Increased Ordering of Potassium Stearate/Stearic Acid/Glyceryl Stearate Confined between Swollen Cross-Linked Poly(acrylic acid).

In this paper, we investigate the phase behavior of a surfactant mixture comprising glyceryl stearate, potassium stearate, and stearic acid, in the presence of Carbopol, a commonly used thickener in personal care products. At low Carbopol concentrations (<0.03%), the surfactant mixture interacted with Carbopol electrostatically, increasing the degree of Carbopol swelling and, consequently, the overall viscosity. However, such an effect diminished as the Carbopol concentration was further increased. At a Carbopol concentration of 0.2%, two types of liquid crystalline surfactant structures, namely, multilamellar vesicles and lamellae, were observed between the swollen Carbopol domains. Although similar types of surfactant structures were present in a much more concentrated surfactant solution having a similar viscosity but without Carbopol, the lamellae in the presence of Carbopol were more ordered and with a larger d spacing. The increased ordering was probably induced by the interactions between the surfactants and Carbopol as the surfactants were confined between the swollen Carbopol domains.

Protective role of acetylcholine and the cholinergic system in the injured heart.

This review explores the roles of the cholinergic system in the heart, comprising the neuronal and non-neuronal cholinergic systems. Both systems are essential for maintaining cardiac homeostasis by regulating the release of acetylcholine (ACh). A reduction in ACh release is associated with the early onset of cardiovascular diseases (CVDs), and increasing evidence supports the protective roles of ACh against CVD. We address the challenges and limitations of current strategies to elevate ACh levels, including vagus nerve stimulation and pharmacological interventions such as cholinesterase inhibitors. Additionally, we introduce alternative strategies to increase ACh in the heart, such as stem cell therapy, gene therapy, microRNAs, and nanoparticle drug delivery methods. These findings offer new insights into advanced treatments for regenerating the injured human heart.

The disruption of NEAT1-miR-125b-5p-SLC1A5 cascade defines the oncogenicity and differential immune profile in head and neck squamous cell carcinoma.

Metabolic reprogramming sustains malignant head and neck squamous cell carcinoma (HNSCC) to overcome stressful microenvironments, and increased glutamine uptake is a common metabolic hallmark in cancers. Since metabolic reprogramming has been recognized as a new therapeutic target for tumor cells, understanding the regulatory axis of glutamine uptake in HNSCC and its potential downstream effects in its pathogenesis of HNSCC would be incredibly beneficial. Bioinformatic analysis of the Cancer Genome Atlas (TCGA)-HNSCC dataset and RNAseq analysis performed on HNSCC indicated that SLC1A5 was the most dysregulated transporter among the seven homologous glutamate or neutral amino acid transporters in the SLC1A family. To further clarify the role of SLC1A5 in HNSCC, we knocked down SLC1A5 expression. This knockdown decelerated cell growth, induced G0/G1 arrest, diminished tumorigenicity, and increased cleavage caspase3, LC3B, and intracellular Fe2+. Inhibitors against apoptosis, autophagy, or ferroptosis rescued the cell viability repressed by SLC1A5 knockdown. SLC1A5 knockdown also suppressed glutamine uptake, enhanced oxidative stress, and increased sensitivity to cisplatin. CRISPR/dCas9-mediated SLC1A5 induction conferred cisplatin resistance and reduced apoptosis, autophagy, and ferroptosis. Reporter assays and western blot data demonstrated that miR-125b-5p targets and attenuates SLC1A5, while the si-NEAT1 increases miR-125b-5p expression. Analysis of the TCGA-HNSCC databases showed concordant upregulation of NEAT1 and downregulation of miR-125b-5p, along with SLC1A5 upregulation in tumors. Analysis of transcriptomic data revealed that tumors harboring higher SLC1A5 expression had significantly lower immune scores in CD8+, monocytes, and dendritic cells, and higher scores in M0 and M1 macrophages. Disruptions in immune modulation, metabolism, and oxidative stress components were associated with SLC1A5 aberrations in HNSCC. This study concludes that the NEAT1/miR-125b-5p/SLC1A5 cascade modulates diverse activities in oncogenicity, treatment efficacy, and immune cell profiles in head and neck/oral carcinoma.

Artificial intelligence prediction of In-Hospital mortality in patients with dementia: A multi-center study.

BACKGROUND: Prediction of mortality is very important for care planning in hospitalized patients with dementia and artificial intelligence has the potential to serve as a solution; however, this issue remains unclear. Thus, this study was conducted to elucidate this matter. METHODS: We identified 10,573 hospitalized patients aged ≥ 45 years with dementia from three hospitals between 2010 and 2020 for this study. Utilizing 44 feature variables extracted from electronic medical records, an artificial intelligence (AI) model was constructed to predict death during hospitalization. The data was randomly separated into 70 % training set and 30 % testing set. We compared predictive accuracy among six algorithms including logistic regression, random forest, extreme gradient boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), multilayer perceptron (MLP), and support vector machine (SVM). Additionally, another set of data collected in 2021 was used as the validation set to assess the performance of six algorithms. RESULTS: The average age was 79.8 years, with females constituting 54.5 % of the sample. The in-hospital mortality rate was 6.7 %. LightGBM exhibited the highest area under the curve (0.991) for predicting mortality compared to other algorithms (XGBoost: 0.987, random forest: 0.985, logistic regression: 0.918, MLP: 0.898, SVM: 0.897). The accuracy, sensitivity, positive predictive value, and negative predictive value of LightGBM were 0.943, 0.944, 0.943, 0.542, and 0.996, respectively. Among the features in LightGBM, the three most important variables were the Glasgow Coma Scale, respiratory rate, and blood urea nitrogen. In the validation set, the area under the curve of LightGBM reached 0.753. CONCLUSIONS: The AI prediction model demonstrates strong accuracy in predicting in-hospital mortality among patients with dementia, suggesting its potential implementation to enhance future care quality.

Initial Investigations into Physician Acceptance of Medical AI: Examining Trust, Resistance, Perceived Job Insecurity, and Usage Intentions.

This study evaluated physicians' attitudes towards medical AI across three Taiwanese hospitals, focusing on constructs of trust, resistance, job insecurity, and adoption willingness, with a survey based on the Dual-factor Model yielding 282 responses and a 94% response rate. Results showed positive trust in AI, low resistance and job insecurity concerns, and a high willingness to adopt AI, indicating a favorable view of AI as a supportive tool rather than a replacement. Key adoption factors were identified as regulatory standards, accuracy, workflow integration, and result clarity, providing valuable insights for future AI development in medicine.

Machine Learning to Predict the Risk of Malnutrition in Hospitalized Patients with Pneumonia and Analysis of Related Prognostic Factor.

This study explored machine learning's potential in predicting the nutritional status and outcomes for pneumonia patients. It focused on 4,368 patients in a Taiwan medical center from Jan 2016 to Feb 2022, excluding ICU cases. The average age was 77.6 years, with 10.2% well-nourished, 76.3% at-risk, and 13.5% malnourished. Machine learning models, particularly LightGBM and XGBoost, showed high accuracy in predicting hospital stays, mortality rates, and readmissions. These findings emphasize the role of data-driven methods in enhancing patient care and managing conditions like pneumonia more effectively.

Enhancing Healthcare Efficiency: Integrating ChatGPT in Nursing Documentation.

Our study at Chi Mei Medical Center introduced "A+ Nurse," a ChatGPT-based LLM tool, into the nursing documentation process to enhance efficiency and accuracy. The tool offers optimized recording and critical reminders, reducing documentation time from 15 to 5 minutes per patient while maintaining record quality. Nurses appreciated the tool's intuitive design and its effectiveness in improving documentation. This successful integration of AI-generated content in healthcare illustrates the potential of AI to streamline processes and improve patient care, setting a precedent for future AI-driven healthcare innovations.

A homeostatic gut-to-brain insulin antagonist restrains neuronally stimulated fat loss.

In C. elegans mechanisms by which peripheral organs relay internal state information to the nervous system remain unknown, although strong evidence suggests that such signals do exist. Here we report the discovery of a peptide of the ancestral insulin superfamily called INS-7 that functions as an enteroendocrine peptide and is secreted from specialized cells of the intestine. INS-7 secretion is stimulated by food withdrawal, increases during fasting and acts as a bona fide gut-to-brain peptide that attenuates the release of a neuropeptide that drives fat loss in the periphery. Thus, INS-7 functions as a homeostatic signal from the intestine that gates the neuronal drive to stimulate fat loss during food shortage. Mechanistically, INS-7 functions as an antagonist at the canonical DAF-2 receptor and functions via FOXO and AMPK signaling in ASI neurons. Phylogenetic analysis suggests that INS-7 bears greater resemblance to members of the broad insulin/relaxin superfamily than to conventional mammalian insulin and IGF peptides. The discovery of an endogenous insulin antagonist secreted by specialized intestinal cells with enteroendocrine functions suggests unexpected and important properties of the intestine and its role in directing neuronal functions.

Fluorinated polymer zwitterions on gold nanoparticles: patterned catalyst surfaces guide interfacial transport and electrochemical CO2 reduction.

We report the use of fluorinated polymer zwitterions to build hybrid systems for efficient CO2 electroreduction. The unique combination of hydrophilic phosphorylcholine and hydrophobic fluorinated moieties in these polymers creates a fractal structure with mixed branched cylinders on the surface of gold nanoparticles (AuNPs). In the presence of these polymers, the CO faradaic efficiency improves by 50-80% in the range of -0.7 V to -0.9 V. The fractal structures have a domain size of ∼3 nm, showing enhanced mass transfer kinetics of CO2 approaching the catalyst surfaces without limiting ion diffusion. The phase-separated hydrophilic and hydrophobic domains offer separated channeling to water and CO2, as confirmed by attenuated total reflectance surface-enhanced infrared absorption spectroscopy (ATR-SEIRAS) and molecule dynamic (MD) simulations. H2O molecules permeate extensively into the polymer layer that adsorbs on zwitterions, forming continuous chains, while CO2 molecules strongly associate with the fluorinated tails of fluorinated polyzwitterions, with oxygen facing the positively charged amine groups. Overall, this coupling of zwitterion and fluorocarbon in a polymer material creates new opportunities for defining microenvironments of metallic nanocatalysts in hybrid structures.

Transplanting mitochondria from gastric epithelial cells reduces the malignancy of gastric cancer.

Mitochondria are essential for energy supplementation and metabolic homeostasis of cancer cells. Using mitochondria transplantation to reduce the malignancy of gastric cancer (GC) cells is herein proposed. In our study normal human gastric mucous epithelium cell line (GES-1) showed a lower mitochondrial membrane potential (MMP) compared to immortalized human vascular endothelial cell line (EAhy 926) and human gastric adenocarcinoma cell line (AGS). The transplantation of GES-1 mitochondria to AGS were confirmed both by confocal microscopy and flow cytometry. After transplanting GES-1 mitochondria, the AGS showed a reduced cell migration, and invasion without affecting cell viability and apoptosis. Investigating the expression of proteins involved in epithelial-mesenchymal-transition (EMT), transplanted GES-1 mitochondria reduced the expression of mesenchymal markers α-SMA, MMP-9, snail, vimentin and N-cadherin, whereas the epithelial markers E-cadherin and clauding-1 were not changed. The proteins implicated in the cell cycle such as cyclin B1 and D1 were decreased. In mice, inoculation with AGS carrying the transplanted GES-1 mitochondria resulted in smaller sized tumors. Further investigating the mitochondrial balance, the transplanted GES-1 mitochondria were more stably preserved compared to endogenous AGS mitochondria. The MMP, ATP production and mitochondrial mass decreased in GES-1 mitochondria and the mitophagic proteins LC3 II and PINK1 were up-regulated. In conclusion the decreased malignancy of AGS was a result of exogenous GES-1 mitochondria transplantation. This suggests for a therapy with low efficiency mitochondria transplantation in the treatment of cancer cells.

Exploring the Charge-Transport and Optical Characteristics of Organic Doublet Radicals: A Theoretical and Experimental Study with Photovoltaic Applications.

Herein, we present a series of stable radicals containing a trityl carbon-centered radical moiety exhibiting interesting properties. The radicals demonstrate the most blue-shifted anti-Kasha doublet emission reported so far with high color purity (full width at half-maximum of 46 nm) and relatively high photoluminescence quantum yields of deoxygenated toluene solutions reaching 31%. The stable radicals demonstrate equilibrated bipolar charge transport with charge mobility values reaching 10-4 cm2/V·s at high electric fields. The experimental results in combination with the results of TD-DFT calculations confirm that the blue emission of radicals violates the Kasha rule and originates from higher excited states, whereas the bipolar charge transport properties are found to stem from the particularity of radicals to involve the same molecular orbital(s) in electron and hole transport. The radicals act as the efficient materials for interlayers, passivating interfacial defects and enhancing charge extraction in PSCs. Consequently, this leads to outstanding performance of PSC, with power conversion efficiency surpassing 21%, accompanied by a remarkable increase in open-circuit voltage and exceptional stability.

The expression of immune co-stimulators as a prognostic predictor of head and neck squamous cell carcinomas and oral squamous cell carcinomas.

Background/purpose: T cells require second immune checkpoint molecules for activation and immune memory after antigen presentation. We found that inducible co-stimulator (ICOS) has been a favorable prognostic factor amongst B7 immune checkpoint co-stimulators (ICSs) families in head and neck squamous cell carcinoma (HNSCC) and oral SCC (OSCC). Materials and methods: This study analyzed the expression of non-B7 tumor necrosis factor (TNF) superfamily ICSs in the Cancer Genome Atlas (TCGA) HNSCC cohort, our OSCC cohort, and TCGA pan-cancer datasets. The correlation in expression, prognosis, and immune status was assessed. Results: The higher expression of CD27, CD30, CD40L, death domain 3 (DR3), and OX40, presumably on the T cell surface, defined better overall survival of HNSCC patients. Besides, CD27, CD30, CD40L, and OX40 were highly correlated with ICOS expression in tumors. CD27, CD40L, and DR3 expression are higher in HPV+ HNSCC tumors than in HPV- tumors. The combined expression level of CD27/OX40 or CD27/CD40L/OX40 enables the potent survival prediction of small, less nodal involvement, early stage, and HPV + tumor subsets. Tumors expressing high CD27, CD30, CD40L, ICOS, and OX40 exhibited enhanced immune cell infiltration. The high correlation in the expression of these ICSs was also noted in the vast majority of tumor types in TCGA datasets. Conclusion: The findings of this study not only confirm the potential of the concordant stimulation of CD27, CD30, CD40L, ICOS, and OX40 as a crucial strategy in cancer immunotherapy but also inspire further exploration into the field, highlighting the promising future of cancer treatment.

Personalized prediction of intradialytic hypotension in clinical practice: Development and evaluation of a novel AI dashboard incorporating risk factors from previous and current dialysis sessions.

BACKGROUND: Intradialytic hypotension (IDH) is one of the most common and critical complications of hemodialysis. Despite many proven factors associated with IDH, accurately predicting it before it occurs for individual patients during dialysis sessions remains a challenge. PURPOSE: To establish artificial intelligence (AI) predictive models for IDH, which consider risk factors from previous and ongoing dialysis to optimize model performance. We then implement a novel digital dashboard with the best model for continuous monitoring of patients' status undergoing hemodialysis. The AI dashboard can display the real-time probability of IDH for each patient in the hemodialysis center providing an objective reference for care members for monitoring IDH and treating it in advance. METHODS: Eight machine learning (ML) algorithms, including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), K Nearest Neighbor (KNN), Light Gradient Boosting Machine (LightGBM), Multilayer Perception (MLP), eXtreme Gradient Boosting (XGBoost), and NaiveBayes, were used to establish the predictive model of IDH to determine if the patient will acquire IDH within 60 min. In addition to real-time features, we incorporated several features sourced from previous dialysis sessions to improve the model's performance. The electronic medical records of patients who had undergone hemodialysis at Chi Mei Medical Center between September 1, 2020 and December 31, 2020 were included in this research. Impact evaluation of AI assistance was conducted by IDH rate. RESULTS: The results showed that the XGBoost model had the best performance (accuracy: 0.858, sensitivity: 0.858, specificity: 0.858, area under the curve: 0.936) and was chosen for AI dashboard implementation. The care members were delighted with the dashboard providing real-time scientific probabilities for IDH risk and historic predictive records in a graphic style. Other valuable functions were appended in the dashboard as well. Impact evaluation indicated a significant decrease in IDH rate after the application of AI assistance. CONCLUSION: This AI dashboard provides high-quality results in IDH risk prediction during hemodialysis. High-risk patients for IDH will be recognized 60 min earlier, promoting individualized preventive interventions as part of the treatment plan. Our approachis believed to promise an excellent way for IDH management.

Feasibility and Preliminary Efficacy of α-Calcium Sulfate Hemihydrate in Socket Preservation: Protocol for a Pilot Randomized Controlled Trial.

BACKGROUND: Tooth extraction procedures often lead to bone resorption, which can have adverse effects on the dimensions of the alveolar ridge. Research has shown that socket preservation techniques using bone graft substitutes can effectively minimize early bone loss in such cases. α-calcium sulfate hemihydrate (α-CSH) has garnered significant attention as a potential bone graft material due to its favorable properties, including osteoconductivity, angiogenic potential, and biocompatibility. Considering these facts, we developed a preliminary protocol for applying α-CSH in addressing alveolar bone loss following tooth extraction. OBJECTIVE: This research's general objective is to evaluate the feasibility and initial effectiveness of α-CSH as bone-inducing graft material for socket preservation after tooth extraction. METHODS: This preliminary clinical trial will involve 30 fresh extraction sockets from individuals aged 18-35 years. The participants will be divided into 2 groups: one group will receive α-CSH graft material after tooth extraction for socket preservation, while the other group will not receive any graft material. Throughout the study, the participants will be closely monitored for safety measures, which will include clinical examinations, radiographic imaging, and blood tests. Radiographic imaging will be used extensively to assist the progress of bone formation. RESULTS: The study commenced enrollment in August 2022 and is scheduled to conclude post assessments and analyses by the end of 2023. The results of the study are anticipated to be accessible in late 2024. CONCLUSIONS: This clinical study represents the initial investigation in humans to assess the feasibility and efficacy of α-CSH in alveolar bone regeneration. We hypothesize that the inclusion of α-CSH can greatly expedite the process of bone formation within fresh sockets, resulting in a swift restoration of bone height without the disadvantages associated with harvesting autogenous bone graft. TRIAL REGISTRATION: Indonesia Registry Center INA-D02FAHP; https://tinyurl.com/2jnf6n3s. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/49922.

Implementing Explainable Machine Learning Models for Practical Prediction of Early Neonatal Hypoglycemia.

Hypoglycemia is a common metabolic disorder that occurs in the neonatal period. Early identification of neonates at risk of developing hypoglycemia can optimize therapeutic strategies in neonatal care. This study aims to develop a machine learning model and implement a predictive application to assist clinicians in accurately predicting the risk of neonatal hypoglycemia within four hours after birth. Our retrospective study analyzed data from neonates born ≥35 weeks gestational age and admitted to the well-baby nursery between 1 January 2011 and 31 August 2021. We collected electronic medical records of 2687 neonates from a tertiary medical center in Southern Taiwan. Using 12 clinically relevant features, we evaluated nine machine learning approaches to build the predictive models. We selected the models with the highest area under the receiver operating characteristic curve (AUC) for integration into our hospital information system (HIS). The top three AUC values for the early neonatal hypoglycemia prediction models were 0.739 for Stacking, 0.732 for Random Forest and 0.732 for Voting. Random Forest is considered the best model because it has a relatively high AUC and shows no significant overfitting (accuracy of 0.658, sensitivity of 0.682, specificity of 0.649, F1 score of 0.517 and precision of 0.417). The best model was incorporated in the web-based application integrated into the hospital information system. Shapley Additive Explanation (SHAP) values indicated mode of delivery, gestational age, multiparity, respiratory distress, and birth weight < 2500 gm as the top five predictors of neonatal hypoglycemia. The implementation of our machine learning model provides an effective tool that assists clinicians in accurately identifying at-risk neonates for early neonatal hypoglycemia, thereby allowing timely interventions and treatments.

The Stamping Method Utilizing a Double-Trough Die in Microforming to Enhance Formability.

Currently, the field of microgear manufacturing faces various processing challenges, particularly in terms of size reduction; these challenges increase the complexity and costs of manufacturing. In this study, a technique for microgear manufacturing is aimed at reducing subsequent processing steps and enhancing material utilization. This technique involves the use of trough dies with extrusion-cutting processing, which enables workpieces to undergo forming in a negative clearance state, thus reducing subsequent processing time for micro products. We conducted finite element simulations using microgear dies, measuring stress, velocity, and flow during the forming process of four types of dies-flat, internal-trough, external-trough, and double-trough dies. The results indicated that the buffering effect of the troughs reduced the rate of increase in the material's internal stress. In the cavity, the material experiences a significant increase in hydrostatic pressure, leading to the formation of a "hydrostatic pressure wall". This pressure barrier imposes substantial constraints on the flow of the material during dynamic processes, making it difficult for the material to move into the remaining areas. This effectively enhances the blockage of material flow, demonstrating the critical role of hydrostatic pressure in controlling material distribution and movement. In addition, combining the characteristics of both into a double-trough die enhances the overall stability of forming velocity, reduces forming load and energy consumption, and maximizes material utilization. Results further revealed that microgears manufactured using double-trough dies exhibited defect-free surfaces, with a dimensional error of less than 5 µm and tolerances ranging from IT5 to IT6. Overall, this study offers new insights into the traditional field of microgear manufacturing, highlighting potential solutions for the challenges encountered in current microstamping processes.

Risk Factors and Nomogram Model for Hepatocellular Carcinoma Development in Chronic Hepatitis B Patients with Low-Level Viremia.

Background and aim: Patients with chronic hepatitis B patients (CHB) with low-level viremia (LLV) are not necessarily at low risk of developing hepatocellular carcinoma (HCC). The question of whether CHB patients with LLV require immediate antiviral agent (AVT) or long-term AVT remains controversial. The study aims to investigate the risk of HCC development and the risk factors in CHB patients with LLV and construct a nomogram model predicting the risk of HCC. Methods: We conducted a retrospective cohort study that enrolled 16,895 CHB patients from January 2008 to December 2020. The patients were divided into three groups for comparison: the LLV group, maintained virological response (MVR) group and HBV-DNA>2000 group. The cumulative incidence of progression to HCC was assessed. Cox regression analysis was performed to determine the final risk factors, and a nomogram model was constructed. The 10-fold Cross-Validation method was utilized for internal validation. Results: A total of 408 new cases of HCC occurred during the average follow-up period of 5.78 years. The 3, 5, and 10-year cumulative HCC risks in the LLV group were 3.56%, 4.96%, and 9.51%, respectively. There was a significant difference in the cumulative risk of HCC between the HBV-DNA level > 2000 IU/mL and LLV groups (p = 0.049). Independent risk factors for HCC development in LLV group included male gender, age, presence of cirrhosis, and platelets count. The Area Under the Curve (AUC) values for the 3-year and 5-year prediction from our HCC risk prediction model were 0.75 and 0.76, respectively. Conclusion: Patients with LLV and MVR are still at risk for developing HCC. The nomogram established for CHB patient with LLV, incorporating identified significant risk factors, serves as an effective tool for predicting HCC-free outcomes. This nomogram model provides valuable information for determining appropriate surveillance strategies and prescribing AVT.

Longitudinal Risk Analysis of Second Primary Cancer after Curative Treatment in Patients with Rectal Cancer.

Predicting and improving the response of rectal cancer to second primary cancers (SPCs) remains an active and challenging field of clinical research. Identifying predictive risk factors for SPCs will help guide more personalized treatment strategies. In this study, we propose that experience data be used as evidence to support patient-oriented decision-making. The proposed model consists of two main components: a pipeline for extraction and classification and a clinical risk assessment. The study includes 4402 patient datasets, including 395 SPC patients, collected from three cancer registry databases at three medical centers; based on literature reviews and discussion with clinical experts, 10 predictive variables were considered risk factors for SPCs. The proposed extraction and classification pipelines that classified patients according to importance were age at diagnosis, chemotherapy, smoking behavior, combined stage group, and sex, as has been proven in previous studies. The C5 method had the highest predicted AUC (84.88%). In addition, the proposed model was associated with a classification pipeline that showed an acceptable testing accuracy of 80.85%, a recall of 79.97%, a specificity of 88.12%, a precision of 85.79%, and an F1 score of 79.88%. Our results indicate that chemotherapy is the most important prognostic risk factor for SPCs in rectal cancer survivors. Furthermore, our decision tree for clinical risk assessment illuminates the possibility of assessing the effectiveness of a combination of these risk factors. This proposed model may provide an essential evaluation and longitudinal change for personalized treatment of rectal cancer survivors in the future.

Implementation of a machine learning model in acute coronary syndrome and stroke risk assessment for patients with lower urinary tract symptoms.

OBJECTIVE: The global population is aging and the burden of lower urinary tract symptoms (LUTS) is expected to increase. According to the National Health Insurance Research Database, our previous studies have showed LUTS may predispose patients to cardiovascular disease. However, it is difficult to provide a personalized risk assessment in the context of "having acute coronary syndrome (ACS) and stroke." This study aimed to develop an artificial intelligence (AI)-based prediction model for patients with LUTS. MATERIAL AND METHODS: We retrospectively reviewed the electronic medical records of 1799 patients with LUTS at Chi Mei Medical Center between January 1, 2001 and December, 31, 2018. Features with >10 cases and high correlations with outcomes were imported into six machine learning algorithms. The study outcomes included ACS and stroke. Model performances was evaluated using the area under the receiver operating characteristic curve (AUC). The model with the highest AUC was used to implement the clinical risk prediction application. RESULTS: Age, systemic blood pressure, diastolic blood pressure, creatinine, glycated hemoglobin, hypertension, diabetes mellitus and hyperlipidemia were the most relevant features that affect the outcomes. Based on the AUC, our optimal model was built using multilayer perception (AUC = 0.803) to predict ACS and stroke events within 3 years. CONCLUSION: We successfully built an AI-based prediction system that can be used as a prediction model to achieve time-saving, precise, personalized risk evaluation; it can also be used to offer warning, enhance patient adherence, early intervention and better health care outcomes.