Machine Learning Model for Anesthetic Risk Stratification for Gynecologic and Obstetric Patients: A Novel Approach for Early Detection.

BACKGROUND: Preoperative evaluation is important, our study explored the application of machine learning methods for anesthetic risk classification and for the evaluation of the contributions of various factors. To minimize the effects of confounding variables during model training, we used a homogenous group with similar physiological states and ages undergoing similar pelvic organ-related procedures not involving malignancies. OBJECTIVE: Data on women of reproductive age (age = 20-50 years) who underwent gestational or gynecological surgery between January 1, 2017, and December 31, 2021, were obtained from the National Taiwan University Hospital Integrated Medical Database. METHODS: We first performed an exploratory analysis and selected key features. We then performed data preprocessing to acquire relevant features related to preoperative examination. To further enhance predictive performance, we employed the log likelihood ratio algorithm to generate comorbidity patterns. Lastly, we input the processed features into the light gradient boosting machine (LightGBM) model for training and subsequent prediction. RESULTS: A total of 10,892 patients were included. Within this data set, 9893 patients were classified as having low anesthetic risk (American Society of Anesthesiologists physical status score 1-2), and 999 patients were classified as having high anesthetic risk (American Society of Anesthesiologists physical status score > 2). The area under the receiver operating characteristic curve of the LightGBM model was 90.25. CONCLUSIONS: By combining comorbidity information and clinical laboratory data, our methodology based on the LightGBM model provides more accurate predictions for anesthetic risk classification. CLINICALTRIAL: This study was registered with the Research Ethics Committee of the National Taiwan University Hospital with trial number 202204010RINB.

Soft peripheral contact lens for eye elongation control (SPACE): 1-year results of a double-blinded randomized controlled trial.

PURPOSE: To examine the safety and efficacy of soft multifocal contact lenses on slowing the rate of myopia progression. METHODS: A prospective, randomized, double-masked clinical trial was conducted including 115 children (55 boys and 60 girls) aged 8 to 15 years. Children were assigned to wear one of two daily disposable soft contact lens designs; a multifocal design (Pegavision) or a dual-focus design (MiSight, Coopervision) in both eyes for at least 8 h per day for one year. All contact lenses were replaced on a daily basis. Measurements were obtained using a logMAR vision meter, including objective refraction, handheld retinoscopy, high (96 %) and low (12 %) contrast sensitivity, and distance and near visual acuity. Axial length was measured every 6 months. RESULTS: After one year, the spherical equivalent refractive error and axial length of the experimental group (Pegavision) increased by -0.50 ± 0.48 D and 0.24 ± 0.16 mm, respectively, in the right eye and -0.47 ± 0.37 D and 0.23 ± 0.16 mm, respectively, in the left eye. The spherical equivalent refractive error and axial length of the control group (MiSight) increased by -0.48 ± 0.47 D and 0.22 ± 0.13 mm, respectively, in the right eye and by -0.50 ± 0.44 D and 0.23 ± 0.14 mm, respectively, in the left eye, with no significant differences observed between the two lens types. CONCLUSIONS: The one-year results from this clinical trial show that the multifocal soft contact lenses used in the experimental group have a similar myopia control efficacy with respect to spherical equivalent refraction and axial length elongation as a commercially available dual focus soft contact lens design.

Sex differences in clinical characteristics and long-term clinical outcomes in Asian hospitalized heart failure patients.

AIMS: Sex differences in long-term post-discharge clinical outcomes in Asian patients hospitalized for acute decompensated heart failure (HF) persist despite the world-wide implementation of guideline-directed medical therapy for decades. The present study aims to elucidate the puzzling dilemma and to depict the directions of solution. METHODS AND RESULTS: Between 2011 and 2020, a total of 12 428 patients (6518 men and 5910 women, mean age 73.50 ± 14.85) hospitalized for acute decompensated HF were retrospectively enrolled from a university HF cohort. Compared with men, women hospitalized for acute decompensated HF were older in age (76.40 ± 13.43 vs. 71.20 ± 15.67 years old, P < 0.0001) with more coexisting hypertension, diabetes, hyperlipidaemia and moderate to severe chronic kidney disease, but less with ischaemic heart disease, cerebrovascular disease and chronic obstructive pulmonary disease (P < 0.0001). In echocardiography measurement parameters, women had smaller left ventricular and left atrial dimensions, higher left ventricular mass index, higher left ventricular ejection fraction (LVEF) and more in HF with preserved ejection fraction (EF) category (LVEF > 50%) than men (P < 0.0001). In HF therapy, women compared with men received more guideline-directed medical HF therapies including angiotensin-converting enzyme inhibitors, angiotensin receptor blockers, angiotensin receptor-neprilysin inhibitors and sodium-glucose cotransporter-2 inhibitors, but similar beta-blockers and mineralocorticoid receptor antagonists (P < 0.0001). Post-discharge long-term clinical outcomes after multivariate-adjusted analysis revealed that women compared with men had lower all-cause mortality [adjusted hazard ratio (aHR): 0.89, 95% confidence interval (CI): 0.84-0.93], lower cardiovascular mortality (aHR: 0.89, 95% CI: 0.80-0.99) and lower 1 year mortality (aHR: 0.91, 95% CI: 0.84-0.99) but similar HF rehospitalization rate (aHR: 1.02, 95% CI: 0.95-1.09) over 8 years of follow-up. The superiority of women over men in all-cause mortality was shown in HF with preserved EF (>50%) and HF with mildly reduced EF (40%-50%), but not in HF with reduced EF (<40%) category. Subgroup forest plot analysis showed body mass index, coexisting hypertension and chronic obstructive pulmonary disease as significant interacting factors. CONCLUSIONS: With more coronary risk factors and medical comorbidities, less cardiac remodelling and better adherence to guideline-directed HF therapy, women hospitalized for acute decompensated HF demonstrated superiority over men in long-term post-discharge clinical outcomes, including all-cause mortality, cardiovascular mortality and 1 year mortality, and mainly in HF with preserved and mid-range EF categories, in the Asian HF cohort.

Enhancing anti-cancer capacity: Novel class I/II HDAC inhibitors modulate EMT, cell cycle, and apoptosis pathways.

Cancer has been a leading cause of death over the last few decades in western countries as well as in Taiwan. However, traditional therapies are limited by the adverse effects of chemotherapy and radiotherapy, and tumor recurrence may occur. Therefore, it is critical to develop novel therapeutic drugs. In the field of HDAC inhibitor development, apart from the hydroxamic acid moiety, 2-aminobenzamide also functions as a zinc-binding domain, which is shown in well-known HDAC inhibitors such as Entinostat and Chidamide. With recent successful experiences in synthesizing 1-(phenylsulfonyl)indole-based compounds, in this study, we further combined two features of the above chemical compounds and generated indolyl benzamides. Compounds were screened in different cancer cell lines, and enzyme activity was examined to demonstrate their potential for anti-HDAC activity. Various biological functional assays evidenced that two of these compounds could suppress cancer growth and migration capacity, through regulating epithelial-mesenchymal transition (EMT), cell cycle, and apoptosis mechanisms. Data from 3D cancer cells and the in vivo zebrafish model suggested the potential of these compounds in cancer therapy in the future.

Web-based artificial intelligence to predict cognitive impairment following stroke: A multicenter study.

BACKGROUND AND PURPOSE: Post-stroke cognitive impairment (PSCI) is highly prevalent in modern society. However, there is limited study implying an accurate and explainable machine learning model to predict PSCI. The aim of this study is to develop and validate a web-based artificial intelligence (AI) tool for predicting PSCI. METHODS: The retrospective cohort study design was conducted to develop and validate a web-based prediction model. Adults who experienced a stroke between January 1, 2004, and September 30, 2017, were enrolled, and patients with PSCI were followed up from the stroke index date until their last follow-up. The model's performance metrics, including accuracy, area under the curve (AUC), recall, precision, and F1 score, were compared. RESULTS: A total of 3209 stroke patients were included in the study. The model demonstrated an accuracy of 0.8793, AUC of 0.9200, recall of 0.6332, precision of 0.9664, and F1 score of 0.7651. In the external validation phase, the accuracy improved to 0.9039, AUC to 0.9094, recall to 0.7457, precision to 0.9168, and F1 score to 0.8224. The final model can be accessed at https://psci-calculator.my.id/. CONCLUSION: Our results are able to produce a user-friendly interface that is useful for health practitioners to perform early prediction on PSCI. These findings also suggest that the provided AI model is reliable and can serve as a roadmap for future studies using AI models in a clinical setting.

Fluorescence-based reagent and spectrum-based optical reader for lactoferrin detection in tears: differentiating Sjögren's syndrome from non-Sjögren's dry eye syndrome.

Identification of an early biomarker and effective testing device to differentiate dry eye disease secondary to autoimmune disease (Sjögren's syndrome dry eye disease) from non-Sjögren's dry eye disease are prerequisites for appropriate treatment. We aimed to demonstrate the capacity of a new photo-detection device to evaluate tear lactoferrin levels as a tool for differentiating systemic conditions associated with dry eye disease. Patients with non-Sjögren's and Sjögren's syndrome dry eye disease (n = 54 and n = 52, respectively) and controls (n = 11) were enrolled. All participants completed the Ocular Surface Disease Index questionnaire. Tear collection was performed with Schirmer test, and tear break-up time was examined using a slit lamp. Tear lactoferrin was evaluated using our newly developed photo-detection device. The average lactoferrin concentration was significantly lower in samples from patients with non-Sjögren's dry eye disease (0.337 ± 0.227 mg/mL, n = 54) and Sjögren's syndrome dry eye disease (0.087 ± 0.010 mg/mL, n = 52) than in control samples (1.272 ± 0.54 mg/mL, n = 11) (p < 0.0001). Further, lactoferrin levels were lower in patients with Sjögren's syndrome dry eye disease than in those with non-Sjögren's dry eye disease (p < 0.001). Our cost-effective, antibody-free, highly sensitive photo-detection device for evaluating tear lactoferrin levels can assist ophthalmologists in differentiating different types of dry eye diseases.

Functional and structural investigation of a broadly neutralizing SARS-CoV-2 antibody.

Since its emergence, SARS-CoV-2 has been continuously evolving, hampering the effectiveness of current vaccines against COVID-19. mAbs can be used to treat patients at risk of severe COVID-19. Thus, the development of broadly protective mAbs and an understanding of the underlying protective mechanisms are of great importance. Here, we isolated mAbs from donors with breakthrough infection with Omicron subvariants using a single-B cell screening platform. We identified a mAb, O5C2, which possesses broad-spectrum neutralization and antibody-dependent cell-mediated cytotoxic activities against SARS-CoV-2 variants, including EG.5.1. Single-particle analysis by cryo-electron microscopy revealed that O5C2 targeted an unusually large epitope within the receptor-binding domain of spike protein that overlapped with the angiotensin-converting enzyme 2 binding interface. Furthermore, O5C2 effectively protected against BA.5 Omicron infection in vivo by mediating changes in transcriptomes enriched in genes involved in apoptosis and interferon responses. Our findings provide insights into the development of pan-protective mAbs against SARS-CoV-2.

Trying a board game intervention on children with autism spectrum disorder in Macau: how do they react?

Limited special education and related services are available for children with autism spectrum disorder (ASD) in Macau, especially those who are educated in general education classrooms. No intervention study has been conducted on these children. This study was conducted to explore the relationship between a board game play intervention and board game play behaviors and social communication of children with ASD educated in general education classrooms in Macau. A repeated measures design was used and the results of this study showed the mean occurrence of unprompted board game play behaviors per session during intervention was not significantly different from that during pre- or post-intervention. The mean occurrence of social communication per session during intervention was significantly higher than that during pre- and post-intervention. These findings suggest a positive relationship existed between the board game intervention used in this study and social communication of children with ASD.

Taipei Medical University Clinical Research Database: a collaborative hospital EHR database aligned with international common data standards.

OBJECTIVE: The objective of this paper is to provide a comprehensive overview of the development and features of the Taipei Medical University Clinical Research Database (TMUCRD), a repository of real-world data (RWD) derived from electronic health records (EHRs) and other sources. METHODS: TMUCRD was developed by integrating EHRs from three affiliated hospitals, including Taipei Medical University Hospital, Wan-Fang Hospital and Shuang-Ho Hospital. The data cover over 15 years and include diverse patient care information. The database was converted to the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) for standardisation. RESULTS: TMUCRD comprises 89 tables (eg, 29 tables for each hospital and 2 linked tables), including demographics, diagnoses, medications, procedures and measurements, among others. It encompasses data from more than 4.15 million patients with various medical records, spanning from the year 2004 to 2021. The dataset offers insights into disease prevalence, medication usage, laboratory tests and patient characteristics. DISCUSSION: TMUCRD stands out due to its unique advantages, including diverse data types, comprehensive patient information, linked mortality and cancer registry data, regular updates and a swift application process. Its compatibility with the OMOP CDM enhances its usability and interoperability. CONCLUSION: TMUCRD serves as a valuable resource for researchers and scholars interested in leveraging RWD for clinical research. Its availability and integration of diverse healthcare data contribute to a collaborative and data-driven approach to advancing medical knowledge and practice.

Association between sodium-glucose cotransporter-2 (SGLT2) inhibitors and macular degeneration in patients with diabetes: a nationwide population-based study in Taiwan.

AIMS: Evidence showed that SGLT2 inhibitors have greater protective effects against retinal diseases compared to other hypoglycemic agents. Thus, we explore the association between SGLT2 inhibitor usage and macular degeneration (MD) in Taiwanese patients with diabetes. METHODS: The National Health Insurance (NHI) program's claim data are released as the National Health Insurance Research Database (NHIRD). This database covers more than 99% of the residents in Taiwan. We included data on patients who were newly diagnosed with type 2 diabetes mellitus (ICD-9-CM: 250, exclude 250.1x; ICD-10-CM: E11), with an age at diagnosis of over 20 years as our study population. Patients who received (sodium-glucose cotransporter 2 inhibitor) SGLT2i (ATC code: A10BK) over 90 days in 2016-2019 were defined as the SGLT2i cohort. Conversely, patients who did never received SGLT2i were defined as the non-SGLT2i cohort. The exclusion criteria were having MD before the index date, receiving SGLT2i within 1-89 days, and missing data on sex, age, or days of SGLT2i usage. Two cohorts were matched by 1:1 propensity score matching, which was based on age, sex, payroll bracket grade, urbanization, comorbidities, and medications. RESULTS: Compared to non-SGLT2i cohort, patients who received SGLT2i had a significantly lower risk of MD (adjusted hazard ratio = 0.70, 95%CI = 0.66-0.75). CONCLUSIONS: We found that SGLT2is has a strong protective effect against MD in patients with diabetes. SGLT2is may have benefits beyond glycemic control in patients with DR. However, additional clinical and experimental studies are required.

The Lived Experiences of Palliative Care Professionals in Cultivating Mindfulness: A Phenomenological Study.

Purpose: The aim of this study was to explore the essence of the lived experiences of palliative care professionals in cultivating mindfulness, with a focus on the meaning of mindfulness in their lives and how mindfulness is experienced throughout their process of caring for others. Design: This was a qualitative study using a phenomenological approach. Methods: Eleven palliative care professionals (three physicians, four nurses, three psychologists, and one spiritual care provider) partook in in-depth interviews. Data were collected from the in-depth interviews and analyzed according to the method of Giorgi. Findings: Two major themes emerged from this study. First, the palliative care professionals realized the need for self-care amid emotional burden, including recognizing their feelings of guilt and self-doubt, emotional contagion of grief, reflections of others' fragility on themself, and their self-imposed limitations. Second, they noticed the transformative impact of mindfulness on them, including detecting reconnection with their body, changes in their personal values, self-acceptance, and liberation. Conclusion: Palliative care professionals can cultivate self-acceptance and facilitate entirely new life experiences through the practice of mindfulness. For them, mindfulness is not merely a self-regulation technique but an existential epiphany, offering hope for self-care and empowerment.

Colorectal Cancer and Subsequent Diabetes Risk: A Population-based Cohort Study in Taiwan.

CONTEXT: The association between colorectal cancer (CRC) and new-onset diabetes mellitus remains unclear. OBJECTIVE: To examine the association between CRC and the risk of subsequent diabetes mellitus and to further investigate the impact of chemotherapy on diabetes mellitus risk in CRC. DESIGN: A nationwide cohort study. METHODS: Using the Taiwan Cancer Registry Database (2007-2018) linked with health databases, 86,268 patients with CRC and an equal propensity score-matched cohort from the general population were enrolled. Among them, 37,277 CRC patients from the Taiwan Cancer Registry (2007-2016) were analyzed for diabetes mellitus risk associated with chemotherapy. Chemotherapy exposure within 3 years of diagnosis was categorized as no chemotherapy, <90 days, 90-180 days, and >180 days. Differences in diabetes mellitus risk were assessed across these categories. RESULTS: Each group involved 86,268 participants after propensity score matching. The patients with CRC had a 14% higher risk of developing diabetes mellitus than the matched general population (hazard ratio [HR]: 1.14, 95% confidence interval [CI]: 1.09-1.20). The highest risk was observed within the first year after diagnosis followed by a sustained elevated risk. Long-term chemotherapy (>180 days within 3 years) was associated with a 60-70% increased risk of subsequent diabetes mellitus (HR: 1.64, 95% CI: 1.07-2.49). CONCLUSION: Patients with CRC are associated with an elevated risk of diabetes mellitus, and long-term chemotherapy, particularly involving capecitabine, increases diabetes mellitus risk. Thus, monitoring blood glucose levels is crucial for patients with CRC, especially during extended chemotherapy.

Salpingectomy for ectopic pregnancy reduces ovarian cancer risk-a nationwide study.

Recent studies propose fallopian tubes as the tissue origin for many ovarian epithelial cancers. To further support this paradigm, we assessed whether salpingectomy for treating ectopic pregnancy had a protective effect using the Taiwan Longitudinal National Health Research Database. We identified 316 882 women with surgical treatment for ectopic pregnancy and 3 168 820 age- and index-date-matched controls from 2000 to 2016. In a nested cohort, 91.5% of cases underwent unilateral salpingectomy, suggesting that most surgically managed patients have salpingectomy. Over a follow-up period of 17 years, the ovarian carcinoma incidence was 0.0069 (95% confidence interval [CI] = 0.0060 to 0.0079) and 0.0089 (95% CI = 0.0086 to 0.0092) in the ectopic pregnancy and the control groups, respectively (P < .001). After adjusting the events to per 100 person-years, the hazard ratio (HR) in the ectopic pregnancy group was 0.70 (95% CI = 0.61 to 0.80). The risk reduction occurred only in epithelial ovarian cancer (HR = 0.73, 95% CI = 0.63 to 0.86) and not in non-epithelial subtypes. These findings show a decrease in ovarian carcinoma incidence after salpingectomy for treating ectopic pregnancy.

Rapid simulation of glycoprotein structures by grafting and steric exclusion of glycan conformer libraries.

Most membrane proteins are modified by covalent addition of complex sugars through N- and O-glycosylation. Unlike proteins, glycans do not typically adopt specific secondary structures and remain very mobile, shielding potentially large fractions of protein surface. High glycan conformational freedom hinders complete structural elucidation of glycoproteins. Computer simulations may be used to model glycosylated proteins but require hundreds of thousands of computing hours on supercomputers, thus limiting routine use. Here, we describe GlycoSHIELD, a reductionist method that can be implemented on personal computers to graft realistic ensembles of glycan conformers onto static protein structures in minutes. Using molecular dynamics simulation, small-angle X-ray scattering, cryoelectron microscopy, and mass spectrometry, we show that this open-access toolkit provides enhanced models of glycoprotein structures. Focusing on N-cadherin, human coronavirus spike proteins, and gamma-aminobutyric acid receptors, we show that GlycoSHIELD can shed light on the impact of glycans on the conformation and activity of complex glycoproteins.

Differential histone acetylation and super-enhancer regulation underlie melanoma cell dedifferentiation.

Dedifferentiation or phenotype switching refers to the transition from a proliferative to an invasive cellular state. We previously identified a 122-gene epigenetic gene signature that classifies primary melanomas as low versus high risk (denoted as Epgn1 or Epgn3). We found that the transcriptomes of the Epgn1 low-risk and Epgn3 high-risk cells are similar to the proliferative and invasive cellular states, respectively. These signatures were further validated in melanoma tumor samples. Examination of the chromatin landscape revealed differential H3K27 acetylation in the Epgn1 low-risk versus Epgn3 high-risk cell lines that corroborated with a differential super-enhancer and enhancer landscape. Melanocytic lineage genes (MITF, its targets and regulators) were associated with super-enhancers in the Epgn1 low-risk state, whereas invasiveness genes were linked with Epgn3 high-risk status. We identified the ITGA3 gene as marked by a super-enhancer element in the Epgn3 invasive cells. Silencing of ITGA3 enhanced invasiveness in both in vitro and in vivo systems, suggesting it as a negative regulator of invasion. In conclusion, we define chromatin landscape changes associated with Epgn1/Epgn3 and phenotype switching during early steps of melanoma progression that regulate transcriptional reprogramming. This super-enhancer and enhancer-driven epigenetic regulatory mechanism resulting in major changes in the transcriptome could be important in future therapeutic targeting efforts.

A strategy of novel molecular hydrogen-producing antioxidative auxiliary system improves virus production in cell bioreactor.

In the increasing demand for virus vaccines, large-scale production of safe, efficient, and economical viral antigens has become a significant challenge. High-cell-density manufacturing processes are the most commonly used to produce vaccine antigens and protein drugs. However, the cellular stress response in large-scale cell culture may directly affect host cell growth and metabolism, reducing antigen production and increasing production costs. This study provided a novel strategy of the antioxidant auxiliary system (AAS) to supply molecular hydrogen (H2) into the cell culture media via proton exchange membrane (PEM) electrolysis. Integrated with a high-density cell bioreactor, the AAS aims to alleviate cellular stress response and increase viral vaccine production. In the results, the AAS stably maintained H2 concentration in media even in the high-air exposure tiding cell bioreactor. H2 treatment was shown safe to cell culture and effectively alleviated oxidative stress. In two established virus cultures models, bovine epidemic fever virus (BEFV) and porcine circovirus virus type 2 (PCV-2), were employed to verify the efficacy of AAS. The virus yield was increased by 3.7 and 2.5 folds in BEFV and PCV-2 respectively. In conclusion, the AAS-connected bioreactor effectively alleviated cellular oxidative stress and enhanced virus production in high-density cell culture.

Effects of a Health Literacy Education Program on Mental Health and Renal Function in Patients With Chronic Kidney Disease: A Randomized Controlled Trial.

BACKGROUND: Chronic kidney disease (CKD) refers to permanent damage to the kidneys that occurs gradually over time. Further progression may be preventable depending on its stage. PURPOSE: This study was developed to evaluate the effect of a health literacy education program (HLEP) on mental health and renal functioning in patients with CKD. METHODS: A single-blind, randomized controlled trial study was conducted. Data were collected from March 25 to December 18, 2021. Participants were randomly assigned to either the experimental group (n = 42), which received multidisciplinary care and HLEP, or the control group (n = 42), which received multidisciplinary care only. Data were collected at baseline (T1), Month 3 (T2), and Month 6 (T3), and the data included patient characteristics, estimated glomerular filtration rate, and responses to the Mandarin Multidimensional Health Literacy Questionnaire and Beck Depression Inventory. RESULTS: After 6 months of the HLEP intervention, the results of generalized estimating equations analysis showed that, compared with the control group, the experimental group had significantly higher health literacy at Month 3 (ß = -3.37, 95% CI [-5.68, -1.06]), significantly improved depression at Month 3 (ß = -2.24, 95% CI [-4.11, -0.37]) and Month 6 (ß = -4.36, 95% CI [-6.60, -2.12]), and a significantly higher estimated glomerular filtration rate at Month 6 (ß = 5.87, 95% CI [1.35, 10.38]). CONCLUSIONS/IMPLICATIONS FOR PRACTICE: The findings of this study may provide a reference for healthcare providers to educate patients with Stage 3-4 CKD using the HLEP. Positive effects on health literacy, depression, and renal function in patients with Stage 3-4 CKD were observed in the short term. Findings from this study may facilitate the implementation of multidisciplinary and nurse-led strategies in primary care to reinforce patients' health literacy, self-care ability, and adjustment to CKD as well as delay disease progression.

Machine-Learning Based Risk Assessment for Cancer Therapy-Related Cardiac Adverse Events Among Breast Cancer Patients.

The study aims to develop machine-learning models to predict cardiac adverse events in female breast cancer patients who receive adjuvant therapy. We selected breast cancer patients from a retrospective dataset of the Taipei Medical University Clinical Research Database and Taiwan Cancer Registry between January 2004 and December 2020. Patients were monitored at the date of prescribed chemo- and/or -target therapies until cardiac adverse events occurred during a year. Variables were used, including demographics, comorbidities, medications, and lab values. Logistics regression (LR) and artificial neural network (ANN) were used. The performance of the algorithms was measured by the area under the receiver operating characteristic curve (AUC). In total, 1321 patients (an equal 15039 visits) were included. The best performance of the artificial neural network (ANN) model was achieved with the AUC, precision, recall, and F1-score of 0.89, 0.14, 0.82, and 0.2, respectively. The most important features were a pre-existing cardiac disease, tumor size, estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2), cancer stage, and age at index date. Further research is necessary to determine the feasibility of applying the algorithm in the clinical setting and explore whether this tool could improve care and outcomes.