Development and Validation of a Prognostic Classification Model Predicting Postoperative Adverse Outcomes in Older Surgical Patients Using a Machine Learning Algorithm: Retrospective Observational Network Study.

BACKGROUND: Older adults are at an increased risk of postoperative morbidity. Numerous risk stratification tools exist, but effort and manpower are required. OBJECTIVE: This study aimed to develop a predictive model of postoperative adverse outcomes in older patients following general surgery with an open-source, patient-level prediction from the Observational Health Data Sciences and Informatics for internal and external validation. METHODS: We used the Observational Medical Outcomes Partnership common data model and machine learning algorithms. The primary outcome was a composite of 90-day postoperative all-cause mortality and emergency department visits. Secondary outcomes were postoperative delirium, prolonged postoperative stay (≥75th percentile), and prolonged hospital stay (≥21 days). An 80% versus 20% split of the data from the Seoul National University Bundang Hospital (SNUBH) and Seoul National University Hospital (SNUH) common data model was used for model training and testing versus external validation. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) with a 95% CI. RESULTS: Data from 27,197 (SNUBH) and 32,857 (SNUH) patients were analyzed. Compared to the random forest, Adaboost, and decision tree models, the least absolute shrinkage and selection operator logistic regression model showed good internal discriminative accuracy (internal AUC 0.723, 95% CI 0.701-0.744) and transportability (external AUC 0.703, 95% CI 0.692-0.714) for the primary outcome. The model also possessed good internal and external AUCs for postoperative delirium (internal AUC 0.754, 95% CI 0.713-0.794; external AUC 0.750, 95% CI 0.727-0.772), prolonged postoperative stay (internal AUC 0.813, 95% CI 0.800-0.825; external AUC 0.747, 95% CI 0.741-0.753), and prolonged hospital stay (internal AUC 0.770, 95% CI 0.749-0.792; external AUC 0.707, 95% CI 0.696-0.718). Compared with age or the Charlson comorbidity index, the model showed better prediction performance. CONCLUSIONS: The derived model shall assist clinicians and patients in understanding the individualized risks and benefits of surgery.

Development and validation of a prediction model for evaluating extubation readiness in preterm infants.

Successful early extubation has advantages not only in terms of short-term respiratory morbidities and survival but also in terms of long-term neurodevelopmental outcomes in preterm infants. However, no consensus exists regarding the optimal protocol or guidelines for extubation readiness in preterm infants. Therefore, the decision to extubate preterm infants was almost entirely at the attending physician's discretion. We identified robust and quantitative predictors of success or failure of the first planned extubation attempt before 36 weeks of post-menstrual age in preterm infants (<32 weeks gestational age) and developed a prediction model for evaluating extubation readiness using these predictors. Extubation success was defined as the absence of reintubation within 72 h after extubation. This observational cohort study used data from preterm infants admitted to the neonatal intensive care unit of Seoul National University Bundang Hospital in South Korea between July 2003 and June 2019 to identify predictors and develop and test a predictive model for extubation readiness. Data from preterm infants included in the Medical Informative Medicine for Intensive Care (MIMIC-III) database between 2001 and 2008 were used for external validation. From a machine learning model using predictors such as demographics, periodic vital signs, ventilator settings, and respiratory indices, the area under the receiver operating characteristic curve and average precision of our model were 0.805 (95% confidence interval [CI], 0.802-0.809) and 0.917, respectively in the internal validation and 0.715 (95% CI, 0.713-0.717) and 0.838, respectively in the external validation. Our prediction model (NExt-Predictor) demonstrated high performance in assessing extubation readiness in both internal and external validations.

Coronary Artery Computed Tomography Angiography for Preventing Cardio-Cerebrovascular Disease: Observational Cohort Study Using the Observational Health Data Sciences and Informatics' Common Data Model.

BACKGROUND: Cardio-cerebrovascular diseases (CVDs) result in 17.5 million deaths annually worldwide, accounting for 46.2% of noncommunicable causes of death, and are the leading cause of death, followed by cancer, respiratory disease, and diabetes mellitus. Coronary artery computed tomography angiography (CCTA), which detects calcification in the coronary arteries, can be used to detect asymptomatic but serious vascular disease. It allows for noninvasive and quick testing despite involving radiation exposure. OBJECTIVE: The objective of our study was to investigate the effectiveness of CCTA screening on CVD outcomes by using the Observational Health Data Sciences and Informatics' Observational Medical Outcomes Partnership Common Data Model (OMOP-CDM) data and the population-level estimation method. METHODS: Using electronic health record-based OMOP-CDM data, including health questionnaire responses, adults (aged 30-74 years) without a history of CVD were selected, and 5-year CVD outcomes were compared between patients undergoing CCTA (target group) and a comparison group via 1:1 propensity score matching. Participants were stratified into low-risk and high-risk groups based on the American College of Cardiology/American Heart Association atherosclerotic cardiovascular disease (ASCVD) risk score and Framingham risk score (FRS) for subgroup analyses. RESULTS: The 2-year and 5-year risk scores were compared as secondary outcomes between the two groups. In total, 8787 participants were included in both the target group and comparison group. No significant differences (calibration P=.37) were found between the hazard ratios of the groups at 5 years. The subgroup analysis also revealed no significant differences between the ASCVD risk scores and FRSs of the groups at 5 years (ASCVD risk score: P=.97; FRS: P=.85). However, the CCTA group showed a significantly lower increase in risk scores at 2 years (ASCVD risk score: P=.03; FRS: P=.02). CONCLUSIONS: Although we could not confirm a significant difference in the preventive effects of CCTA screening for CVDs over a long period of 5 years, it may have a beneficial effect on risk score management over 2 years.

Transforming electronic health record polysomnographic data into the Observational Medical Outcome Partnership's Common Data Model: a pilot feasibility study.

Well-defined large-volume polysomnographic (PSG) data can identify subgroups and predict outcomes of obstructive sleep apnea (OSA). However, current PSG data are scattered across numerous sleep laboratories and have different formats in the electronic health record (EHR). Hence, this study aimed to convert EHR PSG into a standardized data format-the Observational Medical Outcome Partnership (OMOP) common data model (CDM). We extracted the PSG data of a university hospital for the period from 2004 to 2019. We designed and implemented an extract-transform-load (ETL) process to transform PSG data into the OMOP CDM format and verified the data quality through expert evaluation. We converted the data of 11,797 sleep studies into CDM and added 632,841 measurements and 9,535 observations to the existing CDM database. Among 86 PSG parameters, 20 were mapped to CDM standard vocabulary and 66 could not be mapped; thus, new custom standard concepts were created. We validated the conversion and usefulness of PSG data through patient-level prediction analyses for the CDM data. We believe that this study represents the first CDM conversion of PSG. In the future, CDM transformation will enable network research in sleep medicine and will contribute to presenting more relevant clinical evidence.

A Predictive Model Based on Machine Learning for the Early Detection of Late-Onset Neonatal Sepsis: Development and Observational Study.

BACKGROUND: Neonatal sepsis is associated with most cases of mortalities and morbidities in the neonatal intensive care unit (NICU). Many studies have developed prediction models for the early diagnosis of bloodstream infections in newborns, but there are limitations to data collection and management because these models are based on high-resolution waveform data. OBJECTIVE: The aim of this study was to examine the feasibility of a prediction model by using noninvasive vital sign data and machine learning technology. METHODS: We used electronic medical record data in intensive care units published in the Medical Information Mart for Intensive Care III clinical database. The late-onset neonatal sepsis (LONS) prediction algorithm using our proposed forward feature selection technique was based on NICU inpatient data and was designed to detect clinical sepsis 48 hours before occurrence. The performance of this prediction model was evaluated using various feature selection algorithms and machine learning models. RESULTS: The performance of the LONS prediction model was found to be comparable to that of the prediction models that use invasive data such as high-resolution vital sign data, blood gas estimations, blood cell counts, and pH levels. The area under the receiver operating characteristic curve of the 48-hour prediction model was 0.861 and that of the onset detection model was 0.868. The main features that could be vital candidate markers for clinical neonatal sepsis were blood pressure, oxygen saturation, and body temperature. Feature generation using kurtosis and skewness of the features showed the highest performance. CONCLUSIONS: The findings of our study confirmed that the LONS prediction model based on machine learning can be developed using vital sign data that are regularly measured in clinical settings. Future studies should conduct external validation by using different types of data sets and actual clinical verification of the developed model.

Development of Comprehensive Personal Health Records Integrating Patient-Generated Health Data Directly From Samsung S-Health and Apple Health Apps: Retrospective Cross-Sectional Observational Study.

BACKGROUND: Patient-generated health data (PGHD), especially lifelog data, are important for managing chronic diseases. Additionally, personal health records (PHRs) have been considered an effective tool to engage patients more actively in the management of their chronic diseases. However, no PHRs currently integrate PGHD directly from Samsung S-Health and Apple Health apps. OBJECTIVE: The purposes of this study were (1) to demonstrate the development of an electronic medical record (EMR)-tethered PHR system (Health4U) that integrates lifelog data from Samsung S-Health and Apple Health apps and (2) to explore the factors associated with the use rate of the functions. METHODS: To upgrade conventional EMR-tethered PHRs, a task-force team (TFT) defined the functions necessary for users. After implementing a new system, we enrolled adults aged 19 years and older with prior experience of accessing Health4U in the 7-month period after November 2017, when the service was upgraded. RESULTS: Of the 17,624 users, 215 (1.22%) integrated daily steps data, 175 (0.99%) integrated weight data, 51 (0.29%) integrated blood sugar data, and 90 (0.51%) integrated blood pressure data. Overall, 61.95% (10,919/17,624) had one or more chronic diseases. For integration of daily steps data, 48.3% (104/215) of patients used the Apple Health app, 43.3% (93/215) used the S-Health app, and 8.4% (18/215) entered data manually. To retrieve medical documentation, 324 (1.84%) users downloaded PDF files and 31 (0.18%) users integrated their medical records into the Samsung S-Health app via the Consolidated-Clinical Document Architecture download function. We found a consistent increase in the odds ratios for PDF downloads among patients with a higher number of chronic diseases. The age groups of ≥60 years and ≥80 years tended to use the download function less frequently than the others. CONCLUSIONS: This is the first study to examine the factors related to integration of lifelog data from Samsung S-Health and Apple Health apps into EMR-tethered PHRs and factors related to the retrieval of medical documents from PHRs. Our findings on the lifelog data integration can be used to design PHRs as a platform to integrate lifelog data in the future.