Application of logistic regression and machine learning methods for idiopathic inflammatory myopathies malignancy prediction.

OBJECTIVES: Malignancy is related to idiopathic inflammatory myopathies (IIM) and leads to a poor prognosis. Early prediction of malignancy is thought to improve the prognosis. However, predictive models have rarely been reported in IIM. Herein, we aimed to establish and use a machine learning (ML) algorithm to predict the possible risk factors for malignancy in IIM patients. METHODS: We retrospectively reviewed the medical records of 168 patients diagnosed with IIM in Shantou Central hospital, from 2013 to 2021. We randomly divided patients into two groups, the training sets (70%) for construction of the prediction model, and the validation sets (30%) for evaluation of model performance. We constructed six types of ML algorithms models and the AUC of ROC curves were used to describe the efficacy of the model. Finally, we set up a web version using the best prediction model to make it more generally available. RESULTS: According to the multi-variable regression analysis, three predictors were found to be the risk factors to establish the prediction model, including age, ALT<80U/L, and anti-TIF1-γ, and ILD was found to be a protective factor. Compared with five other ML algorithms models, the traditional algorithm logistic regression (LR) model was as good or better than the other models to predict malignancy in IIM. The AUC of the ROC using LR was 0.900 in the training set and 0.784 in the validation set. We selected the LR model as the final prediction model. Accordingly, a nomogram was constructed using the above four factors. A web version was built and can be visited on the website or acquired by scanning the QR code. CONCLUSIONS: The LR algorithm appears to be a good predictor of malignancy and may help clinicians screen, evaluate and follow up high-risk patients with IIM.

Predictive model of risk and severity of enteritis in systemic lupus erythematosus.

INTRODUCTION: To describe the clinical and laboratory features of systemic lupus erythematosus (SLE) enteritis and to establish a predictive model of risk and severity of lupus enteritis (LE). METHODS: Records of patients with SLE complaining about acute digestive symptoms were reviewed. The predictive nomogram for the diagnosis of LE was constructed by using R. The accuracy of the model was tested with correction curves. The receiver operating characteristic curve (ROC curve) program and a Decision curve analysis (DCA) were used for the verification of LE model. Receiver operating characteristic curve was also employed for evaluation of factors in the prediction of severity of LE. RESULTS: During the eight year period, 46 patients were in the LE group, while 32 were in the non-LE group. Abdominal pain, emesis, D-dimer >5 µg/mL, hypo-C3, and anti-SSA positive remained statistically significant and were included into the prediction model. Area under the curve (AUC) of ROC curve in this model was 0.909. Correction curve indicated consistency between the predicted rate and actual diagnostic rates. The DCA showed that the LE model was of benefit. Forty-four patients were included in developing the prediction model of LE severity. Infection, SLE disease activity index (SLEDAI), CT score, and new CT score were validated as risk factors for LE severity. The AUC of the combined SLEDAI, infection and new CT score were 0.870. CONCLUSION: The LE model exhibits good predictive ability to assess LE risk in SLE patients with acute digestive symptoms. The combination of SLEDAI, infection, and new CT score could improve the assessment of LE severity.

Exploring Task Structure for Brain Tumor Segmentation from Multi-modality MR Images.

Brain tumor segmentation, which aims at segmenting the whole tumor area, enhancing tumor core area, and tumor core area from each input multi-modality bioimaging data, has received considerable attention from both academia and industry. However, the existing approaches usually treat this problem as a common semantic segmentation task without taking into account the underlying rules in clinical practice. In reality, physicians tend to discover different tumor areas by weighing different modality volume data. Also, they initially segment the most distinct tumor area, and then gradually search around to find the other two. We refer to the first property as the task-modality structure while the second property as the task-task structure, based on which we propose a novel task-structured brain tumor segmentation network (TSBTS net). Specifically, to explore the task-modality structure, we design a modality-aware feature embedding mechanism to infer the important weights of the modality data during network learning. To explore the tasktask structure, we formulate the prediction of the different tumor areas as conditional dependency sub-tasks and encode such dependency in the network stream. Experiments on BraTS benchmarks show that the proposed method achieves superior performance in segmenting the desired brain tumor areas while requiring relatively lower computational costs, compared to other state-of-the-art methods and baseline models.

Changes in the Prevalence of Rheumatic Diseases in Shantou, China, in the Past Three Decades: A COPCORD Study.

This study aimed to clarify changes in the prevalence of rheumatic diseases in Shantou, China, in the past 3 decades and validate whether stair-climbing is a risk factor for knee pain and knee osteoarthritis (KOA). The World Health Organization-International League Against Rheumatism Community Oriented Program for Control of Rheumatic Diseases (COPCORD) protocol was implemented. In all, 2337 adults living in buildings without elevators and 1719 adults living in buildings with elevators were surveyed. The prevalence of rheumatic pain at any site and in the knee was 15.7% and 10.2%, respectively; both types of pain had a significantly higher incidence in residents of buildings without elevators than was reported by people who lived in buildings with elevators (14.9% vs. 10.6% and 11.32% vs. 8.82%, respectively) (both P < 0.0001). The prevalence of rheumatic pain in the neck, lumbar spine, shoulder, elbow, and foot was 5.6%, 4.5%, 3.1%, 1.4%, and 1.8%, respectively; these findings were similar to the data from the 1987 rural survey, but were somewhat lower than data reported in the urban and suburban surveys of the 1990s, with the exception of neck and lumbar pain. The prevalence of KOA, gout, and fibromyalgia was 7.10%, 1.08%, and 0.07%, respectively, and their prevalence increased significantly compared with those in previous studies from the 20th century. There were no significant differences in the prevalence of rheumatoid arthritis (RA) (0.35%) or ankylosing spondylitis (AS) (0.31%) compared to that reported in prior surveys. The prevalence of KOA was higher in for residents of buildings without elevators than that in those who had access to elevators (16-64 years, 5.89% vs. 3.95%, P = 0.004; 16->85 years, 7.64% vs. 6.26%, P = 0.162). The prevalence of RA and AS remained stable, whereas that of KOA, gout, and fibromyalgia has increased significantly in Shantou, China, during the past 3 decades. Stair-climbing might be an important risk factor for knee pain and KOA.