RESUMO
Background: Recently, it was defined that the sellar barrier entity could be identified as a predictor of cerebrospinal fluid (CSF) intraoperative leakage. The aim of this study is to validate the application of the sellar barrier concept for predicting intraoperative CSF leak in endoscopic endonasal surgery for pituitary adenomas with a machine learning approach. Methods: We conducted a prospective cohort study, from June 2019 to September 2020: data from 155 patients with pituitary subdiaphragmatic adenoma operated through endoscopic approach at the Division of Neurosurgery, Università degli Studi di Napoli "Federico II," were included. Preoperative magnetic resonance images (MRI) and intraoperative findings were analyzed. After processing patient data, the experiment was conducted as a novelty detection problem, splitting outliers (i.e., patients with intraoperative fistula, n = 11/155) and inliers into separate datasets, the latter further separated into training (n = 115/144) and inlier test (n = 29/144) datasets. The machine learning analysis was performed using different novelty detection algorithms [isolation forest, local outlier factor, one-class support vector machine (oSVM)], whose performance was assessed separately and as an ensemble on the inlier and outlier test sets. Results: According to the type of sellar barrier, patients were classified into two groups, i.e., strong and weak barrier; a third category of mixed barrier was defined when a case was neither weak nor strong. Significant differences between the three datasets were found for Knosp classification score (p = 0.0015), MRI barrier: strong (p = 1.405 × 10-6), MRI barrier: weak (p = 4.487 × 10-8), intraoperative barrier: strong (p = 2.788 × 10-7), and intraoperative barrier: weak (p = 2.191 × 10-10). We recorded 11 cases of intraoperative leakage that occurred in the majority of patients presenting a weak sellar barrier (p = 4.487 × 10-8) at preoperative MRI. Accuracy, sensitivity, and specificity for outlier detection were 0.70, 0.64, and 0.72 for IF; 0.85, 0.45, and 1.00 for LOF; 0.83, 0.64, and 0.90 for oSVM; and 0.83, 0.55, and 0.93 for the ensemble, respectively. Conclusions: There is a true correlation between the type of sellar barrier at MRI and its in vivo features as observed during endoscopic endonasal surgery. The novelty detection models highlighted differences between patients who developed an intraoperative CSF leak and those who did not.
RESUMO
OBJECTIVE: At present, several strategies for preventing neuromuscular pain in Type 2 Diabetes Mellitus (T2DM) have been investigated. Recently, findings on genetic variants associated with adverse events to statin-based therapy have been reported. The study aimed at measuring whether Pharmacogenomics (PGx) profile can affect neuromuscular pain in patients carrying T2DM and cardiovascular diseases. An extensive panel of 5 polymorphisms on 4 candidate genes, previously validated as significant markers related to Sulphonylureas and Glitinides (SU-G) plus Simvastatin neuromuscular toxicity, is herein analyzed and discussed. PATIENTS AND METHODS: We genotyped 76 T2DM patients carrying cardiovascular dyscrasia undergone anti-diabetic and anti-cholesterolemic polypharmacy. 35 subjects out of the total received concurrent SU-G and Statin-based therapy. Candidate variants consisted of drug transporters, such as Solute Carrier Organic 1B1 (SLCO1B1) Val174Ala ATP-binding cassette subfamily B member (ABCB1), subfamily C member 8 (ABCC8), and drug biotransformers of Cytochrome P450 Family (CYP) including CYP2C9*2 CYP2C9*3 CYP2C8*3, and CYP3A4*22. Moreover, we also focused on an early outline evaluation of the genotyping costs and benefits. RESULTS: 6 out of 35 patients treated with SU-G plus statins (17.1% experienced adverse neuropathy events). Pharmacogenomics analysis showed a lack of any correlation between candidate gene polymorphisms and toxicity, except for the SLCO1B1 T521C allele; 14.3% of patients had a high risk for grade >2 neuromuscular pain (Odds Ratio [OR] 2.61.95% CI 0.90-7.61, p=0.03). CONCLUSIONS: The clinical polymorphism effectiveness outlined therein will be assured by diagnostic improvements suitable for driving treatment decisions. In light of our experimental results and literature data, the analysis of the SLCO1B1 T521C variant will allow clinicians to take advantage from a better treatment planned for their patients in order to minimize neuromuscular pain and maximize benefits.
Assuntos
Doenças Cardiovasculares/genética , Diabetes Mellitus Tipo 2/genética , Transportador 1 de Ânion Orgânico Específico do Fígado/genética , Dor/genética , Doenças Cardiovasculares/diagnóstico , Doenças Cardiovasculares/tratamento farmacológico , DNA/genética , Diabetes Mellitus Tipo 2/diagnóstico , Diabetes Mellitus Tipo 2/tratamento farmacológico , Feminino , Genótipo , Humanos , Hipoglicemiantes/efeitos adversos , Hipoglicemiantes/uso terapêutico , Masculino , Pessoa de Meia-Idade , Dor/diagnóstico , Dor/tratamento farmacológico , Medição da Dor , Farmacogenética , Polimorfismo de Nucleotídeo Único/genética , Sinvastatina/efeitos adversos , Sinvastatina/uso terapêutico , Compostos de Sulfonilureia/efeitos adversos , Compostos de Sulfonilureia/uso terapêuticoRESUMO
OBJECTIVE: Current precision medicine approaches offer powerful tools to optimize medication regimens; however, the potential impact of these tools in cancer patients with multiple drug treatments has not fully appreciated yet. Here we describe a planning project scheduled to start in the next six months. PATIENTS AND METHODS: The overall endpoint of this project is to explore the potential association between the presence of individual genetic profile and severe toxicity rates in so-called "frail" cancer patients, using a nested case-control study design. The pilot study includes the detection of the individual pharmacogenetic profile of 150 (cases), prospect enrolled cancer "frail" patients, and 150 (control) retrospectively paired enrolled individuals. Methods for addressing the primary endpoint include: (a) Evaluation of cost-effectiveness analysis by recording QALY criteria; (b) Data recording by a brief self-administered questionnaire used to evaluate the adherence of a patient's tests and the impact of this genotyping on the patient's adverse drug reactions (ADR); (c) A sample size of paired (for age, gender, education, social status, geriatric syndromes, number of medications and comorbidities) 150 (cases) and 150 (controls); (d) Genotyping method choice by current widely diffuse platforms. RESULTS: The investigators believe that genotype screening and the management of the overall cost of health care personalized therapy has the potential to reduce the health care costs of the Italian national health system (SSN). CONCLUSIONS: Finally, the innovative issue of this project is to advocate the creation of a new model of the co-operative team (Physicians, pharmacist, geneticist and lab manager) that join for planning the most appropriated personalized therapy for their patient.