A Machine Learning Model to Predict Length of Stay and Mortality among Diabetes and Hypertension Inpatients.

Background and Objectives: Taiwan is among the nations with the highest rates of Type 2 Diabetes Mellitus (T2DM) and Hypertension (HTN). As more cases are reported each year, there is a rise in hospital admissions for people seeking medical attention. This creates a burden on hospitals and affects the overall management and administration of the hospitals. Hence, this study aimed to develop a machine learning (ML) model to predict the Length of Stay (LoS) and mortality among T2DM and HTN inpatients. Materials and Methods: Using Taiwan's National Health Insurance Research Database (NHIRD), this cohort study consisted of 58,618 patients, where 25,868 had T2DM, 32,750 had HTN, and 6419 had both T2DM and HTN. We analyzed the data with different machine learning models for the prediction of LoS and mortality. The evaluation was done by plotting descriptive statistical graphs, feature importance, precision-recall curve, accuracy plots, and AUC. The training and testing data were set at a ratio of 8:2 before applying ML algorithms. Results: XGBoost showed the best performance in predicting LoS (R2 0.633; RMSE 0.386; MAE 0.123), and RF resulted in a slightly lower performance (R2 0.591; RMSE 0.401; MAE 0.027). Logistic Regression (LoR) performed the best in predicting mortality (CV Score 0.9779; Test Score 0.9728; Precision 0.9432; Recall 0.9786; AUC 0.97 and AUPR 0.93), closely followed by Ridge Classifier (CV Score 0.9736; Test Score 0.9692; Precision 0.9312; Recall 0.9463; AUC 0.94 and AUPR 0.89). Conclusions: We developed a robust prediction model for LoS and mortality of T2DM and HTN inpatients. Linear Regression showed the best performance for LoS, and Logistic Regression performed the best in predicting mortality. The results showed that ML algorithms can not only help healthcare professionals in data-driven decision-making but can also facilitate early intervention and resource planning.

Correlation between Post-Thaw Spermatozoa Quality of the Endangered Javan Banteng with OPN Gene Expression.

The role of ex situ conservation facilities or captivity through captive breeding programs is essential in the conservation of the endangered Javan banteng. The development of semen cryopreservation may assist on one side of the conservation plan. However, the male Javan banteng reproductive capability must be considered as it influences the targeted outputs. Studying the potential biomarker for fertility such as osteopontin gene expression is also expected to help predict male fertility. Therefore, this study aimed to analyze the quality of spermatozoa after thawing to help predict the male reproductive capability of Javan banteng. Furthermore, this study investigated the potential role of osteopontin gene expression in male Javan banteng fertility. A positive reinforcement approach was used to accustom the male and female animals as we focused on establishing a collection procedure using neither sedation nor anaesthesia. Semen samples were collected at Taman Safari Indonesia, Bogor, in accordance with the female banteng receptivity. Semen samples were then evaluated and then cryopreserved under field conditions. Our study showed the different predicted reproductive capability of the Javan banteng based on the post-thaw spermatozoa quality, which showed significant differences. The OPN gene showed positive correlations with the progressive motility (r = 0.711, p = 0.048), viability (r = 0.822, p = 0.012), and acrosomal integrity (r = 0.665, p = 0.072) of Javan banteng spermatozoa after thawing. Our study demonstrated the predicted Javan banteng reproductive capability based on various post-thaw spermatozoa variables. This finding is also the first report on the OPN gene potential to be developed as the assessment tool of post-thaw spermatozoa quality of the male Javan banteng. The findings in our study may help give recommendations for future breeding programs, especially in the ex situ conservation sites.

Establishment of semen collection technique using electroejaculator and semen cryopreservation of Javan leopard (Panthera pardus melas Cuvier, 1809).

BACKGROUND AND AIM: The Javan leopard (Panthera pardus melas Cuvier, 1809) is a subspecies of Panthera pardus spp., spread across the African and Asian regions. Information on reproductive aspects is crucial for wild animals, including the Javan leopard. In this study, we aimed to developelectroejaculator (EE) techniques and evaluate cryopreservation success in Javan leopard semen. MATERIALS AND METHODS: The semen of four adult Javan leopards was collected once a week using EE. Placement of the EE probe in the rectum was performed after ultrasound imaging (ultrasonography) to determine the prostate body location. The semen obtained was then evaluated macroscopically and microscopically. Three Javan leopards were used for cryopreservation. The ejaculate was divided into two parts [i.e., one part diluted with AndroMed® (Minitüb, Tiefenbach, Germany) and the other part with Steridyl®(Minitüb, Tiefenbach, Germany)] at a 1:1 ratio immediately after collection and evaluation. The semen was then packed in a 0.25 mL MiniStraw® (Minitüb, Tiefenbach, Germany) then equilibrated at 4°C for 2 h. After equilibration, the straw was then frozen in liquid nitrogen vapor. Frozen semen was then stored in containers until further evaluation. RESULTS: The results showed that ejaculation response occurred at all levels of stimulation, while erections did not always occur. The fastest ejaculation and erection occurred at the fourth voltage. The macroscopic evaluation showed that the semen volume was 0.80±0.26 mL, cloudy white, pH 7.44±0.14, and with watery semen consistency. The microscopic evaluation showed that the sperm motility was 66.98±0.39%, with sperm viability of 75.6±1.79%. Sperm concentration was 62.17±46.95×106 mL-1 with a total concentration of 42.14±23.51×106 cells. Normal sperm morphology is only 40.72±6.26%. CONCLUSION: This study concluded that the development of a semen collection technique using an EE preceded by imaging of the EE probe location using ultrasound was effective for the ejaculation of Javan leopards. The characteristics of the semen of the Javan leopard showed moderate semen volume, sperm motility, and viability. Javan leopard showed low sperm concentration and normal sperm morphology.