Metabolomics by NMR Combined with Machine Learning to Predict Neoadjuvant Chemotherapy Response for Breast Cancer.

Neoadjuvant chemotherapy (NACT) is offered to patients with operable or inoperable breast cancer (BC) to downstage the disease. Clinical responses to NACT may vary depending on a few known clinical and biological features, but the diversity of responses to NACT is not fully understood. In this study, 80 women had their metabolite profiles of pre-treatment sera analyzed for potential NACT response biomarker candidates in combination with immunohistochemical parameters using Nuclear Magnetic Resonance (NMR). Sixty-four percent of the patients were resistant to chemotherapy. NMR, hormonal receptors (HR), human epidermal growth factor receptor 2 (HER2), and the nuclear protein Ki67 were combined through machine learning (ML) to predict the response to NACT. Metabolites such as leucine, formate, valine, and proline, along with hormone receptor status, were discriminants of response to NACT. The glyoxylate and dicarboxylate metabolism was found to be involved in the resistance to NACT. We obtained an accuracy in excess of 80% for the prediction of response to NACT combining metabolomic and tumor profile data. Our results suggest that NMR data can substantially enhance the prediction of response to NACT when used in combination with already known response prediction factors.

Pharmacist interventions in high-risk obstetric inpatient unit: a medication safety issue.

OBJECTIVES: The aim of this study was to report number, type and severity of prescribing errors and pharmacist interventions in high-risk pregnant and postpartum women. DESIGN: A prospective cross-sectional, observational study. SETTING: A high-risk obstetric inpatient unit of a Women's Hospital in Brazil. PARTICIPANTS: About 1826 electronic prescriptions for 549 women in the high-risk obstetrics inpatient unit were included. INTERVENTIONS: When the pharmacist detected potential prescribing errors, interventions were suggested. MAIN OUTCOME MEASURES: Prescriptions were evaluated by clinical pharmacist to identify the type, frequency and severity of prescribing errors and rate of clinical pharmacist intervention acceptance in a high-risk obstetric inpatient. RESULTS: A total of 1826 prescriptions were reviewed with 128 errors (7.0%). The most frequent errors were drug interaction (43.8%), incorrect frequency (21.5%) and improper dose (13.1%). One-hundred and sixty-eight interventions were made by pharmacists, 98.8% of which were accepted by prescribers. Higher maternal age (OR 1.0 (95%CI 1.0-1.1)), higher number of prescribed medications (OR 1.2 (95%CI 1.1-1.3)), obstetric conditions (OR 2.2 (95%CI 1.4-3.3)) and non-breastfeeding postpartum women (OR 3.9 (95% CI 2.5-6.1)) were the independent factors associated with prescribing errors identified through multivariate analysis. CONCLUSIONS: The most common prescription errors related to drug interactions, incorrect frequency and higher number of prescribed medications. The rate of pharmacist acceptance intervention was high.