Predictive Value of Machine Learning for Platinum Chemotherapy Responses in Ovarian Cancer: Systematic Review and Meta-Analysis.

BACKGROUND: Machine learning is a potentially effective method for predicting the response to platinum-based treatment for ovarian cancer. However, the predictive performance of various machine learning methods and variables is still a matter of controversy and debate. OBJECTIVE: This study aims to systematically review relevant literature on the predictive value of machine learning for platinum-based chemotherapy responses in patients with ovarian cancer. METHODS: Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we systematically searched the PubMed, Embase, Web of Science, and Cochrane databases for relevant studies on predictive models for platinum-based therapies for the treatment of ovarian cancer published before April 26, 2023. The Prediction Model Risk of Bias Assessment tool was used to evaluate the risk of bias in the included articles. Concordance index (C-index), sensitivity, and specificity were used to evaluate the performance of the prediction models to investigate the predictive value of machine learning for platinum chemotherapy responses in patients with ovarian cancer. RESULTS: A total of 1749 articles were examined, and 19 of them involving 39 models were eligible for this study. The most commonly used modeling methods were logistic regression (16/39, 41%), Extreme Gradient Boosting (4/39, 10%), and support vector machine (4/39, 10%). The training cohort reported C-index in 39 predictive models, with a pooled value of 0.806; the validation cohort reported C-index in 12 predictive models, with a pooled value of 0.831. Support vector machine performed well in both the training and validation cohorts, with a C-index of 0.942 and 0.879, respectively. The pooled sensitivity was 0.890, and the pooled specificity was 0.790 in the training cohort. CONCLUSIONS: Machine learning can effectively predict how patients with ovarian cancer respond to platinum-based chemotherapy and may provide a reference for the development or updating of subsequent scoring systems.

Comparison of risk prediction models for the progression of pelvic inflammatory disease patients to sepsis: Cox regression model and machine learning model.

Introduction: The present study presents the development and validation of a clinical prediction model using random survival forest (RSF) and stepwise Cox regression, aiming to predict the probability of pelvic inflammatory disease (PID) progressing to sepsis. Methods: A retrospective cohort study was conducted, gathering clinical data of patients diagnosed with PID between 2008 and 2019 from the Medical Information Mart for Intensive Care (MIMIC)-IV database. Patients who met the Sepsis 3.0 diagnostic criteria were selected, with sepsis as the outcome. Univariate Cox regression and stepwise Cox regression were used to screen variables for constructing a nomogram. Moreover, an RSF model was created using machine learning algorithms. To verify the model's performance, a calibration curve, decision curve analysis (DCA), and receiver operating characteristic (ROC) curve were utilized. Furthermore, the capabilities of the two models for estimating the incidence of sepsis in PID patients within 3 and 7 days were compared. Results: A total of 1064 PID patients were included, of whom 54 had progressed to sepsis. The established nomogram highlighted dialysis, reduced platelet (PLT) counts, history of pneumonia, medication of glucocorticoids, and increased leukocyte counts as significant predictive factors. The areas under the curve (AUCs) of the nomogram for prediction of PID progression to sepsis at 3-day and 7-day (3-/7-day) in the training set and the validation set were 0.886/0.863 and 0.824/0.726, respectively, and the C-index of the model was 0.8905. The RSF displayed excellent performance, with AUCs of 0.939/0.919 and 0.712/0.571 for 3-/7-day risk prediction in the training set and validation set, respectively. Conclusion: The nomogram accurately predicted the incidence of sepsis in PID patients, and relevant risk factors were identified. While the RSF model outperformed the Cox regression models in predicting sepsis incidence, its performance exhibited some instability. On the other hand, the Cox regression-based nomogram displayed stable performance and improved interpretability, thereby supporting clinical decision-making in PID treatment.

Association between gene polymorphism of folate metabolism and recurrent spontaneous abortion in Asia: A Meta-analysis.

To evaluate the association between gene polymorphisms of MTHFR (C677T, A1298C) and MTRR (A66G), and the recurrent spontaneous abortion (RSA) risk in Asia.Related case-control studies were collected, selected, and screened. A meta-analysis was conducted by Stata 12.0 software to assess the association between polymorphisms of target genes and RSA.Altogether 30 studies examining the relationship between genetic polymorphism of folate metabolism and RSA risk were included, among which 20 studies were related to MTHFR C677T, 11 to MTHFR A1298C and 6 to MTRR A66G. The studies suggested that MTHFR C677T polymorphism was closely connected with RSA risk under all models (P < .05). Furthermore according to the subgroup analysis of ethnicity, the correlation between C677T polymorphism and RSA was stronger in north of China when compared with south of China and other Asian countries (P > . 05). For MTHFR A1298C, it was closely related to RSA risk in all gene models except for (AC vs AA) (P < .05). However, when it comes to MTRR A66G, there was no significant correlation between gene A66G polymorphism and RSA risk except for the additive gene model (G vs A) (P < .05).The present evidence shows that the correlation between gene polymorphisms and RSA risk can be found in MTHFR C677T, A1298C (except for heterozygote model) and MTRR A66G (only in additive genotypes), and the detection of the correlated gene polymorphisms mentioned above is of certain guiding significance for preventing RSA and screening high-risk groups.

Associations between tumor necrosis factor-α and interleukin-6 polymorphisms and unexplained recurrent spontaneous abortion risk: A meta-analysis.

To evaluate the associations between Tumor necrosis factor-α (TNF-α)(-238G>A) and Interleukin-6 (IL-6)(-174G>C) polymorphism and risk of unexplained recurrent spontaneous abortion (URSA).Correlated case-control studies were collected by computer retrieval. A meta-analysis was conducted by Stata 12.0 software to analysis the strength of association between polymorphism of TNF-α -238G>A and IL-6 -174G>C and URSA.Twenty-one articles with twenty-two studies were included, of which 12 and 10 studies were respectively related to mutation of TNF-α -238G>A, IL-6 -174G>C and URSA. The integrated results showed that the TNF-α-238G>A gene mutation was significantly correlated with the risk of URSA under homozygote model (AA vs GG;OR 1.533,95% CI 1.022-2.301) and recessive model (AA vs GG+AG;OR 1.571,95%CI 1.050-2.350)(P < .05). There was no association between URSA and TNF-α -238G>A under heterozygote model (AG vs GG;OR 0.963,95% CI 0.816-1.137), dominant model (AA+AG vs GG; OR 1.031,95%CI 0.880-1.209) and additive model (A vs G;OR 1.046,95%CI 0.909-1.203)(P > .05). The results of subgroup analysis based on ethnicity showed that -238G>A was significantly correlated with the risk of URSA in Asians under all gene models except for heterozygote model (AG vs GG; OR 1.129,95% CI 0.857-1.487) (P < .05). In Caucasians, it was dominant model (AA+AG vs GG; OR 1.430,95%CI 1.040-1.965) (P < .05) rather than others that showed relationship with URSA. From the integrated results, association was manifested between -174G>C and URSA under all gene models (P < .05) except for recessive model (CC vs GG+CG, OR 1.166, 95%CI 0.938-1.449) (P > .05), which is identical to subgroup analysis based on ethnicity.It is of great guiding significance for screening out and preventing URSA among high-risk women to test on TNF-α -238G>A and IL-6 -174G>C under gene models mentioned above which are highly associated with the risk of URSA, which can act as biological markers for URSA.