Population based health data collection and analysis are important in epidemiological research. In recent years, with the rapid development of big data, Internet and cloud computing, artificial intelligence has gradually attracted attention of epidemiological researchers. More and more researchers are trying to use artificial intelligence algorithms for genome sequencing and medical image data mining, and for disease diagnosis, risk prediction and others. In recent years, machine learning, a branch of artificial intelligence, has been widely used in epidemiological research. This paper summarizes the key fields and progress in the application of machine learning in epidemiology, reviews the development history of machine learning, analyzes the classic cases and current challenges in its application in epidemiological research, and introduces the current application scenarios and future development trends of machine learning and artificial intelligence algorithms for the better exploration of the epidemiological research value of massive medical health data in China.

【Objective】 To explore the role and mechanism of TRPC in promoting extracellular matrix (ECM) deposition in rat glomerular mesangial cells (HBZY-1). Methods Immunofluorescence staining was performed to observe the distribution and expression of TRPC1 and TRPC6 in HBZY-1 cells. After AngⅡ stimulation, qRT-PCR and Western blotting were used to detect the mRNA and protein expressions of Gαq/PLCβ4/TRPC signaling pathway main proteins and ECM deposition indicators (α-SMA, collagenⅢ and fibronectin). By silencing the expressions of TRPC1 and TRPC6 by RNA interference, the expressions of ECM deposition indicators were detected. Changes in [Ca²⁺]i influx were determined through Fluo-4AM Ca²⁺ imaging. 【Results】 Both TRPC1 and TRPC6 were expressed in HBZY-1, and were mainly located in cell membrane and cytoplasm. After AngⅡ stimulation, Gαq/PLCβ4/TRPC signaling pathway was activated, and the mRNA and protein expressions of Gαq, PLCβ4, TRPC1 and TRPC6 were all increased (P<0.05). [Ca²⁺]i influx also increased (P<0.01), and the mRNA and protein expressions of ECM deposition indicators (α-SMA, ColⅢ and Fn) were upregulated (P<0.05). Silencing the expressions of TRPC1 and TRPC6 by RNA interference led to decreased [Ca²⁺]i influx (P<0.05), and downregulated mRNA and protein expressions of ECM deposition indicators in HBZY-1 cells (P<0.05). The results suggested that inhibition of TRPC expressions could inhibit AngⅡ induced ECM deposition in HBZY-1 cells, which might be associated with decreased [Ca²⁺]i influx. 【Conclusion】 TRPC may be a novel therapeutic target of renal fibrosis.

  Objective  Different from other etiologies of early-onset scoliosis (EOS), congenital early-onset scoliosis (CEOS) is mainly linked to vertebral anomalies, such as formation failures and segmentation failures at the apex segments. So far, there is little research on CEOS patients who have completed traditional growing rods (TGR) treatment, and the initial outcomes of TGR with or without apical control technique (ACT) are different. Therefore, we compared the "final" results of CEOS patients who completed TGR treatment with or without ACT.  Methods  We conducted a retrospective study of CEOS patients who completed TGR treatment from 2007—2020. They either had final fusion or were followed up after reaching skeletal maturity. We split the patients into two groups based on whether they had ACT with TGR or not. The ACT-TGR group had apical vertebrectomy/hemivertebrectomy with short fusion and TGR. The TGR-only group had only TGR. We looked at their demographic features, radiographic measurements, and complications.  Results  This study enrolled 46 CEOS patients, of which 13 patients were in the ACT-TGR group and 33 patients in the TGR group. The ACT-TGR group had a longer distraction interval (1.17 years vs. 0.75 years). The ACT-TGR group had a larger preoperative main curve [87.00(63.50, 98.00)], but the residual curve degrees were comparable between the two groups at the last follow-up (P=0.354). At the last follow-up, the T1-12 and T1-S1 heights were similar between the two groups. The ACT-TGR group had a lower number of implant-related complications per patient (0.77 vs. 1.48). Three patients in the ACT-TGR group underwent final fusion, while 17 patients in the TGR group underwent final fusion (P=0.060).  Conclusions  Both ACT-TGR and traditional TGR coud effectively correct deformity and preserve spinal growth in CEOS patients. ACT-TGR had a better corrective effect on patients with severe deformity and did not have a significant impact on spinal height. For patients with acceptable correction, spontaneous fusion and without implant failure, retaining the implant and continuing observation could be a strategy for graduating from growing rod treatment.