Predicting stroke and mortality in mitral stenosis with atrial flutter: A machine learning approach.

BACKGROUND: Our study hypothesized that an intelligent gradient boosting machine (GBM) model can predict cerebrovascular events and all-cause mortality in mitral stenosis (MS) with atrial flutter (AFL) by recognizing comorbidities, electrocardiographic and echocardiographic parameters. METHODS: The machine learning model was used as a statistical analyzer in recognizing the key risk factors and high-risk features with either outcome of cerebrovascular events or mortality. RESULTS: A total of 2184 patients with their chart data and imaging studies were included and the GBM analysis demonstrated mitral valve area (MVA), right ventricular systolic pressure, pulmonary artery pressure (PAP), left ventricular ejection fraction (LVEF), New York Heart Association (NYHA) class, and surgery as the most significant predictors of transient ischemic attack (TIA/stroke). MVA, PAP, LVEF, creatinine, hemoglobin, and diastolic blood pressure were predictors for all-cause mortality. CONCLUSION: The GBM model assimilates clinical data from all diagnostic modalities and significantly improves risk prediction performance and identification of key variables for the outcome of MS with AFL.

Identification and evaluation of novel drug combinations of Aurora kinase inhibitor CCT137690 for enhanced efficacy in oral cancer cells.

Oral cancer is the most prevalent subtype of head and neck cancers and arises mainly from squamous cells of the oral cavity. Patients with advanced metastatic disease have poor overall survival resulting primarily from limited treatment options. Recent advances in the understanding of molecular basis of oral tumorigenesis provide an opportunity for identification and validation of new drug targets. The deregulated expression of the Aurora family of mitotic kinases, for example, has been associated with pathogenesis and poor prognosis in oral cancer. Here, we have evaluated the efficacy of the pan-Aurora inhibitor (CCT137690) alone and in combination with different chemotherapeutic and targeted drugs to identify its synergistic partners in oral cancer cell lines (ORL-48 and ORL-115). CCT137690 effectively inhibits Aurora kinases in both the cell lines and displays potent antiproliferative activity towards them. Prolonged treatment of these cells with CCT137690 results in abrogated mitotic spindle formation, misaligned chromosome attachment and polyploidy that ultimately leads to apoptotic cell death. We further identified that inhibitors of EGFR (gefitinib) and PI3-kinase (pictilisib) synergize with CCT137690 to inhibit the proliferation of the oral cancer cell lines. Moreover, we demonstrate that polyethylene glycol-based nanocapsules harboring combinations of CCT137690 with gefitinib or pictilisib inhibit the growth of oral cancer cell lines in 3D spheroid cultures and induce apoptosis that is comparable to free drug combinations. In conclusion, we have demonstrated the in vitro efficacy of CCT137690 in oral cancer cell lines, identified novel drug combinations with CCT137690 and synthesized nanocapsules containing these drug combinations for co-administration.