ABSTRACT
OBJECTIVE: To develop a risk score for the real-time prediction of readmissions for patients using patient specific information captured in electronic medical records (EMR) in Singapore to enable the prospective identification of high-risk patients for enrolment in timely interventions. METHODS: Machine-learning models were built to estimate the probability of a patient being readmitted within 30 days of discharge. EMR of 25,472 patients discharged from the medicine department at Ng Teng Fong General Hospital between January 2016 and December 2016 were extracted retrospectively for training and internal validation of the models. We developed and implemented a real-time 30-day readmission risk score generation in the EMR system, which enabled the flagging of high-risk patients to care providers in the hospital. Based on the daily high-risk patient list, the various interfaces and flow sheets in the EMR were configured according to the information needs of the various stakeholders such as the inpatient medical, nursing, case management, emergency department, and postdischarge care teams. RESULTS: Overall, the machine-learning models achieved good performance with area under the receiver operating characteristic ranging from 0.77 to 0.81. The models were used to proactively identify and attend to patients who are at risk of readmission before an actual readmission occurs. This approach successfully reduced the 30-day readmission rate for patients admitted to the medicine department from 11.7% in 2017 to 10.1% in 2019 (p < 0.01) after risk adjustment. CONCLUSION: Machine-learning models can be deployed in the EMR system to provide real-time forecasts for a more comprehensive outlook in the aspects of decision-making and care provision.
Subject(s)
Aftercare , Patient Readmission , Humans , Patient Discharge , Prospective Studies , Retrospective Studies , Risk Factors , SingaporeABSTRACT
OBJECTIVE: The chronic obstructive pulmonary disease (COPD) integrated care pathway (ICP) programme was designed and implemented to ensure that the care for patients with COPD is comprehensive and integrated across different care settings from primary care to acute hospital and home. We evaluated the effectiveness of the ICP programme for patients with COPD. DESIGN, SETTING AND PARTICIPANTS: A retrospective propensity score matched cohort study was conducted comparing differences between programme enrolees and propensity-matched non-enrolees in a Regional Health System in Singapore. Data on patients diagnosed with COPD who enrolled in the programme (n=95) and patients who did not enrol (n=6330) were extracted from the COPD registry and hospital administrative databases. Enrolees and non-enrolees were propensity score matched. OUTCOME MEASURES: The risk of COPD hospitalisations and COPD hospital bed days savings were compared between the groups using a difference-in-difference strategy and generalised estimating equation approach. Adherence with recommended care elements for the COPD-ICP group was measured quarterly at baseline and during a 2-year follow-up period. RESULTS: Compared with non-enrolees, COPD hospitalisation risk for ICP programme enrolees was significantly lower in year 2 (incidence rate ratio (IRR): 0.73; 95% CI 0.54 to 1.00). Similarly, COPD hospital bed days was significantly lower for enrolees in year 2 (IRR: 0.78; 95% CI 0.64 to 0.95). ICP programme patients had sustained improvements in compliance with all recommended care elements for patients with COPD. The overall all-or-none care bundle compliance rate had improved from 28% to 54%. CONCLUSION: The study concluded that the COPD-ICP programme was associated with reductions in COPD hospitalisation risk and COPD health utilisation in a 2-year follow-up period.
Subject(s)
Delivery of Health Care, Integrated , Government Programs/standards , Hospitalization/statistics & numerical data , Patient Compliance/statistics & numerical data , Pulmonary Disease, Chronic Obstructive/rehabilitation , Aged , Aged, 80 and over , Female , Humans , Logistic Models , Male , Middle Aged , Multivariate Analysis , Propensity Score , Pulmonary Disease, Chronic Obstructive/physiopathology , Retrospective Studies , Risk Assessment , Severity of Illness Index , SingaporeABSTRACT
The random work-function (WK) induced threshold voltage fluctuation (sigmaVth) in 16 nm Titanium Nitride (TiN) metal-gate fin-type field effect transistors (FinFETs) is explored and modeled by using an experimentally validated Monte Carlo simulation approach. The influences of metal-grain size and device geometry aspect ratio on the random WK-induced sigmaVth are considered in the proposed equation analytically. The formula accounts for the inside of fluctuation and could be used for the assessment of effectiveness of suppression techniques.
