Insulin resistance (IR) is associated with diabetes mellitus, cardiovascular disease (CV), and mortality. Few studies have used machine learning to predict IR in the non-diabetic population. In this prospective cohort study, we trained a predictive model for IR in the non-diabetic populations using the US National Health and Nutrition Examination Survey (NHANES, from JAN 01, 1999 to DEC 31, 2012) database and the Taiwan MAJOR (from JAN 01, 2008 to DEC 31, 2017) database. We analysed participants in the NHANES and MAJOR and participants were excluded if they were aged 0.8 (highest being XGboost, 0.87). In the test group, all AUC were also >0.80 (highest being XGboost, 0.88). Among all 9 features (age, gender, race, body mass index, fasting plasma glucose (FPG), glycohemoglobin, triglyceride, total cholesterol and high-density cholesterol), BMI had the highest value of feature importance on IR (0.43 for XGboost and 0.47 for RF algorithms). All participants from the TWB database were separated into the IR group and the non-IR group according to the XGboost algorithm. The Kaplan–Meier survival curve showed a significant difference between the IR and non-IR groups (p < 0.0001 for CV mortality, and p = 0.0006 for all-cause mortality). Therefore, the XGboost model has clear clinical implications for predicting IR, aside from CV and all-cause mortality. To predict IR in non-diabetic patients with high accuracy, only 9 easily obtained features are needed for prediction accuracy using our machine learning model. Similarly, the model predicts IR patients with significantly higher CV and all-cause mortality. The model can be applied to both Asian and Caucasian populations in clinical practice. 10.13039/501100010101 Taichung Veterans General Hospital , Taiwan and 10.13039/501100001691 Japan Society for the Promotion of Science KAKENHI Grant Number JP21KK0293.

Background: The role of circulating tumor cells (CTCs) for predicting the recurrence of cancer in lung cancer patients after surgery remains unclear. Methods: A negatively selected protocol of CTC identification was applied. For all the enrolled patients, CTC testing was performed before and after surgery on the operation day (day 0), postoperative day 1, and day 3. The daily decline and trend of CTCs were analyzed to correlate with cancer relapse. The mixed model repeated measures (MMRM) adjusted by cancer characteristics was applied for statistical significance. Results: Fifty patients with lung mass undergoing surgery were enrolled. Among 41 primary lung cancers, 26 (63.4%) were pathological stage Tis and I. A total of 200 CTC tests were performed. MMRM analysis indicated that surgery could contribute to a CTC decline after surgery in all patients with statistical significance (p = 0.0005). The daily decrease of CTCs was statistically different between patients with and without recurrence (p = 0.0068). An early rebound of CTC counts on postoperative days 1 and 3 was associated with recurrence months later. Conclusion: CTC testing can potentially serve as a tool for minimal residual disease detection in early-staged lung cancer after curative surgery.

The influenza problem has always been an important global issue. It not only affects people’s health problems but is also an essential topic of governments and health care facilities. Early prediction and response is the most effective control method for flu epidemics. It can effectively predict the influenza-like illness morbidity, and provide reliable information to the relevant facilities. For social facilities, it is possible to strengthen epidemic prevention and care for highly sick groups. It can also be used as a reminder for the public. This study collects information on the influenza-like illness emergency department visits to the Taiwan Centers for Disease Control, and the PM_2.5 open-source data from the Taiwan Environmental Protection Administration's air quality monitoring network. By using deep learning techniques, the relevance of short-term estimates and the outbreak calculation method can be determined. The techniques are published by the WHO to determine whether the influenza-like illness situation is still in a stage of reasonable control. Finally, historical data and future forecasted data are integrated on the web page for visual presentation, to show the actual regional air quality situation and influenza-like illness data and to predict whether there is an outbreak of influenza in the region.

We investigated the associations of insulin resistance and β-cell secretion with bone mineral density (BMD) and osteoporosis using data from the National Health and Nutrition Examination Survey. Data on BMD assessed using dual-energy x-ray absorptiometry from 5292 participants were analyzed. Insulin resistance and β-cell secretion were assessed using the Homeostatic Model Assessment for Insulin Resistance (HOMA-IR) and β-cell function (HOMA-β), respectively. We divided the study population into four groups according to HOMA-IR (<2 vs. ≥ 2) and HOMA-β (<100 vs. ≥ 100). BMD and T score at the lumbar spine, hip joint, and femur were used for analyses. Osteoporosis was defined as a T score ≤ -2.5. Logistic regression analyses were conducted to examine the associations of HOMA-IR and HOMA-β with osteoporosis, and the joint effects of HOMA-IR and HOMA-β on osteoporosis. We found a positive association between HOMA-IR and osteoporosis in participants with a HOMA-β ≥ 100 (OR 8.773, 95% CI 2.160-35.637, p=0.002 at the femoral neck). A negative association between HOMA-β and osteoporosis was noted in those with a HOMA-IR <2 (OR 0.183, 95% CI 0.038-0.882, p=0.034 at the femoral neck). Compared with participants who had HOMA-IR <2 and HOMA-β <100, those with HOMA-IR <2 and HOMA-β ≥ 100 had a lower risk of osteoporosis (OR 0.126, 95% CI 0.020-0.805, p=0.032 at the femoral neck). In conclusion, the association between HOMA-β and BMD/osteoporosis changed as HOMA-IR increased. HOMA-β was negatively associated with osteoporosis when HOMA-IR <2. The association was not significant when HOMA-IR ≥ 2.

Background: Chronic kidney disease (CKD) is a complex syndrome without a definitive treatment. For these patients, insulin resistance (IR) is associated with worse renal and patient outcomes. Until now, no predictive model using machine learning (ML) has been reported on IR in CKD patients. Methods: The CKD population studied was based on results from the National Health and Nutrition Examination Survey (NHANES) of the USA from 1999 to 2012. The homeostasis model assessment of IR (HOMA-IR) was used to assess insulin resistance. We began the model building process via the ML algorithm (random forest (RF), eXtreme Gradient Boosting (XGboost), logistic regression algorithms, and deep neural learning (DNN)). We compared different receiver operating characteristic (ROC) curves from different algorithms. Finally, we used SHAP values (SHapley Additive exPlanations) to explain how the different ML models worked. Results: In this study population, 71,916 participants were enrolled. Finally, we analyzed 1,229 of these participants. Their data were segregated into the IR group (HOMA IR > 3, n = 572) or non-IR group (HOMR IR ≤ 3, n = 657). In the validation group, RF had a higher accuracy (0.77), specificity (0.81), PPV (0.77), and NPV (0.77). In the test group, XGboost had a higher AUC of ROC (0.78). In addition, XGBoost also had a higher accuracy (0.7) and NPV (0.71). RF had a higher accuracy (0.7), specificity (0.78), and PPV (0.7). In the RF algorithm, the body mass index had a much larger impact on IR (0.1654), followed by triglyceride (0.0117), the daily calorie intake (0.0602), blood HDL value (0.0587), and age (0.0446). As for the SHAP value, in the RF algorithm, almost all features were well separated to show a positive or negative association with IR. Conclusion: This was the first study using ML to predict IR in patients with CKD. Our results showed that the RF algorithm had the best AUC of ROC and the best SHAP value differentiation. This was also the first study that included both macronutrients and micronutrients. We concluded that ML algorithms, particularly RF, can help determine risk factors and predict IR in patients with CKD.

Consuming a Mediterranean-style diet (MED) is helpful for primary prevention of atherosclerotic cardiovascular disease (ASCVD). However, few studies have compared mortality in ASCVD subjects with different degrees of adherence to the MED diet or have evaluated the contributions of individual diet components. We analyzed National Health and Nutrition Examination Survey (NHANES) participants with a history of coronary heart disease (CHD) or stroke (N = 2052) in a period from 1999 to 2010. Their individual vital status was linked to the National Death Index till the end of 2011. The level of adherence to the MED diet was quantified using a 9-point evaluation score (aMED score). Cox regression models were used to compare the different levels of adherence to the MED diet, and contributions of individual components of the MED diet on cardiovascular, cancer, and all-cause mortality. Among the 2052 subjects with CHD or stroke, 29.0% (596 of 2052) died after a median follow-up of 5.6 years. In Cox regression analysis, higher absolute aMED score (HR 0.798, p = 0.0079) or above median aMED score (score 4–9) (HR 0.646, p = 0.0013) was negatively associated with all-cause mortality. Among various components of the MED diet, intake of more whole grains or nuts was significantly associated with a lower all-cause mortality. In contrast, a higher aMED score was not associated with less cardiovascular mortality. In a secondary analysis that excluded deaths within 2 years of the NHANES study entry, the above median aMED score (score 4–9) was negatively associated with both all-cause and cardiovascular mortality. In conclusion, subjects with a history of CHD or stroke adhering better to the MED diet in the NHANES study had a lower all-cause mortality during follow-ups. Consuming more whole grains or nuts had a lower all-cause mortality. The protective effect of adherence to the MED diet on decreasing cardiovascular mortality was seen only after excluding those who died within first two years of the NHANES study entry.