Personal health record (PHR)-based care management systems can improve patient engagement and data-driven medical diagnosis in a clinical setting.

Background: Although using the technologies for a variety of chronic health conditions such as personal record (PHR) is reported to be acceptable and useful, there lack evidence on associations between use change outcome patients' response digital app. Objective: This study aimed examine impact PHR wearables improvement sustained app that can associated with patient engagement. Methods: We developed an Android-based mobile phone used wristband-type activity tracker (Samsung Charm) collect...

Abstract Conventional severity-of-illness scoring systems have shown suboptimal performance for predicting in-intensive care unit (ICU) mortality in patients with severe pneumonia. This study aimed to develop and validate machine learning (ML) models prediction retrospective evaluated admitted the ICU pneumonia between January 2016 December 2021. The predictive was analyzed by comparing area under receiver operating characteristic curve (AU-ROC) of ML that conventional systems. Three were...

Prevention and management of chronic diseases are the main goals national health maintenance programs. Previously widely used screening tools, such as Health Risk Appraisal, restricted in their achievement this goal due to limitations, static characteristics, accessibility, generalizability. Hypertension is one most important requiring via nationwide program, care providers should inform patients about risks a complication caused by hypertension.Our was develop compare machine learning...

Background Common data models (CDMs) help standardize electronic health record and facilitate outcome analysis for observational longitudinal research. An of pathology reports is required to establish fundamental information infrastructure data-driven colon cancer The Observational Medical Outcomes Partnership (OMOP) CDM used in distributed research networks clinical data; however, it requires conversion free text–based into the CDM’s format. There are few use cases representing CDM....

Abstract Objective Accurate electronic phenotyping is essential to support collaborative observational research. Supervised machine learning methods can be used train phenotype classifiers in a high-throughput manner using imperfectly labeled data. We developed 10 this approach and evaluated performance across multiple sites within the Observational Health Data Sciences Informatics (OHDSI) network. Materials Methods constructed Automated PHenotype Routine for Definition, Identification,...

Predicting highrisk vascular diseases is a significant issue in the medical domain. Most predicting methods predict prognosis of patients from pathological and radiological measurements, which are expensive require much time to be analyzed. Here we propose deep attention models that onset high risky disease symbolic histories sequence hypertension such as ICD-10 pharmacy codes only, Medical History-based Prediction using Attention Network (MeHPAN). We demonstrate two types based on 1)...

Abstract Well-defined large-volume polysomnographic (PSG) data can identify subgroups and predict outcomes of obstructive sleep apnea (OSA). However, current PSG are scattered across numerous laboratories have different formats in the electronic health record (EHR). Hence, this study aimed to convert EHR into a standardized format—the Observational Medical Outcome Partnership (OMOP) common model (CDM). We extracted university hospital for period from 2004 2019. designed implemented an...

To implement standardized machine-processable clinical sequencing reports in an electronic health record (EHR) system, the International Organization for Standardization Technical Specification (ISO/TS) 20428 international standard was proposed a structured template. However, there are no implementation guidelines data items from at site and or references implementing gene results use. This is significant challenge application of these standards individual sites.

To investigate the short-term effects of a lifestyle modification intervention based on mobile application (app) linked to hospital electronic medical record (EMR) system weight reduction and obstructive sleep apnea (OSA).We prospectively enrolled adults (aged >20 years) with witnessed snoring or from clinic. The patients were randomized into app user (n=24) control (n=23) groups. was designed collect daily data by wearing wrist activity tracker reporting dietary intake. A summary displayed...

Abstract Although several studies have attempted to develop a model for predicting 30-day re-hospitalization, few attempts been made sufficient verification and multi-center expansion clinical use. In this study, we developed that predicts unplanned hospital readmission within 30 days of discharge; the is based on common data considers weather air quality factors, can be easily extended multiple hospitals. We compared four tree-based machine learning methods: decision tree, random forest,...

It is a critical issue to predict the prognosis of adult disease patients due possibility spreading high-risk symptoms in medical fields. Most studies for predicting have used complex data from such as biomedical images, biomarkers, and pathological measurements. We demonstrate language model-like method diagnosis histories using deep recurrent neural networks (RNNs), i.e., prediction RNN (PP-RNN). The proposed PP-RNN uses multiple RNNs learning code sequences order occurrences diseases. use...

Unplanned hospital readmission after discharge reflects low satisfaction and reliability in care the possibility of potential medical accidents, is thus indicative quality patient appropriateness plans.The purpose this study was to develop validate prediction models for all-cause unplanned readmissions within 30 days discharge, based on a common data model (CDM), which can be applied multiple institutions efficient management.Retrospective patient-level were developed clinical two tertiary...

Precise prediction of severe diseases resulting in mortality is one the main issues medical fields. Even if pathological and radiological measurements provide competitive precision, they usually require large costs time expense to obtain analyze data for prediction. Recently, end-to-end approaches based on deep neural networks have been proposed, however, still suffer from low classification performance difficulties interpretation. In this study, we propose a novel disease method, EHAN (EHR...

Objectives: In the era of Fourth Industrial Revolution, where an ecosystem is being developed to enhance quality healthcare services by applying information and communication technologies, systematic sustainable data management essential for medical institutions. this study, we assessed status emerging concerns three institutions, while also examining future directions seamless management.Methods: To evaluate status, examined types, capacities, infrastructure, backup methods, related...

In this paper, we like to study the bioelectrical impedance analysis and propose a smart refrigerator for ubiquitous health care. A has an additional function enabling users keep in track of their by newly equipped installation. Also, it is with body fat analyzer that used gym hospitals order receive care environment. This proposed method measured recognized composition using (BIA). expect medical center manages user's condition such as amount fat, muscle, water etc. through internet two...

This retrospective cohort study aimed to compare coronavirus disease 2019 (COVID-19)-related clinical outcomes between patients with and without gout. Electronic health record-based data from two centers (Seoul National University Hospital [SNUH] Boramae Medical Center [BMC]), January 2021 April 2022, were mapped a common model. Patients gout matched using large-scale propensity-score algorithm based on population-level estimation methods. At the SNUH, risk for COVID-19 diagnosis was not...

Abstract Whereas lifestyle-related factors are recognized as snoring risk factors, the role of genetics in remains uncertain. One way to measure impact genetic is through use a polygenic score (PRS). In this study, we aimed investigate whether plays after adjusting for lifestyle factors. Since effect risks may differ across ethnic groups, calculated PRS from UK Biobank and applied it Korean cohort. We sought evaluate reproducibility cohort interaction on population. utilized obtained Genome...