Erectile dysfunction (ED) affects millions of men worldwide. Men with ED generally complain failure to attain or maintain an adequate erection during sexual activity. The prevalence of ED is strongly correlated with age, affecting about 40% of men at age 40 and nearly 70% at age 70. A variety of chronic diseases, including diabetes, ischemic heart disease, congestive heart failure, hypertension, depression, chronic renal failure, obstructive sleep apnea, prostate disease, gout, and sleep disorder, were reported to be associated with ED. In this study, data retrieved from a subset of the National Health Insurance Research Database (NHIRD) of Taiwan were used for designing the clinical decision support system (CDSS) for predicting ED incidences in men. The positive cases were male patients aged 20-65 who were diagnosed with ED between Jan. 2000 and Dec. 2010 confirmed by at least 3 outpatient visits or at least one inpatient visit, while the negative cases were randomly selected from the database without a history of ED and were frequency (1:1), age, and index year matched with the ED patients. Data of a total of 2,832 ED patients and 2,832 non-ED patients, each consisting of 41 features including index age, 10 comorbidities, and 30 other comorbidity-related variables, were retrieved for designing the predictive models. Integrated genetic algorithm (GA) and support vector machine (SVM) was adopted to design the CDSSs with 2 experiments of independent training and testing (ITT) conducted to verify their effectiveness. In the 1st ITT experiment, data extracted from Jan. 2000 till Dec. 2005 (61.51%, 1,742 positive cases and 1,742 negative cases) were used for training and validating and the data retrieved from Jan. 2006 till Dec. 2010 were used for testing (38.49%); whereas in the 2nd ITT experiment, data in the training set (77.78%) were extracted from Jan. 2000 till Dec. 2007 and those in the testing set (22.22%) were retrieved afterward. Tenfold cross validation and 3 different objective functions were adopted for obtaining the optimal models with best predictive performance in the training phase. The testing results show that the CDSSs achieved a predictive performance with accuracy, sensitivity, specificity, g-mean, and area under ROC curve (AUC) of 74.72-76.65%, 72.33-83.76%, 69.54-77.10%, 0.7468-0.7632, and 0.766-0.817, respectively. In conclusion, the CDSSs designed based on cost-sensitive objective functions as well as salient comorbidity-related features achieve satisfactory predictive performance for predicting ED incidences.

A model with capability for precisely predicting readmission is a target being pursued worldwide. The objective of this study is to design predictive models using artificial intelligence methods and data retrieved from the National Health Insurance Research Database of Taiwan for identifying high-risk pneumonia patients with 30-day all-cause readmissions. An integrated genetic algorithm (GA) and support vector machine (SVM), namely IGS, were used to design predictive models optimized with three objective functions. In IGS, GA was used for selecting salient features and optimal SVM parameters, while SVM was used for constructing the models. For comparison, logistic regression (LR) and deep neural network (DNN) were also applied for model construction. The IGS model with AUC used as the objective function achieved an accuracy, sensitivity, specificity, and area under ROC curve (AUC) of 70.11%, 73.46%, 69.26%, and 0.7758, respectively, outperforming the models designed with LR (65.77%, 78.44%, 62.54%, and 0.7689, respectively) and DNN (61.50%, 79.34%, 56.95%, and 0.7547, respectively), as well as previously reported models constructed using thedata of electronic health records with an AUC of 0.71–0.74. It can be used for automatically detecting pneumonia patients with a risk of all-cause readmissions within 30 days after discharge so as to administer suitable interventions to reduce readmission and healthcare costs.

The quantitative prediction of the SYNTAX score for cardiovascular artery disease patients using the inverse problem algorithm (IPA) technique in artificial intelligence was explored in this study. A 29-term semi-empirical formula was defined according to seven risk factors: (1) age, (2) mean arterial pressure, (3) body surface area, (4) pre-prandial blood glucose, (5) low-density-lipoprotein cholesterol, (6) Troponin I, and (7) C-reactive protein. Then, the formula was computed via the STATISTICA 7.0 program to obtain a compromised solution for a 405-patient dataset with a specific loss function [actual-predicted]² as low as 3.177, whereas 0.0 implies a 100% match between the prediction and observation via “the lower, the better” principle. The IPA technique first created a data matrix [405 × 29] from the included patients’ data and then attempted to derive a compromised solution of the column matrix of 29-term coefficients [29 × 1]. The correlation coefficient, r², of the regression line for the actual versus predicted SYNTAX score was 0.8958, showing a high coincidence among the dataset. The follow-up verification based on another 105 patients’ data from the same group also had a high correlation coefficient of r² = 0.8304. Nevertheless, the verified group’s low derived average AT (agreement) (AT_avg = 0.308 ± 0.193) also revealed a slight deviation between the theoretical prediction from the STATISTICA 7.0 program and the grades assigned by clinical cardiologists or interventionists. The predicted SYNTAX scores were compared with earlier reported findings based on a single-factor statistical analysis or scanned images obtained by sonography or cardiac catheterization. Cardiologists can obtain the SYNTAX score from the semi-empirical formula for an instant referral before performing a cardiac examination.

This study optimized the ultrasound image of carotid artery stenosis using Taguchi dynamic analysis and an indigenous water phantom. Eighteen combinations of seven essential factors of the ultrasound scan facility were organized according to Taguchi’s L₁₈ orthogonal array. The seven factors were assigned as follows: (1) angle of probe; (2) signal gain; (3) resolution vs. speed; (4) dynamic range; (5) XRES; (6) zoom; (7) time gain compensation. An indigenous water phantom was customized to satisfy the quantified need in Taguchi’s analysis. Unlike the conventional dynamic Taguchi analysis, an innovative quantified index, the figure of merit (FOM), was proposed to integrate four specific quality characteristics, namely (i) average difference between the practical scan and theoretically preset area (78.5, 50.2 and 12.6 mm²) of stenosis, (ii) standard deviation of the average, (iii) practical scan’s sensitivity β to various stenosis diameters (10, 8, and 4 mm), and (iv) correlation coefficient r² of the linear regressed sensitivity curve. The highest value (FOM = 0.413) was furnished by the optimal combination of factors on 18 groups under study, yielding high r² and low β or standard deviation values and the best quality of ultrasound images for the further clinical diagnosis. The comparison between FOM and the conventional signal-to-noise (S/N) ratio in Taguchi’s analysis revealed that FOM compiled more quality characteristics that were superior by nature to fulfill the practical need in clinical diagnosis. The alternative choice in ultrasound scan optimization can be based on stenosis diameter variation from a different perspective to be explored in the follow-up study.