Development and validation of a machine learning ASA-score to identify candidates for comprehensive preoperative screening and risk stratification.

OBJECTIVE: The ASA physical status (ASA-PS) is determined by an anesthesia provider or surgeon to communicate co-morbidities relevant to perioperative risk. Assigning an ASA-PS is a clinical decision and there is substantial provider-dependent variability. We developed and externally validated a machine learning-derived algorithm to determine ASA-PS (ML-PS) based on data available in the medical record. DESIGN: Retrospective multicenter hospital registry study. SETTING: University-affiliated hospital networks. PATIENTS: Patients who received anesthesia at Beth Israel Deaconess Medical Center (Boston, MA, training [n = 361,602] and internal validation cohorts [n = 90,400]) and Montefiore Medical Center (Bronx, NY, external validation cohort [n = 254,412]). MEASUREMENTS: The ML-PS was created using a supervised random forest model with 35 preoperatively available variables. Its predictive ability for 30-day mortality, postoperative ICU admission, and adverse discharge were determined by logistic regression. MAIN RESULTS: The anesthesiologist ASA-PS and ML-PS were in agreement in 57.2% of the cases (moderate inter-rater agreement). Compared with anesthesiologist rating, ML-PS assigned more patients into extreme ASA-PS (I and IV), (p < 0.01), and less patients in ASA II and III (p < 0.01). ML-PS and anesthesiologist ASA-PS had excellent predictive values for 30-day mortality, and good predictive values for postoperative ICU admission and adverse discharge. Among the 3594 patients who died within 30 days after surgery, net reclassification improvement analysis revealed that using the ML-PS, 1281 (35.6%) patients were reclassified into the higher clinical risk category compared with anesthesiologist rating. However, in a subgroup of multiple co-morbidity patients, anesthesiologist ASA-PS had a better predictive accuracy than ML-PS. CONCLUSIONS: We created and validated a machine learning physical status based on preoperatively available data. The ability to identify patients at high risk early in the preoperative process independent of the provider's decision is a part of the process we use to standardize the stratified preoperative evaluation of patients scheduled for ambulatory surgery.

Distributed Min-Max Learning Scheme for Neural Networks With Applications to High-Dimensional Classification.

In this article, a novel learning methodology is introduced for the problem of classification in the context of high-dimensional data. In particular, the challenges introduced by high-dimensional data sets are addressed by formulating a L1 regularized zero-sum game where optimal sparsity is estimated through a two-player game between the penalty coefficients/sparsity parameters and the deep neural network weights. In order to solve this game, a distributed learning methodology is proposed where additional variables are utilized to derive layerwise cost functions. Finally, an alternating minimization approach developed to solve the problem where the Nash solution provides optimal sparsity and compensation through the classifier. The proposed learning approach is implemented in a parallel and distributed environment through a novel computational algorithm. The efficiency of the approach is demonstrated both theoretically and empirically with nine data sets.

2,5-Diaryloxadiazoles and their precursors as novel inhibitors of cathepsins B, H and L.

High levels of cathepsins indicated in various pathological conditions like arthritis, cancer progressions, and atherosclerosis explains the need to explore potential inhibitors of these proteases which can be of great therapeutic significance. We, in the present work, report the synthesis of some 2,5-diaryloxadiazoles from N-subsitutedbenzylidenebenzohydrazides. The synthesized compounds were screened for their inhibitory potential on cathepsins B, H and L. Structure Activity Relationship studies show that 2,5-diaryloxadiazoles were less inhibitory than their precursors. 1i and 2k have been found to be most inhibitory to cathepsins B and L. Their Ki values have been calculated as 11.38×10(-8)M and 66.4×10(-8)M for cathepsin B and 4.2×10(-9)M and 47.31×10(-9)M for cathepsin L, respectively. However, cathepsin H activity was maximally inhibited by compounds, 1e and 2c with Ki values of 4.4×10(-7)M and 5.6×10(-7)M, respectively. Enzyme kinetic studies suggest that these compounds are competitive inhibitors to the enzymes. The results have been compared with docking results obtained using iGemDock.

Conversion of 2'-substituted chalcones in the presence of BSA as evidenced by ¹H NMR studies.

The emergence of albumin as a biocatalyst has created continuous interest of researchers for its application not only in the field of asymmetric oxidations and reductions but also in chemical reactions such as additions, condensations and eliminations. In the present work we report the cyclization reactions in presence of an albumin protein, Bovine Serum Albumin (BSA). The work is focused on cyclization of 2'-hydroxychalcone and 2'-aminochalcone to flavanones and azaflavanone, respectively. The results are supported by (1)H NMR studies.

Heat and moisture exchange devices for patients undergoing total laryngectomy.

Patients undergoing total laryngectomy face the challenge of an altered anatomy with the resultant changes in quality of life and significant requirements for post-operative care. Increased production of secretions and sputum, the need for ongoing suctioning, and the formation of stomal crusting require meticulous post-operative care. The use of Heat and Moisture Exchange (HME) devices has been shown to decrease the effect of these factors. This article describes the nature of these devices and their use. The literature is reviewed regarding the long term benefits and new data are presented suggesting an immediate post-operative benefit as well. Finally, costs and other considerations for successful use of HME devices are presented.

Hand-made cloned goat (Capra hircus) embryos­a comparison of different donor cells and culture systems.

Nuclear transfer is a very effective method for propagation of valuable, extinct, and endangered animals. Hand-made cloning (HMC) is an efficient alternative to the conventional micromanipulator-based technique in some domestic species. The present study was carried out for the selection of suitable somatic cells as a nuclear donor and development of an optimum culture system for in vitro culture of zona-free goat cloned embryos. Cleavage and blastocyst rates were observed 72.06 ± 2.94% and 0% for fresh cumulus cells, 81.95 ± 3.40% and 12.74 ± 2.12% for cultured cumulus cells, and 92.94 ± 0.91% and 23.78 ± 3.33% for fetal fibroblast cells, respectively. There was a significant (p < 0.05) increase in blastocyst production in goats when cultured on a flat surface (FS) (23.78 ± 3.33 %) than well of wells (WOW) (15.84 ± 2.12 %) and microdrops (MD) (0.7 ± 0.7%). Furthermore, cleavage and blastocyst production rates were significantly (p < 0.05) more in the WOW (15.84 ± 2.12%) than the MD (0.7 ± 0.7%) system. The quality of HMC blastocysts was studied by differential staining. Genetic similarity was confirmed by polymerase chain reaction (PCR)-based amplification of the second exon of the MHC class II DRB gene, which gave similar bands in electrophoresis (286 bp) both in cloned embryos and donor cells. In conclusion, the present study describes that the fetal fibroblast cell is a suitable candidate as nuclear donor, and the flat surface culture system is suitable for zona-free blastocyst development by the hand-made cloning technique in the goat.

Cyclosporine in the treatment of severe steroid refractory ulcerative colitis: a retrospective analysis of 24 cases.

BACKGROUND: Cyclosporine A (CsA) has been found to be the first successful therapy used in the recovery of patients with steroid-refractory ulcerative colitis (UC). However, the long-term benefits of cyclosporine remain questionable. We report our results on the use of CsA in patients with severe steroid-refractory UC. METHODS: The records of all patients with steroid refractory UC treated with CsA from January 2003 to December 2007 were reviewed. Demographics, clinical characteristics of the disease, responsiveness to CsA, complications arising from the treatment and the need for surgery were recorded for all patients. RESULTS: Of 146 admissions of severe UC, 24 patients who were steroid refractory (mean age 41.7 years; 11 men) received intravenous cyclosporine (4 mg/kg/day) for mean of 6.63 days (range 1-7), followed by oral CsA for a period of 3 months. All patients had failed to respond to intravenous hydrocortisone given for 7 days. Four patients required a colectomy immediately, three of whom failed to respond to CsA, and one had convulsions following drug administration. Nineteen of the 24 patients (79%), in whom a colectomy was avoided during the early stages of their treatment, were followed up for a mean of approximately 38 months (range 12-62 months). Three patients required surgery on follow up; one was operated at day 94, another in the second year and one in the third year. Overall, 16 of 24 patients (67%) remained colectomy-free. The main side-effects observed included infections, tremors, paresthesias, headache, hypertension, hypertrichosis and peripheral neuropathy. Three of seven patients who had to undergo surgery died within 2 weeks. CONCLUSIONS: Our study shows that surgery can be avoided in two-thirds of patients with steroid refractive severe UC. However, the drug toxicity and mortality are significant.