Foundation models for generalist medical artificial intelligence.

The exceptionally rapid development of highly flexible, reusable artificial intelligence (AI) models is likely to usher in newfound capabilities in medicine. We propose a new paradigm for medical AI, which we refer to as generalist medical AI (GMAI). GMAI models will be capable of carrying out a diverse set of tasks using very little or no task-specific labelled data. Built through self-supervision on large, diverse datasets, GMAI will flexibly interpret different combinations of medical modalities, including data from imaging, electronic health records, laboratory results, genomics, graphs or medical text. Models will in turn produce expressive outputs such as free-text explanations, spoken recommendations or image annotations that demonstrate advanced medical reasoning abilities. Here we identify a set of high-impact potential applications for GMAI and lay out specific technical capabilities and training datasets necessary to enable them. We expect that GMAI-enabled applications will challenge current strategies for regulating and validating AI devices for medicine and will shift practices associated with the collection of large medical datasets.

Informative missingness: What can we learn from patterns in missing laboratory data in the electronic health record?

BACKGROUND: In electronic health records, patterns of missing laboratory test results could capture patients' course of disease as well as ​​reflect clinician's concerns or worries for possible conditions. These patterns are often understudied and overlooked. This study aims to identify informative patterns of missingness among laboratory data collected across 15 healthcare system sites in three countries for COVID-19 inpatients. METHODS: We collected and analyzed demographic, diagnosis, and laboratory data for 69,939 patients with positive COVID-19 PCR tests across three countries from 1 January 2020 through 30 September 2021. We analyzed missing laboratory measurements across sites, missingness stratification by demographic variables, temporal trends of missingness, correlations between labs based on missingness indicators over time, and clustering of groups of labs based on their missingness/ordering pattern. RESULTS: With these analyses, we identified mapping issues faced in seven out of 15 sites. We also identified nuances in data collection and variable definition for the various sites. Temporal trend analyses may support the use of laboratory test result missingness patterns in identifying severe COVID-19 patients. Lastly, using missingness patterns, we determined relationships between various labs that reflect clinical behaviors. CONCLUSION: In this work, we use computational approaches to relate missingness patterns to hospital treatment capacity and highlight the heterogeneity of looking at COVID-19 over time and at multiple sites, where there might be different phases, policies, etc. Changes in missingness could suggest a change in a patient's condition, and patterns of missingness among laboratory measurements could potentially identify clinical outcomes. This allows sites to consider missing data as informative to analyses and help researchers identify which sites are better poised to study particular questions.

Crowdsourcing for Machine Learning in Public Health Surveillance: Lessons Learned From Amazon Mechanical Turk.

BACKGROUND: Crowdsourcing services, such as Amazon Mechanical Turk (AMT), allow researchers to use the collective intelligence of a wide range of web users for labor-intensive tasks. As the manual verification of the quality of the collected results is difficult because of the large volume of data and the quick turnaround time of the process, many questions remain to be explored regarding the reliability of these resources for developing digital public health systems. OBJECTIVE: This study aims to explore and evaluate the application of crowdsourcing, generally, and AMT, specifically, for developing digital public health surveillance systems. METHODS: We collected 296,166 crowd-generated labels for 98,722 tweets, labeled by 610 AMT workers, to develop machine learning (ML) models for detecting behaviors related to physical activity, sedentary behavior, and sleep quality among Twitter users. To infer the ground truth labels and explore the quality of these labels, we studied 4 statistical consensus methods that are agnostic of task features and only focus on worker labeling behavior. Moreover, to model the meta-information associated with each labeling task and leverage the potential of context-sensitive data in the truth inference process, we developed 7 ML models, including traditional classifiers (offline and active), a deep learning-based classification model, and a hybrid convolutional neural network model. RESULTS: Although most crowdsourcing-based studies in public health have often equated majority vote with quality, the results of our study using a truth set of 9000 manually labeled tweets showed that consensus-based inference models mask underlying uncertainty in data and overlook the importance of task meta-information. Our evaluations across 3 physical activity, sedentary behavior, and sleep quality data sets showed that truth inference is a context-sensitive process, and none of the methods studied in this paper were consistently superior to others in predicting the truth label. We also found that the performance of the ML models trained on crowd-labeled data was sensitive to the quality of these labels, and poor-quality labels led to incorrect assessment of these models. Finally, we have provided a set of practical recommendations to improve the quality and reliability of crowdsourced data. CONCLUSIONS: Our findings indicate the importance of the quality of crowd-generated labels in developing ML models designed for decision-making purposes, such as public health surveillance decisions. A combination of inference models outlined and analyzed in this study could be used to quantitatively measure and improve the quality of crowd-generated labels for training ML models.

Using Item Response Theory for Explainable Machine Learning in Predicting Mortality in the Intensive Care Unit: Case-Based Approach.

BACKGROUND: Supervised machine learning (ML) is being featured in the health care literature with study results frequently reported using metrics such as accuracy, sensitivity, specificity, recall, or F1 score. Although each metric provides a different perspective on the performance, they remain to be overall measures for the whole sample, discounting the uniqueness of each case or patient. Intuitively, we know that all cases are not equal, but the present evaluative approaches do not take case difficulty into account. OBJECTIVE: A more case-based, comprehensive approach is warranted to assess supervised ML outcomes and forms the rationale for this study. This study aims to demonstrate how the item response theory (IRT) can be used to stratify the data based on how difficult each case is to classify, independent of the outcome measure of interest (eg, accuracy). This stratification allows the evaluation of ML classifiers to take the form of a distribution rather than a single scalar value. METHODS: Two large, public intensive care unit data sets, Medical Information Mart for Intensive Care III and electronic intensive care unit, were used to showcase this method in predicting mortality. For each data set, a balanced sample (n=8078 and n=21,940, respectively) and an imbalanced sample (n=12,117 and n=32,910, respectively) were drawn. A 2-parameter logistic model was used to provide scores for each case. Several ML algorithms were used in the demonstration to classify cases based on their health-related features: logistic regression, linear discriminant analysis, K-nearest neighbors, decision tree, naive Bayes, and a neural network. Generalized linear mixed model analyses were used to assess the effects of case difficulty strata, ML algorithm, and the interaction between them in predicting accuracy. RESULTS: The results showed significant effects (P<.001) for case difficulty strata, ML algorithm, and their interaction in predicting accuracy and illustrated that all classifiers performed better with easier-to-classify cases and that overall the neural network performed best. Significant interactions suggest that cases that fall in the most arduous strata should be handled by logistic regression, linear discriminant analysis, decision tree, or neural network but not by naive Bayes or K-nearest neighbors. Conventional metrics for ML classification have been reported for methodological comparison. CONCLUSIONS: This demonstration shows that using the IRT is a viable method for understanding the data that are provided to ML algorithms, independent of outcome measures, and highlights how well classifiers differentiate cases of varying difficulty. This method explains which features are indicative of healthy states and why. It enables end users to tailor the classifier that is appropriate to the difficulty level of the patient for personalized medicine.

The effects of folate supplementation on inflammatory factors and biomarkers of oxidative stress in overweight and obese women with polycystic ovary syndrome: a randomized, double-blind, placebo-controlled clinical trial.

OBJECTIVE: This study was conducted to determine the effects of folate supplementation on inflammatory factors and biomarkers of oxidative stress among women with polycystic ovary syndrome (PCOS). DESIGN, PATIENTS AND MEASUREMENTS: This randomized, double-blind, placebo-controlled clinical trial was conducted among 69 women diagnosed with PCOS and aged 18-40 year old. Participants were randomly assigned to three groups receiving the following: (1) folate-1: 1 mg/d folate supplements (N = 23); (2) folate-5: 5 mg/d folate supplements (N = 23) and (3) placebo (N = 23) for 8 weeks. Fasting blood samples were taken at the beginning of the study and after 8 weeks to measure homocysteine (Hcy), inflammatory factors including high-sensitivity C-reactive protein (hs-CRP), nitric oxide (NO), biomarkers of oxidative stress including total antioxidant capacity (TAC), glutathione (GSH), malondialdehyde (MDA) and homoeostatic model assessment-beta cell function (HOMA-B). RESULTS: Supplementation with 5 mg/d folate resulted in reduced plasma Hcy (-2·23 vs -1·86 and 1·16 µm, respectively, P < 0·05), HOMA-B (-7·63 vs 1·43 and 13·66, respectively, P < 0·05), serum hs-CRP (-212·2 vs -262·4 and 729·8 µg/l, respectively, P < 0·05) and plasma MDA concentrations (-0·48 vs -0·24 and 0·69 µm, respectively, P < 0·01) compared with folate-1 and placebo groups. Furthermore, a significant rise in plasma TAC (0·64 vs -3·53 and -215·47 mm, respectively, P < 0·01) and GSH levels (162·1 vs 195·8 and -158·2 µm, respectively, P < 0·01) was also observed following the administration of 5 mg/d folate supplements compared with folate-1 and placebo groups. CONCLUSIONS: In conclusion, folate supplementation (5 mg/d) in women with PCOS had beneficial effects on inflammatory factors and biomarkers of oxidative stress.

Effects of daily consumption of synbiotic bread on insulin metabolism and serum high-sensitivity C-reactive protein among diabetic patients: a double-blind, randomized, controlled clinical trial.

BACKGROUND: This study was conducted to evaluate the effects of daily consumption of synbiotic bread on the metabolic status of patients with type 2 diabetes mellitus. METHODS: This randomized, double-blind, controlled clinical trial was performed in 81 diabetic patients. The subjects were randomly assigned to consumption of synbiotic (n = 27), probiotic (n = 27), or control bread (n = 27) for 8 weeks 3 times a day in a 40-gram package. The synbiotic bread contained Lactobacillus sporogenes (1 × 10(8) CFU) and 0.07 g inulin per 1 g. The probiotic bread contained L. sporogenes (1 × 10(8) CFU per 1 g). Fasting blood samples were taken at baseline and after an 8-week intervention for quantification of related factors. RESULTS: Consumption of the synbiotic bread resulted in a significant reduction in serum insulin levels (-3.2 ± 5.4 vs. -0.3 ± 3.4 and 0.6 ± 4.7 µIU/ml, respectively, p = 0.007), homeostatic model assessment for insulin resistance scores (-1.5 ± 2.7 vs. -0.2 ± 1.6 and 0.4 ± 3.5, respectively, p = 0.03), and homeostatic model assessment-ß-cell function (-7.2 ± 16.3 vs. -0.7 ± 10.8 and 0.7 ± 8.2, respectively, p = 0.04) compared to the probiotic and control breads. We did not find any significant effect of synbiotic bread consumption on fasting plasma glucose, the quantitative insulin sensitivity check index, or serum hs-CRP levels compared to other breads. CONCLUSION: Consumption of the synbiotic bread among diabetic patients had beneficial effects on insulin metabolism.

Foundation metrics for evaluating effectiveness of healthcare conversations powered by generative AI.

Generative Artificial Intelligence is set to revolutionize healthcare delivery by transforming traditional patient care into a more personalized, efficient, and proactive process. Chatbots, serving as interactive conversational models, will probably drive this patient-centered transformation in healthcare. Through the provision of various services, including diagnosis, personalized lifestyle recommendations, dynamic scheduling of follow-ups, and mental health support, the objective is to substantially augment patient health outcomes, all the while mitigating the workload burden on healthcare providers. The life-critical nature of healthcare applications necessitates establishing a unified and comprehensive set of evaluation metrics for conversational models. Existing evaluation metrics proposed for various generic large language models (LLMs) demonstrate a lack of comprehension regarding medical and health concepts and their significance in promoting patients' well-being. Moreover, these metrics neglect pivotal user-centered aspects, including trust-building, ethics, personalization, empathy, user comprehension, and emotional support. The purpose of this paper is to explore state-of-the-art LLM-based evaluation metrics that are specifically applicable to the assessment of interactive conversational models in healthcare. Subsequently, we present a comprehensive set of evaluation metrics designed to thoroughly assess the performance of healthcare chatbots from an end-user perspective. These metrics encompass an evaluation of language processing abilities, impact on real-world clinical tasks, and effectiveness in user-interactive conversations. Finally, we engage in a discussion concerning the challenges associated with defining and implementing these metrics, with particular emphasis on confounding factors such as the target audience, evaluation methods, and prompt techniques involved in the evaluation process.

Neurological diagnoses in hospitalized COVID-19 patients associated with adverse outcomes: A multinational cohort study.

Few studies examining the patient outcomes of concurrent neurological manifestations during acute COVID-19 leveraged multinational cohorts of adults and children or distinguished between central and peripheral nervous system (CNS vs. PNS) involvement. Using a federated multinational network in which local clinicians and informatics experts curated the electronic health records data, we evaluated the risk of prolonged hospitalization and mortality in hospitalized COVID-19 patients from 21 healthcare systems across 7 countries. For adults, we used a federated learning approach whereby we ran Cox proportional hazard models locally at each healthcare system and performed a meta-analysis on the aggregated results to estimate the overall risk of adverse outcomes across our geographically diverse populations. For children, we reported descriptive statistics separately due to their low frequency of neurological involvement and poor outcomes. Among the 106,229 hospitalized COVID-19 patients (104,031 patients ≥18 years; 2,198 patients <18 years, January 2020-October 2021), 15,101 (14%) had at least one CNS diagnosis, while 2,788 (3%) had at least one PNS diagnosis. After controlling for demographics and pre-existing conditions, adults with CNS involvement had longer hospital stay (11 versus 6 days) and greater risk of (Hazard Ratio = 1.78) and faster time to death (12 versus 24 days) than patients with no neurological condition (NNC) during acute COVID-19 hospitalization. Adults with PNS involvement also had longer hospital stay but lower risk of mortality than the NNC group. Although children had a low frequency of neurological involvement during COVID-19 hospitalization, a substantially higher proportion of children with CNS involvement died compared to those with NNC (6% vs 1%). Overall, patients with concurrent CNS manifestation during acute COVID-19 hospitalization faced greater risks for adverse clinical outcomes than patients without any neurological diagnosis. Our global informatics framework using a federated approach (versus a centralized data collection approach) has utility for clinical discovery beyond COVID-19.

Vitamin D supplementation affects serum high-sensitivity C-reactive protein, insulin resistance, and biomarkers of oxidative stress in pregnant women.

Unfavorable metabolic profiles and oxidative stress in pregnancy are associated with several complications. This study was conducted to determine the effects of vitamin D supplementation on serum concentrations of high-sensitivity C-reactive protein (hs-CRP), metabolic profiles, and biomarkers of oxidative stress in healthy pregnant women. This randomized, double-blind, placebo-controlled clinical trial was conducted in 48 pregnant women aged 18-40 y old at 25 wk of gestation. Participants were randomly assigned to receive either 400 IU/d cholecalciferol supplements (n = 24) or placebo (n = 24) for 9 wk. Fasting blood samples were taken at study baseline and after 9 wk of intervention to quantify serum concentrations of hs-CRP, lipid concentrations, insulin, and biomarkers of oxidative stress. After 9 wk of intervention, the increases in serum 25-hydroxyvitamin D and calcium concentrations were greater in the vitamin D group (+3.7 µg/L and +0.20 mg/dL, respectively) than in the placebo group (-1.2 µg/L and -0.12 mg/dL, respectively; P < 0.001 for both). Vitamin D supplementation resulted in a significant decrease in serum hs-CRP (vitamin D vs. placebo groups: -1.41 vs. +1.50 µg/mL; P-interaction = 0.01) and insulin concentrations (vitamin D vs. placebo groups: -1.0 vs. +2.6 µIU/mL; P-interaction = 0.04) and a significant increase in the Quantitative Insulin Sensitivity Check Index score (vitamin D vs. placebo groups: +0.02 vs. -0.02; P-interaction = 0.006), plasma total antioxidant capacity (vitamin D vs. placebo groups: +152 vs. -20 mmol/L; P-interaction = 0.002), and total glutathione concentrations (vitamin D vs. placebo groups: +205 vs. -32 µmol/L; P-interaction = 0.02) compared with placebo. Intake of vitamin D supplements led to a significant decrease in fasting plasma glucose (vitamin D vs. placebo groups: -0.65 vs. -0.12 mmol/L; P-interaction = 0.01), systolic blood pressure (vitamin D vs. placebo groups: -0.2 vs. +5.5 mm Hg; P-interaction = 0.01), and diastolic blood pressure (vitamin D vs. placebo groups: -0.4 vs. +3.1 mm Hg; P-interaction = 0.01) compared with placebo. In conclusion, vitamin D supplementation for 9 wk among pregnant women has beneficial effects on metabolic status.

Effect of multispecies probiotic supplements on metabolic profiles, hs-CRP, and oxidative stress in patients with type 2 diabetes.

BACKGROUND: We are aware of no study that has indicated the effects of daily consumption of multispecies probiotic supplements on metabolic profiles, high-sensitivity C-reactive protein (hs-CRP), and oxidative stress in diabetic patients. OBJECTIVE: This study was designed to determine the effects of multispecies probiotic supplements on metabolic profiles, hs-CRP, and oxidative stress in diabetic patients. METHODS: This randomized double-blind placebo-controlled clinical trial was performed on 54 diabetic patients aged 35-70 years. Subjects were randomly assigned to take either a multispecies probiotic supplement (n = 27) or placebo (n = 27) for 8 weeks. The multispecies probiotic supplement consisted of 7 viable and freeze-dried strains: Lactobacillus acidophilus (2 × 10(9) CFU), L. casei (7 × 10(9) CFU), L. rhamnosus (1.5 × 10(9) CFU), L. bulgaricus (2 × 10(8) CFU), Bifidobacterium breve (2 × 10(10) CFU), B. longum (7 × 10(9) CFU), Streptococcus thermophilus (1.5 × 10(9) CFU), and 100 mg fructo-oligosaccharide. Fasting blood samples were taken at baseline and after intervention to measure metabolic profiles, hs-CRP, and biomarkers of oxidative stress including plasma total antioxidant capacity and total glutathione (GSH). RESULTS: Between-group comparisons of fasting plasma glucose (FPG) revealed that consumption of probiotic supplements prevented a rise in FPG (+28.8 ± 8.5 for placebo vs. +1.6 ± 6 mg/dl for probiotic group, p = 0.01). Although a significant within-group increase in serum insulin and low-density lipoprotein cholesterol levels was found in both the probiotic group and the placebo group, the changes were similar between the two groups. We observed a significant increase in HOMA-IR (homeostasis model of assessment-insulin resistance) in both the probiotic group (p = 0.02) and the placebo group (p = 0.001); however, the increase in the placebo group was significantly higher than that in the probiotic group (+2.38 vs. +0.78, p = 0.03). Mean changes in serum hs-CRP were significantly different between the two groups (-777.57 for the probiotic group vs. +878.72 ng/ml for the placebo group, p = 0.02). Probiotic supplementation led to a significant increase in plasma GSH levels compared to placebo (240.63 vs. -33.46 µmol/l, p = 0.03). CONCLUSION: In conclusion, multispecies probiotic supplementation, compared with placebo, for 8 weeks in diabetic patients prevented a rise in FPG and resulted in a decrease in serum hs-CRP and an increase in plasma total GSH.

Predicting patient decompensation from continuous physiologic monitoring in the emergency department.

Anticipation of clinical decompensation is essential for effective emergency and critical care. In this study, we develop a multimodal machine learning approach to predict the onset of new vital sign abnormalities (tachycardia, hypotension, hypoxia) in ED patients with normal initial vital signs. Our method combines standard triage data (vital signs, demographics, chief complaint) with features derived from a brief period of continuous physiologic monitoring, extracted via both conventional signal processing and transformer-based deep learning on ECG and PPG waveforms. We study 19,847 adult ED visits, divided into training (75%), validation (12.5%), and a chronologically sequential held-out test set (12.5%). The best-performing models use a combination of engineered and transformer-derived features, predicting in a 90-minute window new tachycardia with AUROC of 0.836 (95% CI, 0.800-0.870), new hypotension with AUROC 0.802 (95% CI, 0.747-0.856), and new hypoxia with AUROC 0.713 (95% CI, 0.680-0.745), in all cases significantly outperforming models using only standard triage data. Salient features include vital sign trends, PPG perfusion index, and ECG waveforms. This approach could improve the triage of apparently stable patients and be applied continuously for the prediction of near-term clinical deterioration.

Unlocking the Power of EHRs: Harnessing Unstructured Data for Machine Learning-based Outcome Predictions.

The integration of Electronic Health Records (EHRs) with Machine Learning (ML) models has become imperative in examining patient outcomes due to the vast amounts of clinical data they provide. However, critical information regarding social and behavioral factors that affect health, such as social isolation, stress, and mental health complexities, is often recorded in unstructured clinical notes, hindering its accessibility. This has resulted in an over-reliance on clinical data in current EHR-based research, potentially leading to disparities in health outcomes. This study aims to evaluate the impact of incorporating patient-specific context from unstructured EHR data on the accuracy and stability of ML algorithms for predicting mortality, using the MIMIC III database. Results from the study confirmed the significance of incorporating patient-specific information into prediction models, leading to a notable improvement in the discriminatory power and robustness of the ML algorithms. Furthermore, the findings underline the importance of considering non-clinical factors related to a patient's daily life, in addition to clinical factors, when making predictions about patient outcomes. The advent of advanced generative models, such as GPT-4, presents new opportunities for effectively extracting social and behavioral factors from unstructured clinical notes, further enhancing the accuracy and stability of ML algorithms in predicting patient outcomes. The results of our study have significant ramifications for improving ML in clinical decision support and patient outcome predictions, specifically highlighting the potential role of generative models like GPT-4 in advancing ML-based outcome predictions.

Evaluating progress in automatic chest X-ray radiology report generation.

Artificial intelligence (AI) models for automatic generation of narrative radiology reports from images have the potential to enhance efficiency and reduce the workload of radiologists. However, evaluating the correctness of these reports requires metrics that can capture clinically pertinent differences. In this study, we investigate the alignment between automated metrics and radiologists' scoring of errors in report generation. We address the limitations of existing metrics by proposing new metrics, RadGraph F1 and RadCliQ, which demonstrate stronger correlation with radiologists' evaluations. In addition, we analyze the failure modes of the metrics to understand their limitations and provide guidance for metric selection and interpretation. This study establishes RadGraph F1 and RadCliQ as meaningful metrics for guiding future research in radiology report generation.

A retrospective cohort analysis leveraging augmented intelligence to characterize long COVID in the electronic health record: A precision medicine framework.

Physical and psychological symptoms lasting months following an acute COVID-19 infection are now recognized as post-acute sequelae of COVID-19 (PASC). Accurate tools for identifying such patients could enhance screening capabilities for the recruitment for clinical trials, improve the reliability of disease estimates, and allow for more accurate downstream cohort analysis. In this retrospective cohort study, we analyzed the EHR of hospitalized COVID-19 patients across three healthcare systems to develop a pipeline for better identifying patients with persistent PASC symptoms (dyspnea, fatigue, or joint pain) after their SARS-CoV-2 infection. We implemented distributed representation learning powered by the Machine Learning for modeling Health Outcomes (MLHO) to identify novel EHR features that could suggest PASC symptoms outside of typical diagnosis codes. MLHO applies an entropy-based feature selection and boosting algorithms for representation mining. These improved definitions were then used for estimating PASC among hospitalized patients. 30,422 hospitalized patients were diagnosed with COVID-19 across three healthcare systems between March 13, 2020 and February 28, 2021. The mean age of the population was 62.3 years (SD, 21.0 years) and 15,124 (49.7%) were female. We implemented the distributed representation learning technique to augment PASC definitions. These definitions were found to have positive predictive values of 0.73, 0.74, and 0.91 for dyspnea, fatigue, and joint pain, respectively. We estimated that 25 percent (CI 95%: 6-48), 11 percent (CI 95%: 6-15), and 13 percent (CI 95%: 8-17) of hospitalized COVID-19 patients will have dyspnea, fatigue, and joint pain, respectively, 3 months or longer after a COVID-19 diagnosis. We present a validated framework for screening and identifying patients with PASC in the EHR and then use the tool to estimate its prevalence among hospitalized COVID-19 patients.

Effect of daily consumption of probiotic yogurt on oxidative stress in pregnant women: a randomized controlled clinical trial.

BACKGROUND: Due to the enhanced oxygen requirement of the mitochondria-rich placenta primarily during the third trimester, pregnancy is associated with elevated levels of oxidative stress. This study was designed to determine the effects of daily consumption of probiotic yogurt on oxidative stress among Iranian pregnant women. METHODS: This randomized single-blind controlled clinical trial was performed among 70 pregnant women, singleton primigravida, aged 18-30 in their third trimester. Subjects were randomly assigned to two groups to consume 200 g/day of either conventional yogurt (n = 33) or probiotic yogurt (n = 37) for 9 weeks. Fasting blood samples were taken at baseline and after a 9-week intervention to measure oxidative stress parameters. RESULTS: Consumption of probiotic yogurt resulted in increased erythrocyte glutathione reductase (GR) levels as compared to the conventional yogurt (p = 0.01). Despite the significant effect of probiotic yogurt consumption on plasma glutathione (67.9 µmol/l, p = 0.01), erythrocyte glutathione peroxidase (163 mmol/min/ml, p = 0.04) and serum 8-oxo-7,8-dihydroguanine levels (-74.3 ng/ml, p = 0.04), no significant differences were found between the two yogurts in terms of their effects on the mentioned parameters. CONCLUSION: Consumption of probiotic yogurt among pregnant women resulted in increased levels of erythrocyte GR as compared to the conventional yogurt, but could not affect other indices of oxidative stress.

Physical Activity, Sedentary Behavior, and Sleep on Twitter: Multicountry and Fully Labeled Public Data Set for Digital Public Health Surveillance Research.

BACKGROUND: Advances in automated data processing and machine learning (ML) models, together with the unprecedented growth in the number of social media users who publicly share and discuss health-related information, have made public health surveillance (PHS) one of the long-lasting social media applications. However, the existing PHS systems feeding on social media data have not been widely deployed in national surveillance systems, which appears to stem from the lack of practitioners and the public's trust in social media data. More robust and reliable data sets over which supervised ML models can be trained and tested reliably is a significant step toward overcoming this hurdle. The health implications of daily behaviors (physical activity, sedentary behavior, and sleep [PASS]), as an evergreen topic in PHS, are widely studied through traditional data sources such as surveillance surveys and administrative databases, which are often several months out-of-date by the time they are used, costly to collect, and thus limited in quantity and coverage. OBJECTIVE: The main objective of this study is to present a large-scale, multicountry, longitudinal, and fully labeled data set to enable and support digital PASS surveillance research in PHS. To support high-quality surveillance research using our data set, we have conducted further analysis on the data set to supplement it with additional PHS-related metadata. METHODS: We collected the data of this study from Twitter using the Twitter livestream application programming interface between November 28, 2018, and June 19, 2020. To obtain PASS-related tweets for manual annotation, we iteratively used regular expressions, unsupervised natural language processing, domain-specific ontologies, and linguistic analysis. We used Amazon Mechanical Turk to label the collected data to self-reported PASS categories and implemented a quality control pipeline to monitor and manage the validity of crowd-generated labels. Moreover, we used ML, latent semantic analysis, linguistic analysis, and label inference analysis to validate the different components of the data set. RESULTS: LPHEADA (Labelled Digital Public Health Dataset) contains 366,405 crowd-generated labels (3 labels per tweet) for 122,135 PASS-related tweets that originated in Australia, Canada, the United Kingdom, or the United States, labeled by 708 unique annotators on Amazon Mechanical Turk. In addition to crowd-generated labels, LPHEADA provides details about the three critical components of any PHS system: place, time, and demographics (ie, gender and age range) associated with each tweet. CONCLUSIONS: Publicly available data sets for digital PASS surveillance are usually isolated and only provide labels for small subsets of the data. We believe that the novelty and comprehensiveness of the data set provided in this study will help develop, evaluate, and deploy digital PASS surveillance systems. LPHEADA will be an invaluable resource for both public health researchers and practitioners.

International electronic health record-derived post-acute sequelae profiles of COVID-19 patients.

The risk profiles of post-acute sequelae of COVID-19 (PASC) have not been well characterized in multi-national settings with appropriate controls. We leveraged electronic health record (EHR) data from 277 international hospitals representing 414,602 patients with COVID-19, 2.3 million control patients without COVID-19 in the inpatient and outpatient settings, and over 221 million diagnosis codes to systematically identify new-onset conditions enriched among patients with COVID-19 during the post-acute period. Compared to inpatient controls, inpatient COVID-19 cases were at significant risk for angina pectoris (RR 1.30, 95% CI 1.09-1.55), heart failure (RR 1.22, 95% CI 1.10-1.35), cognitive dysfunctions (RR 1.18, 95% CI 1.07-1.31), and fatigue (RR 1.18, 95% CI 1.07-1.30). Relative to outpatient controls, outpatient COVID-19 cases were at risk for pulmonary embolism (RR 2.10, 95% CI 1.58-2.76), venous embolism (RR 1.34, 95% CI 1.17-1.54), atrial fibrillation (RR 1.30, 95% CI 1.13-1.50), type 2 diabetes (RR 1.26, 95% CI 1.16-1.36) and vitamin D deficiency (RR 1.19, 95% CI 1.09-1.30). Outpatient COVID-19 cases were also at risk for loss of smell and taste (RR 2.42, 95% CI 1.90-3.06), inflammatory neuropathy (RR 1.66, 95% CI 1.21-2.27), and cognitive dysfunction (RR 1.18, 95% CI 1.04-1.33). The incidence of post-acute cardiovascular and pulmonary conditions decreased across time among inpatient cases while the incidence of cardiovascular, digestive, and metabolic conditions increased among outpatient cases. Our study, based on a federated international network, systematically identified robust conditions associated with PASC compared to control groups, underscoring the multifaceted cardiovascular and neurological phenotype profiles of PASC.

Detecting Uncertainty of Mortality Prediction Using Confident Learning.

Early mortality prediction is an actively researched problem that has led to the development of various severity scores and machine learning (ML) models for accurate and reliable detection of mortality in severely ill patients staying in intensive care units (ICUs). However, the uncertainty of such predictions due to irregular patient sampling, missing information, or high diversity of patient data has not yet been adequately addressed. In this paper, we used confident learning (CL) to incorporate sample-uncertainty information into our mortality prediction models and evaluated the performance of these models using a large dataset of 139,367 unique ICU admissions within the eICU Collaborative Research Database (eICU-CRD). The results of our study validate the importance of uncertainty quantification in patient outcome prediction and show that the state-of-the-art ML models augmented with CL are more robust against epistemic error and class imbalance.

Predicting Discharge Destination of Critically Ill Patients Using Machine Learning.

Decision making about discharge destination for critically ill patients is a highly subjective and multidisciplinary process, heavily reliant on the ICU care team, patients and their caregivers' preferences, resource demand, staffing, and bed capacity. Timely identification of discharge disposition can be useful in care planning, and as a surrogate for functional status outcomes following critical illness. Although prior research has proposed methods to predict discharge destination in a critical care setting, they are limited in scope and in the generalizability of their findings. We proposed and implemented different machine learning architectures to determine the efficacy of the Acute Physiology and Chronic Health Evaluation (APACHE) IV score as well as the patient characteristics that comprise it to predict the discharge destination for critically ill patients within 24 hours of ICU admission. We conducted a retrospective study of ICU admissions within the eICU Collaborative Research Database (eICU-CRD) populated with de-identified clinical data from adult patients admitted to an ICU between 2014 and 2015. Machine learning models were developed to predict four discharge categories: death, home, nursing facility, and rehabilitation. These models were trained and tested on 115,248 unique ICU admissions. To mitigate class imbalance, we used synthetic minority over-sampling techniques. Hierarchical and ensemble classifiers were used to further study the impact of imbalanced testing set on the performance of our predictive models. Amongst all of the tested models, XGBoost provided the best discrimination performance with an area under the receiver operating characteristic curve of 90% (recall: 71%, F1: 70%). Our findings indicate that the variables used in the APACHE IV model for estimating patient severity of illness are better predictors of hospital discharge destination than the APACHE IV score alone. Incorporating these models into clinical decision support systems may assist patients, caregivers, and the ICU team to begin disposition planning as early as possible during the hospitalization.