Search

BackgroundCommon disease-specific outcomes are vital for ensuring comparability of clinical trial data and enabling meta analyses and interstudy comparisons. Traditionally, the process of deciding which outcomes should be recommended as common for a particular disease relied on assembling and surveying panels of subject-matter experts. This is usually a time-consuming and laborious process. ObjectiveThe objectives of this work were to develop and evaluate a generalized pipeline that can automatically identify common outcomes specific to any given disease by finding, downloading, and analyzing data of previous clinical trials relevant to that disease. MethodsAn automated pipeline to interface with ClinicalTrials.gov’s application programming interface and download the relevant trials for the input condition was designed. The primary and secondary outcomes of those trials were parsed and grouped based on text similarity and ranked based on frequency. The quality and usefulness of the pipeline’s output were assessed by comparing the top outcomes identified by it for chronic obstructive pulmonary disease (COPD) to a list of 80 outcomes manually abstracted from the most frequently cited and comprehensive reviews delineating clinical outcomes for COPD. ResultsThe common disease-specific outcome pipeline successfully downloaded and processed 3876 studies related to COPD. Manual verification indicated that the pipeline was downloading and processing the same number of trials as were obtained from the self-service ClinicalTrials.gov portal. Evaluating the automatically identified outcomes against the manually abstracted ones showed that the pipeline achieved a recall of 92% and precision of 79%. The precision number indicated that the pipeline was identifying many outcomes that were not covered in the literature reviews. Assessment of those outcomes indicated that they are relevant to COPD and could be considered in future research. ConclusionsAn automated evidence-based pipeline can identify common clinical trial outcomes of comparable breadth and quality as the outcomes identified in comprehensive literature reviews. Moreover, such an approach can highlight relevant outcomes for further consideration.

BackgroundCOVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking. ObjectiveThe aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points. MethodsWe used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19–positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions. ResultsUpon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction. ConclusionsWe externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.

BackgroundThe potential of interactive health education for preventive health applications has been widely demonstrated. However, use of mobile apps to promote smoking cessation in hospitalized patients has not been systematically assessed. ObjectiveThis study was conducted to assess the feasibility of using a mobile app for the hazards of smoking education delivered via touch screen tablets to hospitalized smokers. MethodsFifty-five consecutive hospitalized smokers were recruited. Patient sociodemographics and smoking history was collected at baseline. The impact of the mobile app was assessed by measuring cognitive and behavioral factors shown to promote smoking cessation before and after the mobile app use including hazards of smoking knowledge score (KS), smoking attitudes, and stages of change. ResultsAfter the mobile app use, mean KS increased from 27(3) to 31(3) (P

Background The prevalence of smoking is very high among methadone users. As a method of delivering health education, computers can be utilized effectively. However computer-assisted education in methadone users has not been evaluated systematically. Objective This study was aimed at assessing feasibility and patient acceptance of an interactive educational module of a multi-component smoking cessation counseling computer program for former illicit drug users treated in an outpatient methadone clinic. Methods The computer-mediated education for hazards of smoking utilized in this study was driven by major constructs of adult learning theories. The program interface was tailored to individuals with minimal computer experience and was implemented on a touch screen tablet PC. The number of consecutive methadone-treated current smokers enrolled in the study was 35. After providing socio-demographic and smoking profiles, the patients were asked to use the educational program for 40 minutes. The impact of the computer-mediated education was assessed by administering a pre- and post-intervention Hazards of Smoking Knowledge Survey (HSKS). An attitudinal survey and semi-structured qualitative interview were used after the educational session to assess the opinions of participants about their educational experience. Results The computer-mediated education resulted in significant increase of HSKS scores from 60.5 ± 16.3 to 70.4 ± 11.7 with t value 3.69 and P < .001. The majority of the patients (78.8%) felt the tablet PC was easy to use, and most of the patients (91.4%) rated the educational experience as good or excellent. After controlling for patient baseline characteristics, the effect of computer-mediated education remained statistically significant. Conclusions Computer-assisted education using tablet PCs was feasible, well-accepted, and an effective means of providing hazards of smoking education among methadone users.

In emergency department (ED) settings, rapid and precise diagnostic evaluations are critical to ensure better patient outcomes and efficient healthcare delivery. This study assesses the accuracy of differential diagnosis lists generated by the third-generation ChatGPT (ChatGPT-3.5) and the fourth-generation ChatGPT (ChatGPT-4) based on electronic health record notes recorded within the first 24 h of ED admission. These models process unstructured text to formulate a ranked list of potential diagnoses. The accuracy of these models was benchmarked against actual discharge diagnoses to evaluate their utility as diagnostic aids. Results indicated that both GPT-3.5 and GPT-4 reasonably accurately predicted diagnoses at the body system level, with GPT-4 slightly outperforming its predecessor. However, their performance at the more granular category level was inconsistent, often showing decreased precision. Notably, GPT-4 demonstrated improved accuracy in several critical categories that underscores its advanced capabilities in managing complex clinical scenarios. [ABSTRACT FROM AUTHOR]