Applying machine learning methods to predict the hospital re-admission within 30 days of total hip arthroplasty and hemiarthroplasty.

BACKGROUND: Total hip arthroplasty (THA) and hemiarthroplasty are common treatments for severe hip joint disease. To predict the probability of re-admission after discharge when patients are hospitalized will support providing appropriate health education and guidance. METHODS: The research aims to use logistic regression (LR), decision trees (DT), random forests (RF), and artificial neural networks (ANN) to establish predictive models and compare their performances on re-admissions within 30 days after THA or hemiarthroplasty. The data of this study includes patient demographics, physiological measurements, disease history, and clinical laboratory test results. RESULTS: There were 508 and 309 patients in the THA and hemiarthroplasty studies respectively from September 2016 to December 2018. The accuracies of the four models LR, DT, RF, and ANN in the THA experiment are 94.3%, 93.2%, 97.3%, and 93.9%, respectively. In the hemiarthroplasty experiment, the accuracies of the four models are 92.4%, 86.1%, 94.2%, and 94.8%, respectively. Among these, we found that the RF model has the best sensitivity and ANN model has the best area under the receiver operating characteristic (AUROC) score in both experiments. CONCLUSIONS: The THA experiment confirmed that the performance of the RF model is better than the other models. The key factors affecting the prognosis after THA surgery are creatinine, sodium, anesthesia duration, and dialysis. In the hemiarthroplasty experiment, the ANN model showed more accurate results. Poor kidney function increases the risk of hospital re-admission. This research highlights that RF and ANN model perform well on the hip replacement surgery outcome prediction.

Evaluation of salivary function by sialoscintigraphy in locally advanced nasopharyngeal cancer patients after intensity modulated radiotherapy.

PURPOSE: This study aimed to evaluate the salivary gland function changes by sialoscintigraphy in locally advanced nasopharyngeal cancer (NPC) after intensity modulated radiotherapy (IMRT). MATERIALS AND METHODS: Salivary function was assessed by sialoscintigraphy. Quantitative sialoscintigraphy was performed in 24 NPC patients prior to and after IMRT. Results were categorized in four groups according to the duration of treatment. The sialoscintigraphy parameters were examined. RESULTS: Sialoscintigraphy showed a significant difference in the secretion of each interval groups. The parameters of scintigraphy, except maximum accumulation (MA) of submandibular glands, decreased first after radiotherapy, and then recovered. However, the MA of submandibular glands was continuously downhill after radiation. CONCLUSIONS: The sialoscintigraphy parameters of each gland changed with the different radiation dose and follow-up intervals. The salivary function was influenced after radiotherapy in locally advanced NPC, especially, in the submandibular gland. Strategies to improve the salivary function should be assessed.

Factors affecting contraceptive use in women seeking pregnancy tests: Missouri, 1997.

CONTEXT: If the national health objective of reducing unintended pregnancy is to be met, a better understanding is needed of barriers to women's acquisition and use of contraceptives. METHODS: A sample of 311 Missouri women who were seeking pregnancy tests in public health department clinics in 1997 and who said their potential pregnancy was unintended were asked about potential barriers to family planning. Factors affecting contraceptive use among these women were examined by frequency of use, insurance status, education and race. RESULTS: In general, the women mostly disagreed that particular factors were potential barriers to contraceptive use. For only one item--worry over the potential side effects of the hormonal injectable contraceptive--did a majority agree or strongly agree that it was a barrier to method use in the previous six months. Women who used a contraceptive infrequently were more likely than frequent users to identify 33 factors in nine areas as being potential barriers to contraceptive use. These ranged from factors involving access to services and condom-specific issues to cost-related concerns, social norms, pregnancy denial, embarrassment over discussing or obtaining birth control, worry about side effects and experience with forced sex, among others. Perceived barriers differed somewhat by insurance status in the areas of access, embarrassment, side effects and forced sex. For example, women with no insurance coverage reported a higher level of agreement that transportation problems had hindered their access to a clinic than did women with private insurance. Level of education affected agreement only in the area of side effects, with more-educated women expressing greater concern about side effects than less-educated women. The respondent's race affected agreement in six areas: access, social norms, pregnancy denial, embarrassment, forced sex and other miscellaneous concerns, such as condom use and relationship issues. CONCLUSION: Better education and improved access to and delivery of services might address several factors affecting contraceptive use that are associated with unintended pregnancy. Some barriers, however, such as those related to self-efficacy, self-esteem and fatalistic attitudes about pregnancy, would be much harder for family planning providers to resolve.