Search

Background: Machine learning has been used to analyse heart failure subtypes, but not across large, distinct, population-based datasets, across the whole spectrum of causes and presentations, or with clinical and non-clinical validation by different machine learning methods. Using our published framework, we aimed to discover heart failure subtypes and validate them upon population representative data. Methods: In this external, prognostic, and genetic validation study we analysed individuals aged 30 years or older with incident heart failure from two population-based databases in the UK (Clinical Practice Research Datalink [CPRD] and The Health Improvement Network [THIN]) from 1998 to 2018. Pre-heart failure and post-heart failure factors (n=645) included demographic information, history, examination, blood laboratory values, and medications. We identified subtypes using four unsupervised machine learning methods (K-means, hierarchical, K-Medoids, and mixture model clustering) with 87 of 645 factors in each dataset. We evaluated subtypes for (1) external validity (across datasets); (2) prognostic validity (predictive accuracy for 1-year mortality); and (3) genetic validity (UK Biobank), association with polygenic risk score (PRS) for heart failure-related traits (n=11), and single nucleotide polymorphisms (n=12). Findings: We included 188 800, 124 262, and 9573 individuals with incident heart failure from CPRD, THIN, and UK Biobank, respectively, between Jan 1, 1998, and Jan 1, 2018. After identifying five clusters, we labelled heart failure subtypes as (1) early onset, (2) late onset, (3) atrial fibrillation related, (4) metabolic, and (5) cardiometabolic. In the external validity analysis, subtypes were similar across datasets (c-statistics: THIN model in CPRD ranged from 0·79 [subtype 3] to 0·94 [subtype 1], and CPRD model in THIN ranged from 0·79 [subtype 1] to 0·92 [subtypes 2 and 5]). In the prognostic validity analysis, 1-year all-cause mortality after heart failure diagnosis (subtype 1 0·20 [95% CI 0·14–0·25], subtype 2 0·46 [0·43–0·49], subtype 3 0·61 [0·57–0·64], subtype 4 0·11 [0·07–0·16], and subtype 5 0·37 [0·32–0·41]) differed across subtypes in CPRD and THIN data, as did risk of non-fatal cardiovascular diseases and all-cause hospitalisation. In the genetic validity analysis the atrial fibrillation-related subtype showed associations with the related PRS. Late onset and cardiometabolic subtypes were the most similar and strongly associated with PRS for hypertension, myocardial infarction, and obesity (p

Background: An increasing number of digital health interventions (DHIs) for remote postoperative monitoring have recently been developed and evaluated. We aimed to review DHIs for postoperative monitoring and evaluate their readiness for implementation into routine care.Methods: This systematic review identified studies on implementation and evaluation of DHIs for postoperative monitoring published before 1st December 2022 (PROSPERO ID: CRD42021264289). Studies which included postoperative monitoring use-cases for general postoperative recovery or specific complications were defined according to their IDEAL (Idea, Development, Exploration, Assessment and Long-term follow-up) stages of innovation. A novel clinical innovation network analysis (CINA) using co-authorship and citations of previous work was used to examine collaboration and progression within the field. The WHO framework for monitoring and evaluating DHIs was used for the thematic narrative synthesis.Findings: There were 126 studies of 100 novel DHIs identified from 8,591 records. Of these studies, 80.2% (n=101/126) were classed as at an early stage of innovation (IDEAL stage 1 & 2a), and only 1 had achieved routine implementation at a single centre. There is limited evidence of collaboration based on co-authorship or reference to previous work, with 90.7%, n=107/118 of studies beyond IDEAL stage 1 without prior stages published. There were notable differences in evaluation across IDEAL stages, with clear omissions in evaluation across all use-cases: more than 4/5 studies did not consider the feasibility, accessibility, or the impact of these interventions on the cost, efficiency or quality of care.Interpretation: Use of DHIs for postoperative monitoring remains at an early stage of innovation, with promising but generally low-quality supporting evidence. Comprehensive evaluation within high-quality, large-scale trials and real-world data are required to definitively establish readiness for routine implementation.

BACKGROUND: Validated questionnaires are used to assess asthma control over the past 1-4 weeks from reporting. However, they do not adequately capture asthma control in patients with fluctuating symptoms. Using the Mobile Airways Sentinel Network for airway diseases (MASK-air) app, we developed and validated an electronic daily asthma control score (e-DASTHMA).METHODS: We used MASK-air data (freely available to users in 27 countries) to develop and assess different daily control scores for asthma. Data-driven control scores were developed based on asthma symptoms reported by a visual analogue scale (VAS) and self-reported asthma medication use. We included the daily monitoring data from all MASK-air users aged 16-90 years (or older than 13 years to 90 years in countries with a lower age of digital consent) who had used the app in at least 3 different calendar months and had reported at least 1 day of asthma medication use. For each score, we assessed construct validity, test-retest reliability, responsiveness, and accuracy. We used VASs on dyspnoea and work disturbance, EQ-5D-VAS, Control of Allergic Rhinitis and Asthma Test (CARAT), CARAT asthma, and Work Productivity and Activity Impairment: Allergy Specific (WPAI:AS) questionnaires as comparators. We performed an internal validation using MASK-air data from Jan 1 to Oct 12, 2022, and an external validation using a cohort of patients with physician-diagnosed asthma (the INSPIRERS cohort) who had had their diagnosis and control (Global Initiative for Asthma [GINA] classification) of asthma ascertained by a physician.FINDINGS: We studied 135 635 days of MASK-air data from 1662 users from May 21, 2015, to Dec 31, 2021. The scores were strongly correlated with VAS dyspnoea (Spearman correlation coefficient range 0·68-0·82) and moderately correlated with work comparators and quality-of-life-related comparators (for WPAI:AS work, we observed Spearman correlation coefficients of 0·59-0·68). They also displayed high test-retest reliability (intraclass correlation coefficients range 0·79-0·95) and moderate-to-high responsiveness (correlation coefficient range 0·69-0·79; effect size measures range 0·57-0·99 in the comparison with VAS dyspnoea). The best-performing score displayed a strong correlation with the effect of asthma on work and school activities in the INSPIRERS cohort (Spearman correlation coefficients 0·70; 95% CI 0·61-0·78) and good accuracy for the identification of patients with uncontrolled or partly controlled asthma according to GINA (area under the receiver operating curve 0·73; 95% CI 0·68-0·78).INTERPRETATION: e-DASTHMA is a good tool for the daily assessment of asthma control. This tool can be used as an endpoint in clinical trials as well as in clinical practice to assess fluctuations in asthma control and guide treatment optimisation.FUNDING: None.

To describe the information technology and artificial intelligence support in management experiences of the pediatric designated hospital in the wave of COVID-19 in Shanghai.: We retrospectively concluded the management experiences at the largest pediatric designated hospital from March 1The COVID-19 designated hospitals were built particularly for critical patients requiring high-level medical care, responded quickly and scientifically to prevent and control the epidemic situation. From March 1Information technology and artificial intelligence has provided significant supports in the management. The system optimizes the admission screening process, increases the communication inside and outside the ward, achieves early detection and diagnosis, timely isolates patients, and timely treatment of various types of children.

Faced with the current time-sensitive COVID-19 pandemic, the overburdened healthcare systems resulted in a strong demand to develop newer methods to control the spread of the pandemic. Big data and artificial intelligence (AI) have been leveraged amid the COVID-19 pandemic; however, little is known about its use for supporting public health efforts. In epidemic surveillance and containment, efforts are needed to treat critical patients, track and manage the health status of residents, isolate suspected cases, develop vaccines and antiviral drugs. The applications of emerging practices of artificial intelligence and big data have become powerful "weapons" to fight against the pandemic and provide strong support in pandemic prevention and control, such as early warning, analysis and judgment, interruption and intervention of epidemic, to achieve goals of early detection, early report, early diagnosis, early isolation and early treatment, and these are the decisive factors to control the spread of the epidemic and reduce the mortality. This paper systematically summarizes the application of big data and AI in epidemic, and describes practical cases and challenges with emphasis in epidemic prevention and control. The included studies showed that big data and AI have the potential strength to fight against COVID-19. However, many of the proposed methods are not yet widely accepted. Thus, the most rewarding research will be on methods promising value beyond COVID-19. More efforts are needed for developing standardized reporting protocols or guidelines for practice.

The coronavirus disease 2019 (COVID-19) pandemic is ravaging the world. Many therapies have been explored to treat COVID-19. This report aimed to assess the global research trends for the development of COVID-19 therapies.We searched the relevant articles on COVID-19 therapies published from January 1, 2020, to May 25, 2022, in the Web of Science Core Collection Database (WOSCC). VOSviewer 1.6.18 software was used to assess data on the countries, institutions, authors, collaborations, keywords, and journals that were most implicated in COVID-19 pharmacological research. The latest research and changing trends in COVID-19-relevant pharmacological research were analyzed.After manually eliminating articles that do not meet the requirements, a total of 5,289 studies authored by 32,932 researchers were eventually included in the analyses, which comprised 95 randomized controlled trials. 3044 (57.6%) studies were published in 2021. The USA conducted the greatest number of studies, followed by China and India. The primary USA collaborators were China and England. The topics covered in the publications included: the general characteristics, the impact on pharmacists' work, the pharmacological research, broad-spectrum antiviral drug therapy and research, and promising targets or preventive measures, such as vaccine. The temporal diagram revealed that the current research hotspots focused on the vaccine, molecular docking, Mpro, and drug delivery keywords.Comprehensive bibliometric analysis can aid the rapid identification of the principal research topics, potential collaborators, and the direction of future research. Pharmacological research is critical for the development of therapeutic and preventive COVID-19-associated measures. This study may therefore provide valuable information for eradicating COVID-19.

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is highly effective in controlling motor symptoms in patients with Parkinson's disease. However, correct selection of stimulation parameters is pivotal to treatment success and currently follows a time-consuming and demanding trial-and-error process. We aimed to assess treatment effects of stimulation parameters suggested by a recently published algorithm (StimFit) based on neuroimaging data.This double-blind, randomised, crossover, non-inferiority trial was carried out at Charité - Universitätsmedizin, Berlin, Germany, and enrolled patients with Parkinson's disease treated with directional octopolar electrodes targeted at the STN. All patients had undergone DBS programming according to our centre's standard of care (SoC) treatment before study recruitment. Based on perioperative imaging data, DBS electrodes were reconstructed and StimFit was applied to suggest optimal stimulation settings. Patients underwent motor assessments using the Movement Disorder Society-Sponsored Revision of the Unified Parkinson's Disease Rating Scale part III (MDS-UPDRS-III) during OFF-medication and in OFF-stimulation and ON-stimulation states under both conditions, StimFit and SoC parameter settings. Patients were randomly assigned (1:1) to receive either StimFit-programmed DBS first and SoC-programmed DBS second, or SoC-programmed DBS first and StimFit-programmed DBS second. The allocation schedule was generated using a computerised random number generator. Both the rater and patients were masked to the sequence of SoC and StimFit stimulation conditions. All patients who participated in the study were included in the analysis. The primary endpoint of this study was the absolute mean difference between MDS-UPDRS-III scores under StimFit and SoC stimulation, with a non-inferiority margin of 5 points. The study was registered at the German Register for Clinical Trials (DRKS00023115), and is complete.Between July 10, 2020, and Oct 28, 2021, 35 patients were enrolled in the study; 18 received StimFit followed by SoC stimulation, and 17 received SoC followed by StimFit stimulation. Mean MDS-UPDRS-III scores improved from 47·3 (SD 17·1) at OFF-stimulation baseline to 24·7 (SD 12·4) and 26·3 (SD 12·4) under SoC and StimFit stimulation, respectively. Mean difference between motor scores was -1·6 (SD 7·1; 95% CI -4·0 to 0·9; superiority test psuperiority=0·20; n=35), establishing non-inferiority of StimFit stimulation at a margin of -5 points (non-inferiority test pnon-inferiority=0·0038). In six patients (17%), initial programming of StimFit settings resulted in acute side-effects and amplitudes were reduced until side-effects disappeared.Automated data-driven algorithms can predict stimulation parameters that lead to motor symptom control comparable to SoC treatment. This approach could significantly decrease the time necessary to obtain optimal treatment parameters.Deutsche Forschungsgemeinschaft through NeuroCure Clinical Research Center and TRR 295.

One challenge in the field of in-vitro fertilisation is the selection of the most viable embryos for transfer. Morphological quality assessment and morphokinetic analysis both have the disadvantage of intra-observer and inter-observer variability. A third method, preimplantation genetic testing for aneuploidy (PGT-A), has limitations too, including its invasiveness and cost. We hypothesised that differences in aneuploid and euploid embryos that allow for model-based classification are reflected in morphology, morphokinetics, and associated clinical information.In this retrospective study, we used machine-learning and deep-learning approaches to develop STORK-A, a non-invasive and automated method of embryo evaluation that uses artificial intelligence to predict embryo ploidy status. Our method used a dataset of 10 378 embryos that consisted of static images captured at 110 h after intracytoplasmic sperm injection, morphokinetic parameters, blastocyst morphological assessments, maternal age, and ploidy status. Independent and external datasets, Weill Cornell Medicine EmbryoScope+ (WCM-ES+; Weill Cornell Medicine Center of Reproductive Medicine, NY, USA) and IVI Valencia (IVI Valencia, Health Research Institute la Fe, Valencia, Spain) were used to test the generalisability of STORK-A and were compared measuring accuracy and area under the receiver operating characteristic curve (AUC).Analysis and model development included the use of 10 378 embryos, all with PGT-A results, from 1385 patients (maternal age range 21-48 years; mean age 36·98 years [SD 4·62]). STORK-A predicted aneuploid versus euploid embryos with an accuracy of 69·3% (95% CI 66·9-71·5; AUC 0·761; positive predictive value [PPV] 76·1%; negative predictive value [NPV] 62·1%) when using images, maternal age, morphokinetics, and blastocyst score. A second classification task trained to predict complex aneuploidy versus euploidy and single aneuploidy produced an accuracy of 74·0% (95% CI 71·7-76·1; AUC 0·760; PPV 54·9%; NPV 87·6%) using an image, maternal age, morphokinetic parameters, and blastocyst grade. A third classification task trained to predict complex aneuploidy versus euploidy had an accuracy of 77·6% (95% CI 75·0-80·0; AUC 0·847; PPV 76·7%; NPV 78·0%). STORK-A reported accuracies of 63·4% (AUC 0·702) on the WCM-ES+ dataset and 65·7% (AUC 0·715) on the IVI Valencia dataset, when using an image, maternal age, and morphokinetic parameters, similar to the STORK-A test dataset accuracy of 67·8% (AUC 0·737), showing generalisability.As a proof of concept, STORK-A shows an ability to predict embryo ploidy in a non-invasive manner and shows future potential as a standardised supplementation to traditional methods of embryo selection and prioritisation for implantation or recommendation for PGT-A.US National Institutes of Health.

Challenges for the effective management of interstitial lung diseases (ILDs) include difficulties with the early detection of disease, accurate prognostication with baseline data, and accurate and precise response to therapy. The purpose of this Review is to describe the clinical and research gaps in the diagnosis and prognosis of ILD, and how machine learning can be applied to image biomarker research to close these gaps. Machine-learning algorithms can identify ILD in at-risk populations, predict the extent of lung fibrosis, correlate radiological abnormalities with lung function decline, and be used as endpoints in treatment trials, exemplifying how this technology can be used in care for people with ILD. Advances in image processing and analysis provide further opportunities to use machine learning that incorporates deep-learning-based image analysis and radiomics. Collaboration and consistency are required to develop optimal algorithms, and candidate radiological biomarkers should be validated against appropriate predictors of disease outcomes.

© 2022 Elsevier B.V.Objective: Objective methods to monitor the sleep of preterm infants at the neonatal intensive care unit (NICU) are required to prevent potentially adverse neurodevelopmental outcomes. This study aimed to determine the concordance of actigraphy and amplitude-integrated electroencephalogram (aEEG) against gold standard direct observation (DO) in assessing sleep/wake states of typically developing preterm infants. Methods: This prospective observational study was conducted in a single center level III NICU. Sleep variables were measured using Philips Respironics Mini-Mitter® Actiwatch-2 for 24 h and compared with 8-h matched data of aEEG and DO. Sensitivity-specificity analysis, Cohen's kappa, prevalence-adjusted and bias-adjusted kappa (PABAK), and Bland Altman plots were generated. Results: Seventeen preterm infants were recruited. A total of 11252 epochs were studied. Sensitivity (86.4%), agreement rate (67.9%), and predictive value for wake (47.9%) for the actigraphy were highest at the automatic activity threshold whereas specificity (54.5%) and predictive value for sleep (75.5%) were highest at low threshold. The sensitivity of aEEG was 79.3% and the specificity was 54.3%. At all thresholds, the agreement was largely equivalent with low kappas (0.14–0.17) and PABAK coefficients (0.22–0.35) for actigraphy and DO. Moderate agreement was observed between aEEG and DO according to the PABAK coefficient (0.44). Mean differences in sleep parameters were not different between DO and aEEG as well as DO/aEEG and actigraphy at medium threshold (p > 0.05). Conclusions: Actigraphy at medium threshold can be used in depicting sleep in typically developing preterm infants at NICU. aEEG may be an alternative adjunctive method to actigraphy for the evaluation of sleep/wake states in the NICU setting. Clinical trial registration number: NCT04145362

Current treatment guidelines do not provide recommendations to support the selection of treatment for most people with type 2 diabetes. We aimed to develop and validate an algorithm to allow selection of optimal treatment based on glycaemic response, weight change, and tolerability outcomes when choosing between SGLT2 inhibitor or DPP-4 inhibitor therapies.In this retrospective cohort study, we identified patients initiating SGLT2 and DPP-4 inhibitor therapies after Jan 1, 2013, from the UK Clinical Practice Research Datalink (CPRD). We excluded those who received SGLT2 or DPP-4 inhibitors as first-line treatment or insulin at the same time, had estimated glomerular filtration rate (eGFR) of less than 45 mL/min per 1·73 mAmong 10 253 patients initiating SGLT2 inhibitors and 16 624 patients initiating DPP-4 inhibitors in CPRD, baseline HbAA validated treatment selection algorithm for SGLT2 inhibitor and DPP-4 inhibitor therapies can support decisions on optimal treatment for people with type 2 diabetes.BHF-Turing Cardiovascular Data Science Award and the UK Medical Research Council.

Rigorous evaluation of artificial intelligence (AI) systems for image classification is essential before deployment into health-care settings, such as screening programmes, so that adoption is effective and safe. A key step in the evaluation process is the external validation of diagnostic performance using a test set of images. We conducted a rapid literature review on methods to develop test sets, published from 2012 to 2020, in English. Using thematic analysis, we mapped themes and coded the principles using the Population, Intervention, and Comparator or Reference standard, Outcome, and Study design framework. A group of screening and AI experts assessed the evidence-based principles for completeness and provided further considerations. From the final 15 principles recommended here, five affect population, one intervention, two comparator, one reference standard, and one both reference standard and comparator. Finally, four are appliable to outcome and one to study design. Principles from the literature were useful to address biases from AI; however, they did not account for screening specific biases, which we now incorporate. The principles set out here should be used to support the development and use of test sets for studies that assess the accuracy of AI within screening programmes, to ensure they are fit for purpose and minimise bias.

Background Idiopathic pulmonary fibrosis is a progressive fibrotic lung disease with a variable clinical trajectory. Decline in forced vital capacity (FVC) is the main indicator of progression; however, missingness prevents long-term analysis of patterns in lung function. We aimed to identify distinct clusters of lung function trajectory among patients with idiopathic pulmonary fibrosis using machine learning techniques. Methods We did a secondary analysis of longitudinal data on FVC collected from a cohort of patients with idiopathic pulmonary fibrosis from the PROFILE study; a multicentre, prospective, observational cohort study. We evaluated the imputation performance of conventional and machine learning techniques to impute missing data and then analysed the fully imputed dataset by unsupervised clustering using self-organising maps. We compared anthropometric features, genomic associations, serum biomarkers, and clinical outcomes between clusters. We also performed a replication of the analysis on data from a cohort of patients with idiopathic pulmonary fibrosis from an independent dataset, obtained from the Chicago Consortium. Findings 415 (71%) of 581 participants recruited into the PROFILE study were eligible for further analysis. An unsupervised machine learning algorithm had the lowest imputation error among tested methods, and self-organising maps identified four distinct clusters (1–4), which was confirmed by sensitivity analysis. Cluster 1 comprised 140 (34%) participants and was associated with a disease trajectory showing a linear decline in FVC over 3 years. Cluster 2 comprised 100 (24%) participants and was associated with a trajectory showing an initial improvement in FVC before subsequently decreasing. Cluster 3 comprised 113 (27%) participants and was associated with a trajectory showing an initial decline in FVC before subsequent stabilisation. Cluster 4 comprised 62 (15%) participants and was associated with a trajectory showing stable lung function. Median survival was shortest in cluster 1 (2·87 years [IQR 2·29–3·40]) and cluster 3 (2·23 years [1·75–3·84]), followed by cluster 2 (4·74 years [3·96–5·73]), and was longest in cluster 4 (5·56 years [5·18–6·62]). Baseline FEV1 to FVC ratio and concentrations of the biomarker SP-D were significantly higher in clusters 1 and 3. Similar lung function clusters with some shared anthropometric features were identified in the replication cohort. Interpretation Using a data-driven unsupervised approach, we identified four clusters of lung function trajectory with distinct clinical and biochemical features. Enriching or stratifying longitudinal spirometric data into clusters might optimise evaluation of intervention efficacy during clinical trials and patient management., National Institute for Health and Care Research, Medical Research Council, GlaxoSmithKline