Today, despite decades of developments in medicine and the growing interest in precision healthcare, vast majority of diagnoses happen once patients begin to show noticeable signs of illness. Early ...indication and detection of diseases, however, can provide patients and carers with the chance of early intervention, better disease management, and efficient allocation of healthcare resources. The latest developments in machine learning (including deep learning) provides a great opportunity to address this unmet need. In this study, we introduce BEHRT: A deep neural sequence transduction model for electronic health records (EHR), capable of simultaneously predicting the likelihood of 301 conditions in one's future visits. When trained and evaluated on the data from nearly 1.6 million individuals, BEHRT shows a striking improvement of 8.0-13.2% (in terms of average precision scores for different tasks), over the existing state-of-the-art deep EHR models. In addition to its scalability and superior accuracy, BEHRT enables personalised interpretation of its predictions; its flexible architecture enables it to incorporate multiple heterogeneous concepts (e.g., diagnosis, medication, measurements, and more) to further improve the accuracy of its predictions; its (pre-)training results in disease and patient representations can be useful for future studies (i.e., transfer learning).
Higher levels of physical activity (PA) are associated with a lower risk of cardiovascular disease (CVD). However, uncertainty exists on whether the inverse relationship between PA and incidence of ...CVD is greater at the highest levels of PA. Past studies have mostly relied on self-reported evidence from questionnaire-based PA, which is crude and cannot capture all PA undertaken. We investigated the association between accelerometer-measured moderate, vigorous, and total PA and incident CVD.
We obtained accelerometer-measured moderate-intensity and vigorous-intensity physical activities and total volume of PA, over a 7-day period in 2013-2015, for 90,211 participants without prior or concurrent CVD in the UK Biobank cohort. Participants in the lowest category of total PA smoked more, had higher body mass index and C-reactive protein, and were diagnosed with hypertension. PA was associated with 3,617 incident CVD cases during 440,004 person-years of follow-up (median (interquartile range IQR): 5.2 (1.2) years) using Cox regression models. We found a linear dose-response relationship for PA, whether measured as moderate-intensity, vigorous-intensity, or as total volume, with risk of incident of CVD. Hazard ratios (HRs) and 95% confidence intervals for increasing quarters of the PA distribution relative to the lowest fourth were for moderate-intensity PA: 0.71 (0.65, 0.77), 0.59 (0.54, 0.65), and 0.46 (0.41, 0.51); for vigorous-intensity PA: 0.70 (0.64, 0.77), 0.54 (0.49,0.59), and 0.41 (0.37,0.46); and for total volume of PA: 0.73 (0.67, 0.79), 0.63 (0.57, 0.69), and 0.47 (0.43, 0.52). We took account of potential confounders but unmeasured confounding remains a possibility, and while removal of early deaths did not affect the estimated HRs, we cannot completely dismiss the likelihood that reverse causality has contributed to the findings. Another possible limitation of this work is the quantification of PA intensity-levels based on methods validated in relatively small studies.
In this study, we found no evidence of a threshold for the inverse association between objectively measured moderate, vigorous, and total PA with CVD. Our findings suggest that PA is not only associated with lower risk for of CVD, but the greatest benefit is seen for those who are active at the highest level.
One major impediment to the wider use of deep learning for clinical decision making is the difficulty of assigning a level of confidence to model predictions. Currently, deep Bayesian neural networks ...and sparse Gaussian processes are the main two scalable uncertainty estimation methods. However, deep Bayesian neural networks suffer from lack of expressiveness, and more expressive models such as deep kernel learning, which is an extension of sparse Gaussian process, captures only the uncertainty from the higher-level latent space. Therefore, the deep learning model under it lacks interpretability and ignores uncertainty from the raw data. In this paper, we merge features of the deep Bayesian learning framework with deep kernel learning to leverage the strengths of both methods for a more comprehensive uncertainty estimation. Through a series of experiments on predicting the first incidence of heart failure, diabetes and depression applied to large-scale electronic medical records, we demonstrate that our method is better at capturing uncertainty than both Gaussian processes and deep Bayesian neural networks in terms of indicating data insufficiency and identifying misclassifications, with a comparable generalization performance. Furthermore, by assessing the accuracy and area under the receiver operating characteristic curve over the predictive probability, we show that our method is less susceptible to making overconfident predictions, especially for the minority class in imbalanced datasets. Finally, we demonstrate how uncertainty information derived by the model can inform risk factor analysis towards model interpretability.
Advances in public health and medical care have enabled better pregnancy and birth outcomes. The rates of perinatal health indicators such as maternal mortality and morbidity; fetal, neonatal, and ...infant mortality; low birthweight; and preterm birth have reduced over time. However, they are still a public health concern, and considerable disparities exist within and between countries. For perinatal researchers who are engaged in unraveling the tangled web of causation for maternal and child health outcomes and for clinicians involved in the care of pregnant women and infants, artificial intelligence offers novel approaches to prediction modeling, diagnosis, early detection, and monitoring in perinatal health. Machine learning, a commonly used artificial intelligence method, has been used to predict preterm birth, birthweight, preeclampsia, mortality, hypertensive disorders, and postpartum depression. Real-time electronic health recording and predictive modeling using artificial intelligence have found early success in fetal monitoring and monitoring of women with gestational diabetes especially in low-resource settings. Artificial intelligence–based methodologies have the potential to improve prenatal diagnosis of birth defects and outcomes in assisted reproductive technology too. In this scenario, we envision artificial intelligence for perinatal research to be based on three goals: (1) availability of population-representative, routine clinical data (rich multimodal data of large sample size) for perinatal research; (2) modification and application of current state-of-the-art artificial intelligence for prediction and classification in health care research to the field of perinatal health; and (3) development of methods for explaining the decision-making processes of artificial intelligence models for perinatal health indicators. Achieving these three goals via a multidisciplinary approach to the development of artificial intelligence tools will enable trust in these tools and advance research, clinical practice, and policies to ensure optimal perinatal health.
Current physical activity recommendations have been based on evidence from systematic reviews of questionnaire-based data. Questionnaire-based physical activity data are subject to both random and ...non-random error. If the estimated association between physical activity and health outcomes was different when a more accurate, objective measure was used, this would have important health policy implications for physical activity. We conducted a systematic review and meta-analysis of published cohort studies that investigated the association between an objective measure of physical activity and all cause mortality. We searched PubMed, Scopus, Embase, Cochrane library, and SPORTDiscus for prospective cohort studies that examined the association between objectively measured (accelerometer, pedometer, or doubly labeled water method) physical activity and mortality in adults aged≥18 years, of either sex. Summary hazard ratios and 95% confidence interval CIs were computed using random-effects models. Thirty-three articles from 15 cohort studies were identified that together ascertained 3903 deaths. The mean years of follow-up ranged from 2.3–14.2 years. Individuals in the highest category of light, moderate-to-vigorous, and total physical activity had 40% (95%CI 20% to 55%), 56% (95%CI 41% to 67%), and 67% (95%CI 57% to 75%), respectively, lower risk for mortality compared to individuals in the lowest category of light, moderate-to-vigorous, and total physical activity. The summary hazard ratio for objectively measured physical activity and all cause mortality is lower than previously estimated from questionnaire based studies. Current recommendations for physical activity that are based on subjective measurement may underestimate the true reduction in mortality risk associated with physical activity.
•Increased physical activity is beneficial, irrespective of the intensity-level.•Estimate from studies using objective measures is much lower than evidence from questionnaires.•Current physical activity recommendations may underestimate the true reduction in mortality.
There are few population-based studies of sufficient size and follow-up duration to have reliably assessed perinatal outcomes for pregnant women hospitalised with SARS-CoV-2 infection. The United ...Kingdom Obstetric Surveillance System (UKOSS) covers all 194 consultant-led UK maternity units and included all pregnant women admitted to hospital with an ongoing SARS-CoV-2 infection. Here we show that in this large national cohort comprising two years' active surveillance over four SARS-CoV-2 variant periods and with near complete follow-up of pregnancy outcomes for 16,627 included women, severe perinatal outcomes were more common in women with moderate to severe COVID-19, during the delta dominant period and among unvaccinated women. We provide strong evidence to recommend continuous surveillance of pregnancy outcomes in future pandemics and to continue to recommend SARS-CoV-2 vaccination in pregnancy to protect both mothers and babies.
The aims of this systematic review and meta-analysis are to examine the prevalence of adverse mental health outcomes, both short-term and long-term, among SARS patients, healthcare workers and the ...general public of SARS-affected regions, and to examine the protective and risk factors associated with these mental health outcomes.
We conducted a systematic search of the literature using databases such as Medline, Pubmed, Embase, PsycInfo, Web of Science Core Collection, CNKI, the National Central Library Online Catalog and dissertation databases to identify studies in the English or Chinese language published between January 2003 to May 2020 which reported psychological distress and mental health morbidities among SARS patients, healthcare workers, and the general public in regions with major SARS outbreaks.
The literature search yielded 6984 titles. Screening resulted in 80 papers for the review, 35 of which were included in the meta-analysis. The prevalence of post-recovery probable or clinician-diagnosed anxiety disorder, depressive disorder, and post-traumatic stress disorder (PTSD) among SARS survivors were 19, 20 and 28%, respectively. The prevalence of these outcomes among studies conducted within and beyond 6 months post-discharge was not significantly different. Certain aspects of mental health-related quality of life measures among SARS survivors remained impaired beyond 6 months post-discharge. The prevalence of probable depressive disorder and PTSD among healthcare workers post-SARS were 12 and 11%, respectively. The general public had increased anxiety levels during SARS, but whether there was a clinically significant population-wide mental health impact remained inconclusive. Narrative synthesis revealed occupational exposure to SARS patients and perceived stigmatisation to be risk factors for adverse mental health outcomes among healthcare workers, although causality could not be determined due to the limitations of the studies.
The chronicity of psychiatric morbidities among SARS survivors should alert us to the potential long-term mental health complications of covid-19 patients. Healthcare workers working in high-risk venues should be given adequate mental health support. Stigmatisation against patients and healthcare workers should be explored and addressed. The significant risk of bias and high degree of heterogeneity among included studies limited the certainty of the body of evidence of the review.
Background Myocardial infarction (MI), stroke and diabetes share underlying risk factors and commonalities in clinical management. We examined if their combined impact on mortality is proportional, ...amplified or less than the expected risk separately of each disease and whether the excess risk is explained by their associated comorbidities. Methods Using large-scale electronic health records, we identified 2,007,731 eligible patients (51% women) and registered with general practices in the UK and extracted clinical information including diagnosis of myocardial infarction (MI), stroke, diabetes and 53 other long-term conditions before 2005 (study baseline). We used Cox regression to determine the risk of all-cause mortality with age as the underlying time variable and tested for excess risk due to interaction between cardiometabolic conditions. Results At baseline, the mean age was 51 years, and 7% (N = 145,910) have had a cardiometabolic condition. After a 7-year mean follow-up, 146,994 died. The sex-adjusted hazard ratios (HR) (95% confidence interval CI) of all-cause mortality by baseline disease status, compared to those without cardiometabolic disease, were MI = 1.51 (1.49-1.52), diabetes = 1.52 (1.51-1.53), stroke = 1.84 (1.82-1.86), MI and diabetes = 2.14 (2.11-2.17), MI and stroke = 2.35 (2.30-2.39), diabetes and stroke = 2.53 (2.50-2.57) and all three = 3.22 (3.15-3.30). Adjusting for other concurrent comorbidities attenuated these estimates, including the risk associated with having all three conditions (HR = 1.81 95% CI 1.74-1.89). Excess risks due to interaction between cardiometabolic conditions, particularly when all three conditions were present, were not significantly greater than expected from the individual disease effects. Conclusion Myocardial infarction, stroke and diabetes were associated with excess mortality, without evidence of any amplification of risk in people with all three diseases. The presence of other comorbidities substantially contributed to the excess mortality risks associated with cardiometabolic disease multimorbidity. Keywords: Myocardial infarction, Stroke, Diabetes, Multimorbidity, Mortality, Electronic health records