Background: Although papillary thyroid cancer (PTC) patients are known to have an excellent prognosis, up to 30% of patients experience disease recurrence after initial treatment. Accurately predicting disease prognosis remains a challenge given that the predictive value of several predictors remains controversial. Thus, we investigated whether machine learning (ML) approaches based on comprehensive predictors can predict the risk of structural recurrence for PTC patients. Methods: A total of 2244 patients treated with thyroid surgery and radioiodine were included. Twenty-nine perioperative variables consisting of four dimensions (demographic characteristics and comorbidities, tumor-related variables, lymph node (LN)-related variables, and metabolic and inflammatory markers) were analyzed. We applied five ML algorithms—logistic regression (LR), support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), and neural network (NN)—to develop the models. The area under the receiver operating characteristic (AUC-ROC) curve, calibration curve, and variable importance were used to evaluate the models’ performance. Results: During a median follow-up of 45.5 months, 179 patients (8.0%) experienced structural recurrence. The non-stimulated thyroglobulin, LN dissection, number of LNs dissected, lymph node metastasis ratio, N stage, comorbidity of hypertension, comorbidity of diabetes, body mass index, and low-density lipoprotein were used to develop the models. All models showed a greater AUC (AUC = 0.738 to 0.767) than did the ATA risk stratification (AUC = 0.620, DeLong test: P < 0.01). The SVM, XGBoost, and RF model showed greater sensitivity (0.568, 0.595, 0.676), specificity (0.903, 0.857, 0.784), accuracy (0.875, 0.835, 0.775), positive predictive value (PPV) (0.344, 0.272, 0.219), negative predictive value (NPV) (0.959, 0.959, 0.964), and F1 score (0.429, 0.373, 0.331) than did the ATA risk stratification (sensitivity = 0.432, specificity = 0.770, accuracy = 0.742, PPV = 0.144, NPV = 0.938, F1 score = 0.216). The RF model had generally consistent calibration compared with the other models. The Tg and the LNR were the top 2 important variables in all the models, the N stage was the top 5 important variables in all the models. Conclusions: The RF model achieved the expected prediction performance with generally good discrimination, calibration and interpretability in this study. This study sheds light on the potential of ML approaches for improving the accuracy of risk stratification for PTC patients. Trial registration: Retrospectively registered at www.chictr.org.cn (trial registration number: ChiCTR2300075574, date of registration: 2023-09-08).

Original Article Wavelet transformation can enhance computed tomography texture features: a multicenter radiomics study for grade assessment of COVID-19 pulmonary lesions Zekun Jiang, Jin Yin, Peilun Han, Nan Chen, Qingbo Kang, Yue Qiu, Yiyue Li, Qicheng Lao, Miao Sun, Dan Yang, Shan Huang, Jiajun Qiu, Kang Li

Early screening of PDAC (pancreatic ductal adenocarcinoma) based on plain CT (computed tomogra-phy) images is of great significance. Therefore, this work conducted a radiomics-aided diagnosis analysis of PDAC based on plain CT images. We explored a novel MSTA (multiresolution-statistical texture analysis) architecture to extract texture features and built machine learning models to classify PDACs and HPs (healthy pancreases). We also performed significance tests of differences to analyze the relationships between histopathological characteristics and texture features. The MSTA architecture originates from the analysis of histopathological characteristics and combines multiresolution analysis and statistical analysis to extract texture features. The MSTA architecture achieved better experimental results than the traditional architecture that scales the coefficient matrices of the multiresolution analysis. In the validation of the classifica-tions, the MSTA architecture achieved an accuracy of 81.19% and an AUC (area under the ROC (receiver operating characteristic) curve) of 0.88 (95% confidence interval: 0.84-0.92). In the test of the classifications, it achieved an accuracy of 77.66% and an AUC of 0.79 (95% confidence interval: 0.71-0.87). Moreover, the significance tests of differences showed that the extracted texture features may be relevant to the histopathological characteristics. The MSTA architecture is beneficial for the radiomics-aided diagnosis of PDAC based on plain CT images. Its texture features can potentially enhance radiologists’ imaging interpretation abilities.

Background: Low-density lipoprotein:high-density lipoprotein cholesterol ratio (LDL:HDL ratio) has a good performance in identifying diabetes mellitus (DM) and insulin resistance. However, it is not yet clear whether the LDL:HDL ratio is associated with a high-risk state of prediabetes. Methods: This cohort study retrospectively analyzed the data of 100,309 Chinese adults with normoglycemia at baseline. The outcome event of interest was new-onset prediabetes. Using multivariate Cox regression and smoothing splines to assess the association of LDL:HDL ratio with prediabetes. Results: During an average observation period of 37.4 months, 12,352 (12.31%) subjects were newly diagnosed with prediabetes. After adequate adjustment for important risk factors, the LDL:HDL ratio was positively correlated with the prediabetes risk, and the sensitivity analysis further suggested the robustness of the results. Additionally, in stratified analysis, we discovered significant interactions between LDL:HDL ratio and family history of DM, sex, body mass index and age (all P-interaction < 0.05); among them, the LDL:HDL ratio-related prediabetes risk decreased with the growth of body mass index and age, and increased significantly in women and people with a family history of DM. Conclusions: The increased LDL:HDL ratio in the Chinese population indicates an increased risk of developing prediabetes, especially in women, those with a family history of DM, younger adults, and non-obese individuals.

Background: Suicidal behaviors, including suicide deaths and attempts, are major public health concerns. However, previous suicide models required a huge amount of input features, resulting in limited applicability in clinical practice. Objective: We aimed to construct applicable models (ie, with limited features) for short- and long-term suicidal behavior prediction. We further validated these models among individuals with different genetic risks of suicide. Methods: Based on the prospective cohort of UK Biobank, we included 223 (0.06%) eligible cases of suicide attempts or deaths, according to hospital inpatient or death register data within 1 year from baseline and randomly selected 4460 (1.18%) controls (1:20) without such records. We similarly identified 833 (0.22%) cases of suicidal behaviors 1 to 6 years from baseline and 16,660 (4.42%) corresponding controls. Based on 143 input features, mainly including sociodemographic, environmental, and psychosocial factors; medical history; and polygenic risk scores (PRS) for suicidality, we applied a bagged balanced light gradient-boosting machine (LightGBM) with stratified 10-fold cross-validation and grid-search to construct the full prediction models for suicide attempts or deaths within 1 year or between 1 and 6 years. The Shapley Additive Explanations (SHAP) approach was used to quantify the importance of input features, and the top 20 features with the highest SHAP values were selected to train the applicable models. The external validity of the established models was assessed among 50,310 individuals who participated in UK Biobank repeated assessments both overall and by the level of PRS for suicidality. Results: Individuals with suicidal behaviors were on average 56 years old, with equal sex distribution. The application of these full models in the external validation data set demonstrated good model performance, with the area under the receiver operating characteristic (AUROC) curves of 0.919 and 0.892 within 1 year and between 1 and 6 years, respectively. Importantly, the applicable models with the top 20 most important features showed comparable external-validated performance (AUROC curves of 0.901 and 0.885) as the full models, based on which we found that individuals in the top quintile of predicted risk accounted for 91.7% (n=11) and 80.7% (n=25) of all suicidality cases within 1 year and during 1 to 6 years, respectively. We further obtained comparable prediction accuracy when applying these models to subpopulations with different genetic susceptibilities to suicidality. For example, for the 1-year risk prediction, the AUROC curves were 0.907 and 0.885 for the high (>2nd tertile of PRS) and low (<1st) genetic susceptibilities groups, respectively. Conclusions: We established applicable machine learning–based models for predicting both the short- and long-term risk of suicidality with high accuracy across populations of varying genetic risk for suicide, highlighting a cost-effective method of identifying individuals with a high risk of suicidality.