Machine and deep learning-based clinical characteristics and laboratory markers for the prediction of sarcopenia.

BACKGROUND: Sarcopenia is an age-related progressive skeletal muscle disorder involving the loss of muscle mass or strength and physiological function. Efficient and precise AI algorithms may play a significant role in the diagnosis of sarcopenia. In this study, we aimed to develop a machine learning model for sarcopenia diagnosis using clinical characteristics and laboratory indicators of aging cohorts. METHODS: We developed models of sarcopenia using the baseline data from the West China Health and Aging Trend (WCHAT) study. For external validation, we used the Xiamen Aging Trend (XMAT) cohort. We compared the support vector machine (SVM), random forest (RF), eXtreme Gradient Boosting (XGB), and Wide and Deep (W&D) models. The area under the receiver operating curve (AUC) and accuracy (ACC) were used to evaluate the diagnostic efficiency of the models. RESULTS: The WCHAT cohort, which included a total of 4057 participants for the training and testing datasets, and the XMAT cohort, which consisted of 553 participants for the external validation dataset, were enrolled in this study. Among the four models, W&D had the best performance (AUC = 0.916 ± 0.006, ACC = 0.882 ± 0.006), followed by SVM (AUC =0.907 ± 0.004, ACC = 0.877 ± 0.006), XGB (AUC = 0.877 ± 0.005, ACC = 0.868 ± 0.005), and RF (AUC = 0.843 ± 0.031, ACC = 0.836 ± 0.024) in the training dataset. Meanwhile, in the testing dataset, the diagnostic efficiency of the models from large to small was W&D (AUC = 0.881, ACC = 0.862), XGB (AUC = 0.858, ACC = 0.861), RF (AUC = 0.843, ACC = 0.836), and SVM (AUC = 0.829, ACC = 0.857). In the external validation dataset, the performance of W&D (AUC = 0.970, ACC = 0.911) was the best among the four models, followed by RF (AUC = 0.830, ACC = 0.769), SVM (AUC = 0.766, ACC = 0.738), and XGB (AUC = 0.722, ACC = 0.749). CONCLUSIONS: The W&D model not only had excellent diagnostic performance for sarcopenia but also showed good economic efficiency and timeliness. It could be widely used in primary health care institutions or developing areas with an aging population. TRIAL REGISTRATION: Chictr.org, ChiCTR 1800018895.

Effects of fenofibrate on inflammatory cytokines in diabetic retinopathy patients.

The role of cytokines in diabetic retinopathy (DR) and effects of fenofibrate on cytokines were explored by observing changes in serum IL-1ß, TNF-α, VEGF, and Lp-PLA2 in different stages of DR and the intervention effect of oral fenofibrate on cytokines.In total, 190 patients with type 2 DR were enrolled and divided into 3 groups: diabetic without retinopathy (NDR) group (n = 30), nonproliferative diabetic retinopathy (NPDR) group (n = 80), and proliferative diabetic retinopathy (PDR) group (n = 80). According to whether or not to accept fenofibrate treatment, NPDR and PDR groups were further divided into the NPDR control (NPDR1) group (n = 40) and the NPDR treatment (NPDR2) group (n = 40), and the proliferative diabetic retinopathy control (PDR1, n = 40) group and the proliferative diabetic retinopathy treatment (PDR2) group (n = 40). At 12 weeks after fenofibrate treatment, serum IL-1ß, TNF-α, VEGF, and Lp-PLA2 levels were detected.In PDR and NPDR patients, levels of serum cytokines such as IL-1ß (120.56 ±â€Š27.32 pg/mL vs 112.34 ±â€Š19.45 pg/mL vs 82.9 ±â€Š13.8 pg/mL), TNF-α (125.86 ±â€Š25.57 pg/mL vs 109.48 ±â€Š20.15 pg/mL vs 80.7 ±â€Š12.8 pg/mL), VEGF (166.65 ±â€Š37.74 pg/mL vs 148.54 ±â€Š36.27 pg/mL vs 88.97 ±â€Š24.86 pg/mL), and Lp-PLA2 (172.34 ±â€Š45.22 µg/L vs 154.66 ±â€Š40.98 µg/L vs 125.88 ±â€Š38.87 µg/L) were significantly higher than in diabetes patients without retinopathy. After fenofibrate treatment, serum IL-1ß, TNF-α, VEGF, and Lp-PLA2 significantly decreased in NPDR and PDR patients.Serum IL-1ß, TNF-α, VEGF, and Lp-PLA2 play an important role in occurrence and development of diabetic retinopathy. Fenofibrate can reduce cytokine levels in DR patients and improve inflammatory response.

Is it time to abandon the digital rectal examination? Lessons from the PLCO Cancer Screening Trial and peer-reviewed literature.

OBJECTIVE: In 2012 the US Preventive Services Task Force released recommendations against prostate specific antigen (PSA) based screening for prostate cancer, but did not fully address screening via digital rectal exam (DRE). As such, many practitioners continue to perform DRE in attempts to identify men with clinically significant prostate cancer (CSPC). This study seeks to determine the value of DRE in detecting CSPC in the era of PSA-based screening. METHODS: Data from the Prostate, Lung, Colorectal, and Ovarian (PLCO) Screening Trial, a nationwide population-based study evaluating cancer screening programs and their impact on cancer mortality, was analyzed for PSA, DRE, and cancer status. In the screening arm of the PLCO, 38,340 men received annual PSA and DRE examinations for the first 3 years. Those with an abnormal test result were referred to their individual care provider for biopsy. The ability of DRE to detect CSPC, defined as intermediate risk or higher based on National Comprehensive Cancer Network guidelines and age ≤75, was evaluated in the context of both normal and abnormal PSA. RESULTS: A total of 5064 men had abnormal DRE in the setting of normal PSA, of whom 99 (2%) were diagnosed with CSPC. When both PSA and DRE were abnormal, 218 (20%) participants were diagnosed with CSPC (RR = 2.06 [1.78-2.39] versus abnormal PSA alone). CONCLUSIONS: DRE screening in the setting of normal PSA captured an additional 2% of men with CSPC. This incremental gain suggests that routine DRE screening subjects a large number of men to invasive, potentially uncomfortable examinations for relatively minimal gain. Key limitations: Our conclusions are based on data derived from the PLCO study which has been criticized on the basis of inconsistent biopsies following positive screening tests, lack of end of study biopsies to determine population disease burden, and low numbers of black men.