ABSTRACT
OBJECTIVES: Surgery for colonic perforation has high morbidity and mortality rates. Predicting complications preoperatively would help improve short-term outcomes; however, no predictive risk stratification model exists to date. Therefore, the current study aimed to determine risk factors for complications after colonic perforation surgery and use machine learning to construct a predictive model. METHODS: This retrospective study included 51 patients who underwent emergency surgery for colorectal perforation. We investigated the connection between overall complications and several preoperative indicators, such as lactate and the Glasgow Prognostic Score. Moreover, we used the classification and regression tree (CART), a machine-learning method, to establish an optimal prediction model for complications. RESULTS: Overall complications occurred in 32 patients (62.7%). Multivariate logistic regression analysis identified high lactate levels [odds ratio (OR), 1.86; 95% confidence interval (CI), 1.07-3.22; p = 0.027] and hypoalbuminemia (OR, 2.56; 95% CI, 1.06-6.25; p = 0.036) as predictors of overall complications. According to the CART analysis, the albumin level was the most important parameter, followed by the lactate level. This prediction model had an area under the curve (AUC) of 0.830. CONCLUSIONS: Our results determined that both preoperative albumin and lactate levels were valuable predictors of postoperative complications among patients who underwent colonic perforation surgery. The CART analysis determined optimal cutoff levels with high AUC values to predict complications, making both indicators clinically easier to use for decision making.
ABSTRACT
BACKGROUND: Leukemia is a deadly hematological malignancy that usually affects all age groups and imposes significant burden on public funds and society. The objective of this study was to analyze the cost of illness (COI) of leukemia, and to mark out the underlying driving factors, in Japan. METHODS: COI method was applied to the data from government statistics. We first summed up the direct and indirect costs from 1996 to 2014; then future COI for the year 2017-2029 was projected. RESULTS: Calculated COI showed an upward trend with a 13% increase from 1996 to 2014 (270-305 billion yen). Increased COI was attributed to an increase in direct costs. Although mortality cost accounted for the largest proportion of COI, but followed a downward trend. Decreased mortality costs reflected the effects of aging. Mortality cost per person also decreased, however, the percentage of mortality cost for individuals ≥65 years of age increased consistently from 1996 to 2014. If a similar trend in health-related indicators continue, COI would remain stable from 2017 to 2029 regardless of models. CONCLUSION: COI of leukemia increased from 1996 to 2014, but was projected to decrease in foreseeable future. With advancement of new therapies, leukemia has become potentially curable and require long-term care; so direct cost and morbidity cost will remain unchanged. This reveal the further continuing burden on public funds. Thus, the information obtained from this study can be regarded as beneficial to future policy making with respect to government policies in Japan.
