Objective. This study was undertaken to estimate the cumulative incidence rate of rheumatoid arthritis (RA) in the Taiwanese population ages 16-84 years, and life expectancy, loss of life expectancy, and lifetime health care expenditures for incident RA in Taiwan after 2003, when biologics began to be prescribed.Methods. We obtained all claims data for the period 1999 to 2016 from the National Health Insurance program of Taiwan, and validated the data against the Catastrophic Illness Registry to establish the study cohort. We estimated the survival function for RA and extrapolated to lifetime using a rolling-over algorithm. For every RA case, we simulated sex-, age-, and calendar year-matched referents from vital statistics and estimated their life expectancy. The difference between the life expectancy of the referent and the life expectancy of the RA patient was the loss of life expectancy for the RA patient. Average monthly health care expenditures were multiplied by the corresponding survival rates and summed up throughout the lifetime to calculate the lifetime health care expenditures.Results. A total of 29,352 new RA cases were identified during 2003-2016. There was a decreasing trend in cumulative incidence rate in those ages 16-84 for both sexes. Mean life expectancy after diagnosis of RA was 26.3 years, and mean lifetime cost was $72,953. RA patients had a mean loss of life expectancy of 4.97 years. Women with RA survived 1-2 years longer than men with RA of the same age, which resulted in higher lifetime expenditures for the former. Since the life expectancy for women in Taiwan was 6-7 years higher than that for men, the loss of life expectancy for women with RA was higher than that for men with RA. Annual health care expenditures were similar for both sexes. Conclusion.Our findings indicate that since biologics became available, RA patients have lived longer and had higher lifetime expenditures, which should be monitored and evaluated for cost-effectiveness.

two-phase study used data from Reliant Medical Group electronic medical records linked to healthcare claims for 1,647 patients with SICCA syndrome (estimated prevalence=15%). Primary outcomes included presence and early indicators of SjS. Patient, clinical, and treatment characteristics were included as predictors. Random forest (RF) and optimal classification tree (OCT) machinelearning (ML) models were used. In phase 1, the RF model was used to 1) identify patients with high risk of SjS; 2) assist with a targeted chart review; 3) identify SNOMED codes to use as proxy for SjS diagnosis. In phase 2, RF and OCT models were used to identify early indicators of SjS up to 3 years pre-SjS diagnosis. Area under the curve (AUC), sensitivity, and specificity were used to estimate model performance. Results: Phase 1: Research nurses reviewed 200 (stratified) randomly-selected patient charts to confirm SjS. The charts were used to train the RF model, subsequently applied on the 1,447 patients to select additional 200 patient charts for the ML-guided chart review. ML-guided-chart-review results were used to refine model prediction and identify and confirm the use of SNOMED codes as an SjS-diagnosis proxy (AUC=85%, sensitivity=75%, speci-ficity=70%). Phase 2: RF and OCT models were estimated on all 1,647 patients to identify early indicators of SjS. Notable early predictors from the RF model (AUC=86%, sensitivity=90%, specificity=65%) included: patient's age and sex, specialist visits (e.g., rheumatology, ophthalmology), tests (e.g., anti-SSA/SSB, RNP antibody/SCL-70, ANA and RF titer, complement, immunoglobulin blood), and vaccinations (e.g., DPT). OCT results were consistent with RF results though model performance was slightly worse (e.g., AUC=64%). Conclusions: Advanced ML methods can be used to inform clinicians about early indicators to facilitate timely diagnosis of SjS.