Development of an interpretable machine learning model associated with heavy metals' exposure to identify coronary heart disease among US adults via SHAP: Findings of the US NHANES from 2003 to 2018.

Limited information is available on the links between heavy metals' exposure and coronary heart disease (CHD). We aim to establish an efficient and explainable machine learning (ML) model that associates heavy metals' exposure with CHD identification. Our datasets for investigating the associations between heavy metals and CHD were sourced from the US National Health and Nutrition Examination Survey (US NHANES, 2003-2018). Five ML models were established to identify CHD by heavy metals' exposure. Further, 11 discrimination characteristics were used to test the strength of the models. The optimally performing model was selected for identification. Finally, the SHapley Additive exPlanations (SHAP) tool was used for interpreting the features to visualize the selected model's decision-making capacity. In total, 12,554 participants were eligible for this study. The best performing random forest classifier (RF) based on 13 heavy metals to identify CHD was chosen (AUC: 0.827; 95%CI: 0.777-0.877; accuracy: 95.9%). SHAP values indicated that cesium (1.62), thallium (1.17), antimony (1.63), dimethylarsonic acid (0.91), barium (0.76), arsenous acid (0.79), total arsenic (0.01) in urine, and lead (3.58) and cadmium (4.66) in blood positively contributed to the model, while cobalt (-0.15), cadmium (-2.93), and uranium (-0.13) in urine negatively contributed to the model. The RF model was efficient, accurate, and robust in identifying an association between heavy metals' exposure and CHD among US NHANES 2003-2018 participants. Cesium, thallium, antimony, dimethylarsonic acid, barium, arsenous acid, and total arsenic in urine, and lead and cadmium in blood show positive relationships with CHD, while cobalt, cadmium, and uranium in urine show negative relationships with CHD.

Efficacy and safety of laser combination therapy and laser alone therapy for keloid: a systematic review and meta-analysis.

To evaluate the efficacy and safety of laser alone therapy and laser combination therapy (mainly combined with other kinds of laser or steroids) for keloid.PubMed, Embase and Web of Science were searched for relevant articles from inception to June 2020. Comprehensive Meta-Analysis software 2.0 (CMA) was used to perform the meta-analysis.A total of 29 articles were included in this meta-analysis. During the mean follow-up of 14 (1-84) months, the overall improvement rates of baseline Vancouver scar scale (VSS) score and itch were 0.454 (95%CI 0.351-0.561, I2 = 0) and 0.786 (95%CI 0.613-0.895, I2 = 0) in the laser combination therapy group. The improvement rates of scar height and flexibility in the laser combination therapy group were 0.629 (95%CI 0.519-0.727, I2 = 52.089) and 0.784 (95%CI 0.251-0.975, I2 = 89.420). The average improvement rate of the scar score in laser combination therapy was 0.338 (0.201-0.510); however, there were insufficient data for laser alone therapy comparison. The laser combination therapy had a greater pain improvement rate, 0.580 (0.389-0.750) versus 0.420 (0.224-0.645), compared to laser alone therapy, and a greater degree of good or excellent (> 50%) improvement in the overall scar, 0.636 (95%CI 0.347-0.852) versus 0.149 (95%CI 0.032-0.482), with laser alone therapy. Moreover, a lower regrowth rate of 0.187 (0.129-0.263) versus 0.249 (0.060-0.631), a lower post-treatment pigmentation rate of 0.125 (0.091-0.169) versus 0.135 (0.058-0.282), and a lower infection rate of 0.047 (0.009-0.209) versus 0.076 (0.012-0.351) were observed in the laser combination therapy compared with those rates in the laser alone therapy.The overall effect of laser combination therapy was better than that of laser alone therapy, and the incidence of adverse reactions was lower in laser combination therapy than in laser alone therapy.

Association between MTHFR polymorphisms and overall survival of colorectal cancer patients in Northeast China.

A follow-up study has been carried out to assess the association between MTHFR polymorphisms (SNPs) and overall survival (OS) of colorectal cancer (CRC) patients. Data on 411 CRC patients after surgery were tested for the MTHFR 677C > T and 1298A > C polymorphisms. For MTHFR C677T, patients with CT genotype (HR = 1.17; 95 % CI 0.77-1.80) and those with TT genotype (HR = 1.09; 95 % CI 0.67-1.75) had no statistically significant greater risk of dying than those with wild-type genotype. For MTHFR A1298C, the HRs of AC and CC genotype were 1.09 (95 % CI 0.75-1.59) and 0.79 (95 % CI 0.48-1.29) comparing with AA genotype. In the subgroup, 183 patients received chemotherapy treatment, and the HRs of patients with CT and TT genotype were 0.93 (95 % CI 0.50-1.72) and 0.86 (95 % CI 0.44-1.68) for MTHFR C677T. For A1298C polymorphism, AC genotype (HR = 1.39; 95 % CI 0.81-2.39) and CC genotype (HR = 1.22; 95 % CI 0.75-2.00) did not show significant differences. In conclusions, no significant association was observed between the 677C > T and 1298A > C polymorphisms of MTHFR and the prognosis of colorectal cancer patients with curative resection, including all the subjects and the subgroup of chemotherapy.