Search

Background: The severity of laboratory and imaging finding was found to be inconsistent with clinical symptoms in COVID-19 patients, thereby increasing casualties. As compared to conventional biomarkers, machine learning algorithms can learn nonlinear and complex interactions and thus improve prediction accuracy. This study aimed at evaluating role of biochemical and immunological parameters–based machine learning algorithms for severity indexing in COVID-19. Methods: Laboratory biochemical results of 5715 COVID-19 patients were mined from electronic records including 509 admitted in COVID-19 ICU. Random Forest Classifier (RFC), Support Vector Machine (SVM), Naive Bayesian Classifier (NBC) and K-Nearest Neighbours (KNN) classifier models were used. Lasso regression helped in identifying the most influential parameter. A decision tree was made for subdivided data set, based on randomization. Results: Accuracy of SVM was highest with 94.18% and RFC with 94.04%. SVM had highest PPV (1.00), and NBC had highest NPV (0.95). QUEST modelling ignored age, urea and total protein, and only C-reactive protein and lactate dehydrogenase were considered to be a part of decision-tree algorithm. The overall percentage of correct classification was 78.31% in the overall algorithm with a sensitivity of 87.95% and an AUC of 0.747. Conclusion: C-reactive protein and lactate dehydrogenase being routinely performed tests in clinical laboratories in peripheral setups, this algorithm could be an effective predictive tool. SVM and RFC models showed significant accuracy in predicting COVID-19 severity and could be useful for future pandemics.

Background: The severity of laboratory and imaging finding was found to be inconsistent with clinical symptoms in COVID‑19 patients, thereby increasing casualties. As compared to conventional biomarkers, machine learning algorithms can learn nonlinear and complex interactions and thus improve prediction accuracy. This study aimed at evaluating role of biochemical and immunological parameters–based machine learning algorithms for severity indexing in COVID‑19. Methods: Laboratory biochemical results of 5715 COVID‑19 patients were mined from electronic records including 509 admitted in COVID‑19 ICU. Random Forest Classifier (RFC), Support Vector Machine (SVM), Naive Bayesian Classifier (NBC) and K‑Nearest Neighbours (KNN) classifier models were used. Lasso regression helped in identifying the most influential parameter. A decision tree was made for subdivided data set, based on randomization. Results: Accuracy of SVM was highest with 94.18% and RFC with 94.04%. SVM had highest PPV (1.00), and NBC had highest NPV (0.95). QUEST modelling ignored age, urea and total protein, and only C‑reactive protein and lactate dehydrogenase were considered to be a part of decision‑tree algorithm. The overall percentage of correct classification was 78.31% in the overall algorithm with a sensitivity of 87.95% and an AUC of 0.747. Conclusion: C‑reactive protein and lactate dehydrogenase being routinely performed tests in clinical laboratories in peripheral setups, this algorithm could be an effective predictive tool. SVM and RFC models showed significant accuracy in predicting COVID‑19 severity and could be useful for future pandemics. [ABSTRACT FROM AUTHOR]

Background: LDL-C is a strong risk factor for cardiovascular disorders. The formulas used to calculate LDL-C showed varying performance in different populations. Machine learning models can study complex interactions between the variables and can be used to predict outcomes more accurately. The current study evaluated the predictive performance of three machine learning models—random forests, XGBoost, and support vector Rregression (SVR) to predict LDL-C from total cholesterol, triglyceride, and HDL-C in comparison to linear regression model and some existing formulas for LDL-C calculation, in eastern Indian population. Methods: The lipid profiles performed in the clinical biochemistry laboratory of AIIMS Bhubaneswar during 2019–2021, a total of 13,391 samples were included in the study. Laboratory results were collected from the laboratory database. 70% of data were classified as train set and used to develop the three machine learning models and linear regression formula. These models were tested in the rest 30% of the data (test set) for validation. Performance of models was evaluated in comparison to best six existing LDL-C calculating formulas. Results: LDL-C predicted by XGBoost and random forests models showed a strong correlation with directly estimated LDL-C (r = 0.98). Two machine learning models performed superior to the six existing and commonly used LDL-C calculating formulas like Friedewald in the study population. When compared in different triglycerides strata also, these two models outperformed the other methods used. Conclusion: Machine learning models like XGBoost and random forests can be used to predict LDL-C with more accuracy comparing to conventional linear regression LDL-C formulas. [ABSTRACT FROM AUTHOR]

Abstract Background The complications associated with abdominal testis include torsion, rupture, and malignant transformation. Case presentation A 40-year-old man presented with complaints of left-sided abdominal mass and abdominal pain. On contrast-enhanced computed tomography (CECT), there was a well-defined heterogeneously enhancing mass lesion in the lower abdomen with calcification showing fistulous communication to the adjacent ileal loops. The lesion was seen supplied by the left gonadal artery raising suspicion for testicular origin. On performing a scrotal ultrasound, the left testis was found absent. A radiological diagnosis of abdominal testicular neoplasm was made. Conclusions Histopathological examination proved the lesion to be a germ cell tumor, consistent with seminoma.

Hashimoto's encephalopathy (HE) is a rare neuroendocrine disorder, and there are no reports regarding anesthetic implications in a patient diagnosed with HE. These patients can have a plethora of systemic manifestations involving cardiovascular, respiratory, renal, gastrointestinal, hematologic, and central nervous systems. Once diagnosed, meticulous preoperative assessment is essential to rule out systemic involvement and to reduce the perioperative morbidity. Perioperative steroid therapy, neuromonitoring in the perioperative period, opioid free analgesia, and avoidance of nephrotoxic drugs are of paramount importance in the management of such patients. Awareness of the clinical condition and extreme vigilance can detect relapses in the perioperative period. Thus, a meticulous preoperative assessment, balanced anesthesia, perioperative neuromonitoring, and steroid therapy are essential to reduce the perioperative morbidity. [ABSTRACT FROM AUTHOR]

The aim of this paper is to review the literature on suicide attempts in Malaysia. PsycINFO, PubMed, and Medline databases from 1845 to 2012 and detailed manual search of local official reports from the Ministry of Health and the Malaysian Psychiatric Association and unpublished dissertations from 3 local universities providing postgraduate psychiatric training were included in the current review. A total of 38 studies on suicide attempts in Malaysia were found and reviewed. Twenty-seven (76%) of the studies on suicide attempts were descriptive studies looking at sociodemographic data, psychiatric illnesses, and methods and reasons for suicide attempts. No study has been conducted on treatment and interventions for suicide attempts and the impact of culture was rarely considered. The review showed that in order for researchers, clinicians, and public health policy makers to obtain a better understanding of suicide attempts in Malaysia, more systematic and empirically stringent methodologies and research frameworks need to be used.

The present study evaluated the psychometric properties and factor structure of the Satisfaction With Life Scale (SWLS) in a sample of clinical outpatients in Malaysia. The SWLS is a measure designed to assess subjective life satisfaction. Four hundred eighty-three participants (283 with psychiatric illnesses and 200 with other medical illnesses) completed the SWLS and other self-report instruments. Results of the EFA and CFA supported the fit for the one-factor model as the best-fitting model. The internal consistency of the SWLS (α=0.86) was found to be high. Correlational analyses showed that SWLS had adequate concurrent validity. Scores on SWLS, which differentiated psychiatric patients and medical patients, supported criterion validity. The logistic regression analyses showed good discriminative validity of SWLS. The SWLS is a reliable and valid instrument to measure the satisfaction with life among psychiatry and clinical outpatients in Malaysia., (Copyright © 2014 Elsevier Inc. All rights reserved.)