Experimental and Computational Approaches for the Classification and Correlation of Temperament (Mizaj) and Uterine Dystemperament (Su’-I-Mizaj Al-Rahim) in Abnormal Vaginal Discharge (Sayalan Al-Rahim) Based on Clinical Analysis Using Support Vector Machine

Abstract

The temperament (Mizaj) of the body is an essential constituent for health conservancy and diagnosis of several diseases. Hence, general body temperament and uterine dystemperament (Su’-i-Mizaj) with abnormal vaginal discharge (Salayan al-Rahim) need evaluation. In addition, we also applied a computational intelligence technique for enhancing scientific validity to classify the warm-cold and wet-dry temperaments. This trial included a total of 66 participants with a vaginal discharge of reproductive age. Data included demographic characteristics of the participants, symptoms associated with vaginal discharge, women’s general temperament, and symptoms of uterine dystemperament. Correlation between general body temperament and age, abnormal vaginal discharge, and its associated symptoms was also performed. Additionally, we used the Support Vector Machine-Radial Basis Function (SVM-RBF) model to classify the warm-cold and wet-dry temperaments. Warm general temperament was highly prevalent (77.27%), followed by moderate (19.69%) on the warm-cold temperament scale. In wet-dry temperament, moderate general body temperament (50%) was more prevalent. In warm-cold and wet-dry scores, 78.78% and 74.24% had warm and wet uterine dystemperament, respectively. The age and symptoms were correlated with general temperament. A strong positive correlation was found between warm general temperament and warm dystemperament of the uterus (r = 0.40, p < 0.009). In addition, our SVM-RBF CV-5 classification model achieved the highest accuracy (99.2%). Our results showed that vaginal discharge is more common in warm general temperament and warm-wet dystemperament of the uterus. The same has been proven by computational intelligence. Nevertheless, vaginal discharge can also happen in normal and other temperaments.

Therapeutic Efficacy of a Formulation Prepared with Linum usitatissimum L., Plantago ovata Forssk., and Honey on Uncomplicated Pelvic Inflammatory Disease Analyzed with Machine Learning Techniques

“…Hence, we evaluated and compared the efficacy of the vaginal application of a formulation prepared with L. usitatissimum , P. ovata , and honey [ 12 ] on uPID with standard drugs, doxycycline, and metronidazole. In addition, we also used the same machine learning models [ 49 , 50 , 51 , 52 , 53 , 54 ] including Decision Tree (DT) [ 55 , 56 , 57 ], Random Forest (RF) [ 58 , 59 ], Logistic Regression (LR), and AdaBoost (AB) with three cross-validation models including 2-fold, 5-fold, and 10-fold to classify the standard and pessary groups. The main contributions of this study are given below: The pessary of psyllium and linseed with honey is beneficial for PID but has not been validated to date.…”

BCNet: A Deep Learning Computer-Aided Diagnosis Framework for Human Peripheral Blood Cell Identification

“…The evaluation results shown in the result section are achieved over a 5-fold cross-validation test to investigate the reliability and feasibility of the proposed BCNet. The definition of the evaluation metrics is summarized in Equations (1)–(7) [ 20 , 59 , 60 , 61 , 62 , 63 ]. True positive (TP), true negative (TN), false positive (FP), and false negative (FN) are derived via a multi-class confusion matrix for each fold test.…”

A Novel Smart Belt for Anxiety Detection, Classification, and Reduction Using IIoMT on Students’ Cardiac Signal and MSY

“…Therefore, we considered four significant evaluation measures to capture different perspectives of outcomes. The chosen measures quantify the effectiveness of the classification model [ 54 , 55 , 56 ]. Here, we have discussed the basic knowledge to understand how various performance metrics such as True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), sensitivity, and specificity, are calculated.…”