RESUMEN
Intradialytic hypotension (IDH) is a common and potentially life-threatening complication in hemodialysis patients. Traditional preventive measures have shown limited effectiveness in reducing IDH incidence. This systematic review evaluates the existing literature on the use of artificial intelligence (AI) and machine learning (ML) models for predicting IDH in hemodialysis patients. A comprehensive literature search identified five eligible studies employing diverse AI/ML algorithms, including artificial neural networks, decision trees, support vector machines, XGBoost, random forests, and LightGBM. These models utilized various features such as patient demographics, clinical data, laboratory findings, and dialysis-related parameters. The studies reported promising results, with several models achieving high prediction accuracies, sensitivities, specificities, and area under the receiver operating characteristic curve values for predicting IDH. However, limitations include variations in study populations, retrospective designs, and the need for prospective validation. Future research should focus on multicenter prospective studies, assessing clinical utility, and integrating interpretable AI/ML models into clinical decision support systems.
RESUMEN
Patients diagnosed with human epidermal growth factor receptor 2 (HER2)-positive breast cancer require treatment upfront because of the aggressive nature of this type of cancer. Patients with early-stage HER2-positive breast cancer are usually treated with neoadjuvant therapy. This neoadjuvant therapy comprises targeted therapy and chemotherapy. Targeted therapy is given with trastuzumab. Pertuzumab is either administered or not with trastuzumab as a targeted therapy. This systematic review and meta-analysis aim to find out and compare the benefit achieved in terms of pathologic complete response (pCR) by adding pertuzumab to the neoadjuvant treatment regimen for early-stage HER2-positive breast cancer patients. Various databases were searched to find out relevant clinical trials. After going through PubMed, Embase, and Cochrane, three clinical trials were shortlisted for this systematic review and meta-analysis. These three clinical trials were double-armed. Pertuzumab was present in one arm while being absent in one arm to assess the benefit of adding pertuzumab in terms of pCR achieved. Data were analyzed using RevMan Web (Cochrane, London, UK). The odds ratio and 95% confidence interval were calculated for the outcome. The Mantel-Haenszel method and random effect model were used for analysis. The risk of bias in studies was evaluated using the Cochrane risk of bias tool for randomized controlled trials (ROB2). The summary statistics showed that the incidence of pCR was more in the experimental group (having pertuzumab) as compared to the control group (without pertuzumab) with an odds ratio of 2.10 (95% CI: 1.56-2.83) with I2 = 0%. In three double-arm trials, there were 840 participants, 445 in the experimental group and 395 in the control group. A total of 203 (45%) patients out of 445 in the experimental group achieved pCR, whereas 127 (32%) patients out of 395 in the control group achieved pCR. Through the results of this study, it can be concluded that the rate of pCR achieved was higher in that arm in which pertuzumab was present compared to the study arm in which only trastuzumab was given as targeted therapy. Thus, it can be suggested that pertuzumab be added to the neoadjuvant regimen for early-stage HER2-positive breast cancer patients. This would result in achieving a better pCR. And by improving pCR rates, the survival outcomes of patients can be significantly improved.