Metastasis is one of the most challenging problems in cancer diagnosis and treatment, as causal factors have yet to be fully disentangled. Prediction of the metastatic status of breast cancer is important for informing treatment protocols and reducing mortality. However, the systems biology behind metastasis is complex and driven by a variety of interacting factors. Furthermore, the prediction of cancer metastasis is a challenging task due to the variation in parameters and conditions specific to individual patients and mutation subtypes. In this paper, we apply tree-based machine learning algorithms for gene expression data analysis in the estimation of metastatic potentials within a group of 490 breast cancer patients. Tree-based machine learning algorithms including decision trees, gradient boosting, and extremely randomized trees are used to assess the variable importance of different genes in breast cancer metastasis. ighly accurate values were obtained from all three algorithms, with the gradient boosting method having the highest accuracy at 0.8901. The most significant ten genetic variables and fifteen gene functions in metastatic progression were identified. Respective importance scores and biological functions were also cataloged. Key genes in metastatic breast cancer progression include but are not limited to CD8, PB1, and THP-1.

Childhood hydrocephalus is a common disorder in which too much Cerebrospinal Fluid (CSF) accumulates within the ventricles (fluid-containing spaces) of the brain and is usually the-ted by cerebrospinal fluid shunting using a ventriculoperitoneal or ventriculoarterial shunts. The most common condition is hydrocephalus, where there is dilation of the ventricular system due to an obstruction in the flow of CSF or decreased absorption of CSF by the arachnoid villi. Shunting of CSF is the treatment of choice in childhood hydrocephalus.

Traditional preoperative assessment tools use patients’ comorbidities to predict surgical outcomes, however, some functional, social and behavioral factors are known to predict surgical outcomes. Capturing functional, social and behavioral factors by incorporating patient reported measures (PROMs) into preoperative practice may be responsive to perioperative management and contribute to improved outcomes. We developed a preoperative PROM tool to identify functional, social, and behavioral factors. We describe the development and implementation of the tool as a health system quality initiative. We also report the results of the PROMs among preoperative surgical patients. In our survey of 162 patients with mean age of 65, 53% were female, 29% were undergoing orthopedic surgery 12% were undergoing urologic surgery. 56% of the patients had at least one or more deficits in social or functional domain. The most common deficit was with ADLs with higher rate of deficit with advanced age. Implementation of a systematic assessment of functional and social determinants to improve processes of care in the preoperative setting is feasible. The majority of preoperative patients had at least one deficit and if identified preoperatively, appropriate interventions can be offered through well-designed intervention algorithms.