Machine Learning for Selecting Important Clinical Markers of Imaging Subgroups of Cerebral Small Vessel Disease Based on a Common Data Model

Differences in the imaging subgroups of cerebral small vessel disease(CSVD)need to be further explored.First,we use propensity score matching to obtain balanced datasets.Then random forest(RF)is adopted to classify the subgroups compared with support vector machine(SVM)and extreme gradient boosting(XGBoost),and to select the features.The top 10 important features are included in the stepwise logistic regression,and the odds ratio(OR)and 95%confidence interval(CI)are obtained.There are 41290 adult inpatient records diagnosed with CSVD.Accuracy and area under curve(AUC)of RF are close to 0.7,which performs best in classification compared to SVM and XGBoost.OR and 95%CI of hematocrit for white matter lesions(WMLs),lacunes,microbleeds,atrophy,and enlarged perivascular space(EPVS)are 0.9875(0.9857−0.9893),0.9728(0.9705−0.9752),0.9782(0.9740−0.9824),1.0093(1.0081−1.0106),and 0.9716(0.9597−0.9832).OR and 95%CI of red cell distribution width for WMLs,lacunes,atrophy,and EPVS are 0.9600(0.9538−0.9662),0.9630(0.9559−0.9702),1.0751(1.0686−1.0817),and 0.9304(0.8864−0.9755).OR and 95%CI of platelet distribution width for WMLs,lacunes,and microbleeds are 1.1796(1.1636−1.1958),1.1663(1.1476−1.1853),and 1.0416(1.0152−1.0687).This study proposes a new analytical framework to select important clinical markers for CSVD with machine learning based on a common data model,which has low cost,fast speed,large sample size,and continuous data sources.

2017 Chinese expert consensus on the clinical application ofserum marker for thyroid cancer

In recent years, the clinical incidence of thyroid cancer has been increasing year by year, and its risk assessment and clinical management methods have also been accordingly modified and constantly improved. There are great differences between the clinical diagnostic and therapeutic modes and disease management of thyroid cancer employed by various medical institutions in China, particularly with regard to the clinical application of serum marker of thyroid cancer. To this end, the China Anti-Cancer Association Thyroid Cancer Specialized Committee Chinese Association of Thyroid Oncology organized this compilation of ExpertConsensus on Clinical Application of Serum Marker of Thyroid Cancer to help and impel relevant clinical institutions and professionals to standardize clinical diagnosis, treatment, and long-term management of thyroid cancer, and to properly utilize the serum marker for scientific auxiliary clinical diagnosis and assessment of thyroid cancer before and after operation.

Recent advance of fluorescent probes for detection of drug-induced liver injury markers

Drug-induced liver injury(DILI)is a common and serious adverse drug reaction.At present,DILI is perfectly diagnozed in clinical settings using Roussel Uclaf causality assessment method(RUCAM)in its original version published 1993 and its updated version published 2016,well established worldwide as a diagnostic algorithm with a high sensitivity and specificity.Nevertheless,the search for additional detection methods supporting RUCAM continues.In recent years,with the development of optical imaging technology,fluorescent probes have gradually shown great advantages in the detection and diagnosis of DILI markers such as high sensitivity,anti-interference,real-time monitoring and non-invasive measurement.In this review,the recent advances of fluorescent probes for evaluation of DILI in experimental studies were summarized according to various markers of DILI.We believe that learning about the design and practical application of these probes will contribute to the further development of detection sensors for DILI markers.

Increased Expression of Serum Monocyte Chemoattractant Protein-1,Chemokine(C-C motif)Ligand 3,and Interleukins in Patients With Vitiligo

Objective:Vitiligo is a chronic,acquired depigmentation of the skin,which can be divided into active and stable vitiligo.The stable and active stages are not immutable and often alternate.Identification of internal markers would help to diagnose the active stage of vitiligo,and the purpose of this study was to find potential active markers in the progression of vitiligo.Methods:We compared 30 healthy controls to 60 patients with vitiligo(30 with active disease and 30 with stable disease)regarding the expression of serum monocyte chemoattractant protein(MCP)-1,chemokine(C-C motif)ligand(CCL)3,CCL5,CCL21,interleukin(IL)-6,and IL-17.Specimens were collected from May 2017 to December 2018.Serological detection was carried out by enzyme-linked immunosorbent assay.The difference between groups was compared by Kruskal-Wallis H test and Mann-Whitney U test.Results:We found that the serum levels of MCP-1,CCL3,IL-6,and IL-17 were significantly higher in patients with vitiligo than in healthy controls(P<0.01)and that IL-17 was higher in patients with active vitiligo than in those with stable vitiligo(P<0.01).After 3months of treatment,the serum IL-17 level of patients with active vitiligo was not significantly different from that before treatment(P=0.526);after 6months of treatment,however,the serum IL-17 level had significantly decreased(P<0.01).Conclusion:These findings suggest that the serum IL-17 level can be used as a marker of vitiligo disease activity giving it certain guiding significance for clinical treatment.

Expression of PC-cell-derived growth factor in breast cancer

This study is mainly aimed at evaluating the expression of PC-cell-derived growth factor(PCDGF)in breast cancer and breast adenofibroma,and to compare with other commonly used clinical pathological indices,then to investigate the diagnostic and targeted therapeutic purpose of PCDGF in breast cancer tissue.In this study,we detected the expression of PCDGF,p53 and CerbB-2 in breast cancer tissue and the expression of PCDGF in breast adenofibroma tissue by immunohistochemical method,and analyzed the relationship between them.We found that PCDGF was expressed in most breast cancer tissue,but was not in breast adenofibroma tissue,and the expression of PCDGF was related with the tumor’s pathological category and the expression of estrogen receptor(ER)and progesterone receptor(PR)and p53,but there was no statistical dependability between PCDGF and cerbB-2.From this study,we predict that PCDGF may serve as a marker in the secondary diagnosis of breast cancer,and may participate in the generation and differentiation of breast cancer cells,and become an effective target of therapy for breast cancer.