0·0001).
INTERPRETATION
MI performs very well in diagnosing type 1 NSTEMI, demonstrating comparability to the ESC 0/1h-algorithm in an emergency department setting when using early serial blood draws.
FUNDING
Swiss National Science Foundation, Swiss Heart Foundation, the EU, the University Hospital Basel, the University of Basel, Abbott, Beckman Coulter, Roche, Idorsia, Ortho Clinical Diagnostics, Quidel, Siemens, and Singulex.
Topics: Humans; Male; Female; Middle Aged; Aged; Early Diagnosis; Machine Learning; Algorithms; Non-ST Elevated Myocardial Infarction; Troponin I; Prospective Studies; Cohort Studies; Europe; Myocardial Infarction; Emergency Service, Hospital; Biomarkers
PubMed: 38906613
DOI: 10.1016/S2589-7500(24)00088-8 -
The Lancet. Digital Health Jul 2024Broad-capture proteomic technologies have the potential to improve disease prediction, enabling targeted prevention and management, but studies have so far been limited...
BACKGROUND
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.
METHODS
We designed multiple case-cohorts nested in the EPIC-Norfolk 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.
FINDINGS
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.
INTERPRETATION
We show the value of broad-capture proteomic biomarker discovery studies across multiple diseases of diverse causes, pointing to those that might benefit the most from proteomic approaches, and the potential to derive common sparse biomarker panels for prediction of multiple diseases at once. This framework could enable follow-up studies to explore the generalisability of proteomic models and to benchmark these against clinical assays, which are required to understand the translational potential of these findings.
FUNDING
Medical Research Council, Health Data Research UK, UK Research and Innovation-National Institute for Health and Care Research, Cancer Research UK, and Wellcome Trust.
Topics: Humans; Middle Aged; Machine Learning; Male; Female; Prospective Studies; Biomarkers; Proteomics; Aged; Adult; England; Risk Assessment; Risk Factors
PubMed: 38906612
DOI: 10.1016/S2589-7500(24)00087-6 -
The Lancet. Digital Health Jul 2024Despite the availability of effective treatments, most depressive disorders remain undetected and untreated. Internet-based depression screening combined with automated... (Randomized Controlled Trial)
Randomized Controlled Trial
BACKGROUND
Despite the availability of effective treatments, most depressive disorders remain undetected and untreated. Internet-based depression screening combined with automated feedback of screening results could reach people with depression and lead to evidence-based care. We aimed to test the efficacy of two versions of automated feedback after internet-based screening on depression severity compared with no feedback.
METHODS
DISCOVER was an observer-masked, three-armed, randomised controlled trial in Germany. We recruited individuals (aged ≥18 years) who were undiagnosed with depression and screened positive for depression on an internet-based self-report depression rating scale (Patient Health Questionnaire-9 [PHQ-9] ≥10 points). Participants were randomly assigned 1:1:1 to automatically receive no feedback, non-tailored feedback, or tailored feedback on the depression screening result. Randomisation was stratified by depression severity (moderate: PHQ-9 score 10-14 points; severe: PHQ-9 score ≥15 points). Participants could not be masked but were kept unaware of trial hypotheses to minimise expectancy bias. The non-tailored feedback included the depression screening result, a recommendation to seek professional diagnostic advice, and brief general information about depression and its treatment. The tailored feedback included the same basic information but individually framed according to the participants' symptom profiles, treatment preferences, causal symptom attributions, health insurance, and local residence. Research staff were masked to group allocation and outcome assessment as these were done using online questionnaires. The primary outcome was change in depression severity, defined as change in PHQ-9 score 6 months after random assignment. Analyses were conducted following the intention-to-treat principle for participants with at least one follow-up visit. This trial was registered at ClinicalTrials.gov, NCT04633096.
FINDINGS
Between Jan 12, 2021, and Jan 31, 2022, 4878 individuals completed the internet-based screening. Of these, 1178 (24%) screened positive for depression (mean age 37·1 [SD 14·2] years; 824 [70%] woman, 344 [29%] men, and 10 [1%] other gender identity). 6 months after random assignment, depression severity decreased by 3·4 PHQ-9 points in the no feedback group (95% CI 2·9-4·0; within-group d 0·67; 325 participants), by 3·5 points in the non-tailored feedback group (3·0-4·0; within-group d 0·74; 319 participants), and by 3·7 points in the tailored feedback group (3·2-4·3; within-group d 0·71; 321 participants), with no significant differences among the three groups (p=0·72). The number of participants seeking help for depression or initiating psychotherapy or antidepressant treatment did not differ among study groups. The results remained consistent when adjusted for fulfilling the DSM-5-based criteria for major depressive disorder or subjective belief of having a depressive disorder. Negative effects were reported by less than 1% of the total sample 6 months after random assignment.
INTERPRETATION
Automated feedback following internet-based depression screening did not reduce depression severity or prompt sufficient depression care in individuals previously undiagnosed with but affected by depression.
FUNDING
German Research Foundation.
Topics: Humans; Male; Female; Germany; Adult; Internet; Middle Aged; Depression; Mass Screening; Feedback; Depressive Disorder; Surveys and Questionnaires
PubMed: 38906611
DOI: 10.1016/S2589-7500(24)00070-0 -
The Lancet. Digital Health Jul 2024
PubMed: 38906610
DOI: 10.1016/S2589-7500(24)00120-1 -
The Lancet. Digital Health Jul 2024
PubMed: 38906609
DOI: 10.1016/S2589-7500(24)00121-3