No studies have discussed machine learning algorithms to predict recurrence within 10 years after breast cancer surgery. This study purposed to compare the accuracy of forecasting models to predict recurrence within 10 years after breast cancer surgery and to identify significant predictors of recurrence. Registry data for breast cancer surgery patients were allocated to a training dataset (n = 798) for model development, a testing dataset (n = 171) for internal validation, and a validating dataset (n = 171) for external validation. Global sensitivity analysis was then performed to evaluate the significance of the selected predictors. Demographic characteristics, clinical characteristics, quality of care, and preoperative quality of life were significantly associated with recurrence within 10 years after breast cancer surgery (p < 0.05). Artificial neural networks had the highest prediction performance indices. Additionally, the surgeon volume was the best predictor of recurrence within 10 years after breast cancer surgery, followed by hospital volume and tumor stage. Accurate recurrence within 10 years prediction by machine learning algorithms may improve precision in managing patients after breast cancer surgery and improve understanding of risk factors for recurrence within 10 years after breast cancer surgery.

The impact of pay-for-performance (P4P) programs on long-term mortality for chronic illnesses, especially diabetes mellitus, has been rarely reported. Several studies described the favorable impact of P4P for diabetes mellitus on medical utilizations or intermediate outcomes. Therefore, this study aimed to investigate the impact of a P4P program on mortality in patients with type 2 diabetes. The P4P group in this population-based cohort study was 2090 individuals with a primary diagnosis of type 2 diabetes who had been newly enrolled in the P4P program of Taiwan between January 1, 2004 and December 31, 2004. Matched by 1:1 ratio, patients in the non-P4P group were selected by propensity score matching (PSM) for sex, age, the first year of diagnosis as diabetes, and 32 other potential confounding factors. Mean (SD) age was 60.91 (12.04) years when diabetes was first diagnosed and mean (SD) duration of diabetes was 4.3 (1.9) years at baseline. The time-dependent Cox regression model was used to explore the impact of P4P on all-cause mortality. During a mean of 5.13 years (SD = 1.07 years) of follow-up, 206 and 263 subjects died in the P4P group and the non-P4P group, respectively. After adjusting for the potential confounding factors at baseline, survival was significantly longer in the P4P group than in the non-P4P group (hazard ratio, 0.76 [95% confidence interval, 0.64–0.92], P = 0.004, by log-rank test). This decrease in mortality is equivalent to one less death for every 37 patients who were treated in the P4P program for 5.13 years. In this study, the P4P program significantly increased the medical utilization of physician visits and diabetes-related examinations, improved the adherence of oral hypoglycemic drugs during the first 3 years and that of insulin during the second 3 years, and was negatively associated with risk of cancer and chronic kidney disease. In annual health expense, there was no significant difference between P4P and non-P4P groups, P = 0.430. As compared with control, pay-for-performance program significantly improved survival in patients with diabetes without increasing the medical cost. The P4P group had significantly lower risk of cancer and chronic kidney disease.

The purpose of this study was to explore the increasing prevalence of factors affecting hospital charges for primary total hip replacement/total knee replacement (THR/TKR). This study analysed 37,918 THR and 76,727 TKR procedures performed in Taiwan from 1996 to 2004. Odds ratio (OR) and effect size (ES) were calculated to assess the relative change rate. Multiple regression models were employed to predict hospital charges. The following factors were associated with increased hospital charges: age younger than 65 years old; increased disease severity (Charlson comorbidity index [CCI] = 1 or ≥2); absence of primary diagnoses of osteoarthritis (OA), rheumatoid arthritis (RA), avascular necrosis (AVN); treatment at a hospital or by a surgeon performing a high volume of operations; and longer average length of stay (ALOS). The Bureau of National Health Insurance (BNHI) should ensure that surgeons take precautionary measures to minimise complications and maximise quality of life after surgery. Use of joint prostheses from different manufacturers can reduce costs without compromising patient satisfaction.

For patients with locally advanced rectal cancer (LARC), achieving a pathological complete response (pCR) after neoadjuvant chemoradiotherapy (CRT) provides them with the optimal prognosis. However, no reliable prediction model is presently available. We evaluated the performance of an artificial neural network (ANN) model in pCR prediction in patients with LARC. Predictive accuracy was compared between the ANN, k-nearest neighbor (KNN), support vector machine (SVM), naïve Bayes classifier (NBC), and multiple logistic regression (MLR) models. Data from two hundred seventy patients with LARC were used to compare the efficacy of the forecasting models. We trained the model with an estimation data set and evaluated model performance with a validation data set. The ANN model significantly outperformed the KNN, SVM, NBC, and MLR models in pCR prediction. Our results revealed that the post-CRT carcinoembryonic antigen is the most influential pCR predictor, followed by intervals between CRT and surgery, chemotherapy regimens, clinical nodal stage, and clinical tumor stage. The ANN model was a more accurate pCR predictor than other conventional prediction models. The predictors of pCR can be used to identify which patients with LARC can benefit from watch-and-wait approaches.