Machine learning-based in-hospital mortality prediction models for patients with acute coronary syndrome

Exploring trends and autonomy levels of adaptive business intelligence in healthcare: A systematic review

OBJECTIVE

In order to comprehensively understand the characteristics of Adaptive Business Intelligence (ABI) in Healthcare, this study is structured to provide insights into the common features and evolving patterns within this domain. Applying the Sheridan's Classification as a framework, we aim to assess the degree of autonomy exhibited by various ABI components. Together, these objectives will contribute to a deeper understanding of ABI implementation and its implications within the Healthcare context.

METHODS

A comprehensive search of academic databases was conducted to identify relevant studies, selecting AIS e-library (AISel), Decision Support Systems Journal (DSSJ), Nature, The Lancet Digital Health (TLDH), PubMed, Expert Systems with Application (ESWA) and npj Digital Medicine as information sources. Studies from 2006 to 2022 were included based on predefined eligibility criteria. PRISMA statements were used to report this study.

RESULTS

The outcomes showed that ABI systems present distinct levels of development, autonomy and practical deployment. The high levels of autonomy were essentially associated with predictive components. However, the possibility of completely autonomous decisions by these systems is totally excluded. Lower levels of autonomy are also observed, particularly in connection with prescriptive components, granting users responsibility in the generation of decisions.

CONCLUSION

The study presented emphasizes the vital connection between desired outcomes and the inherent autonomy of these solutions, highlighting the critical need for additional research on the consequences of ABI systems and their constituent elements. Organizations should deploy these systems in a way consistent with their objectives and values, while also being mindful of potential adverse effects. Providing valuable insights for researchers, practitioners, and policymakers aiming to comprehend the diverse levels of ABI systems implementation, it contributes to well-informed decision-making in this dynamic field.

1-Year Mortality Prediction through Artificial Intelligence Using Hemodynamic Trace Analysis among Patients with ST Elevation Myocardial Infarction

Background and Objectives: Patients presenting with ST Elevation Myocardial Infarction (STEMI) due to occlusive coronary arteries remain at a higher risk of excess morbidity and mortality despite being treated with primary percutaneous coronary intervention (PPCI). Identifying high-risk patients is prudent so that close monitoring and timely interventions can improve outcomes. Materials and Methods: A cohort of 605 STEMI patients [64.2 ± 13.2 years, 432 (71.41%) males] treated with PPCI were recruited. Their arterial pressure (AP) wave recorded throughout the PPCI procedure was analyzed to extract features to predict 1-year mortality. After denoising and extracting features, we developed two distinct feature selection strategies. The first strategy uses linear discriminant analysis (LDA), and the second employs principal component analysis (PCA), with each method selecting the top five features. Then, three machine learning algorithms were employed: LDA, K-nearest neighbor (KNN), and support vector machine (SVM). Results: The performance of these algorithms, measured by the area under the curve (AUC), ranged from 0.73 to 0.77, with accuracy, specificity, and sensitivity ranging between 68% and 73%. Moreover, we extended the analysis by incorporating demographics, risk factors, and catheterization information. This significantly improved the overall accuracy and specificity to more than 76% while maintaining the same level of sensitivity. This resulted in an AUC greater than 0.80 for most models. Conclusions: Machine learning algorithms analyzing hemodynamic traces in STEMI patients identify high-risk patients at risk of mortality.

Prognostic prediction of sepsis patient using transformer with skip connected token for tabular data

Sepsis is known as a common syndrome in intensive care units (ICU), and severe sepsis and septic shock are among the leading causes of death worldwide. The purpose of this study is to develop a deep learning model that supports clinicians in efficiently managing sepsis patients in the ICU by predicting mortality, ICU length of stay (>14 days), and hospital length of stay (>30 days). The proposed model was developed using 591 retrospective data with 16 tabular data related to a sequential organ failure assessment (SOFA) score. To analyze tabular data, we designed the modified architecture of the transformer that has achieved extraordinary success in the field of languages and computer vision tasks in recent years. The main idea of the proposed model is to use a skip-connected token, which combines both local (feature-wise token) and global (classification token) information as the output of a transformer encoder. The proposed model was compared with four machine learning models (ElasticNet, Extreme Gradient Boosting [XGBoost]), and Random Forest) and three deep learning models (Multi-Layer Perceptron [MLP], transformer, and Feature-Tokenizer transformer [FT-Transformer]) and achieved the best performance (mortality, area under the receiver operating characteristic (AUROC) 0.8047; ICU length of stay, AUROC 0.8314; hospital length of stay, AUROC 0.7342). We anticipate that the proposed model architecture will provide a promising approach to predict the various clinical endpoints using tabular data such as electronic health and medical records.

A comparative study of explainable ensemble learning and logistic regression for predicting in-hospital mortality in the emergency department

This study addresses the challenges associated with emergency department (ED) overcrowding and emphasizes the need for efficient risk stratification tools to identify high-risk patients for early intervention. While several scoring systems, often based on logistic regression (LR) models, have been proposed to indicate patient illness severity, this study aims to compare the predictive performance of ensemble learning (EL) models with LR for in-hospital mortality in the ED. A cross-sectional single-center study was conducted at the ED of Imam Reza Hospital in northeast Iran from March 2016 to March 2017. The study included adult patients with one to three levels of emergency severity index. EL models using Bagging, AdaBoost, random forests (RF), Stacking and extreme gradient boosting (XGB) algorithms, along with an LR model, were constructed. The training and validation visits from the ED were randomly divided into 80% and 20%, respectively. After training the proposed models using tenfold cross-validation, their predictive performance was evaluated. Model performance was compared using the Brier score (BS), The area under the receiver operating characteristics curve (AUROC), The area and precision-recall curve (AUCPR), Hosmer-Lemeshow (H-L) goodness-of-fit test, precision, sensitivity, accuracy, F1-score, and Matthews correlation coefficient (MCC). The study included 2025 unique patients admitted to the hospital's ED, with a total percentage of hospital deaths at approximately 19%. In the training group and the validation group, 274 of 1476 (18.6%) and 152 of 728 (20.8%) patients died during hospitalization, respectively. According to the evaluation of the presented framework, EL models, particularly Bagging, predicted in-hospital mortality with the highest AUROC (0.839, CI (0.802-0.875)) and AUCPR = 0.64 comparable in terms of discrimination power with LR (AUROC (0.826, CI (0.787-0.864)) and AUCPR = 0.61). XGB achieved the highest precision (0.83), sensitivity (0.831), accuracy (0.842), F1-score (0.833), and the highest MCC (0.48). Additionally, the most accurate models in the unbalanced dataset belonged to RF with the lowest BS (0.128). Although all studied models overestimate mortality risk and have insufficient calibration (P > 0.05), stacking demonstrated relatively good agreement between predicted and actual mortality. EL models are not superior to LR in predicting in-hospital mortality in the ED. Both EL and LR models can be considered as screening tools to identify patients at risk of mortality.

C-reactive protein to albumin ratio may predict in-hospital mortality in non-ST elevation myocardial infarction

Objective: The authors investigated the value of novel inflammatory markers, systemic immune-inflammation index and C-reactive protein to albumin ratio (CAR), to predict in-hospital mortality in patients with non-ST elevation myocardial infarction (NSTEMI). Materials & methods: A total of 308 patients who underwent percutaneous coronary intervention because of NSTEMI were retrospectively included in the study. Killip classification, Thrombolysis in Myocardial Infarction score, SYNTAX score, and CAR and systemic immune-inflammation index values were calculated. Results: CAR (cutoff: 0.0864; sensitivity: 94.1%; specificity: 40.5%; p = 0.008) and Killip classification (cutoff: 2.5; sensitivity: 64.7%; specificity: 8.9%; p = 0.001) were found to be significantly higher in determining in-hospital mortality. Conclusion: This study revealed that CAR is an inexpensive and significant factor in predicting in-hospital mortality in patients undergoing percutaneous coronary intervention for NSTEMI.

Applications of deep learning models in precision prediction of survival rates for heart failure patients

BACKGROUND

Heart failure poses a significant challenge in the global health domain, and accurate prediction of mortality is crucial for devising effective treatment plans. In this study, we employed a Seq2Seq model from deep learning, integrating 12 patient features. By finely modeling continuous medical records, we successfully enhanced the accuracy of mortality prediction.

OBJECTIVE

The objective of this research was to leverage the Seq2Seq model in conjunction with patient features for precise mortality prediction in heart failure cases, surpassing the performance of traditional machine learning methods.

METHODS

The study utilized a Seq2Seq model in deep learning, incorporating 12 patient features, to intricately model continuous medical records. The experimental design aimed to compare the performance of Seq2Seq with traditional machine learning methods in predicting mortality rates.

RESULTS

The experimental results demonstrated that the Seq2Seq model outperformed conventional machine learning methods in terms of predictive accuracy. Feature importance analysis provided critical patient risk factors, offering robust support for formulating personalized treatment plans.

CONCLUSIONS

This research sheds light on the significant applications of deep learning, specifically the Seq2Seq model, in enhancing the precision of mortality prediction in heart failure cases. The findings present a valuable direction for the application of deep learning in the medical field and provide crucial insights for future research and clinical practices.

The predictive value of machine learning for mortality risk in patients with acute coronary syndromes: a systematic review and meta-analysis

BACKGROUND

Acute coronary syndromes (ACS) are the leading cause of global death. Optimizing mortality risk prediction and early identification of high-risk patients is essential for developing targeted prevention strategies. Many researchers have built machine learning (ML) models to predict the mortality risk in ACS patients. Our meta-analysis aimed to evaluate the predictive value of various ML models in predicting death in ACS patients at different times.

METHODS

PubMed, Embase, Web of Science, and Cochrane Library were searched systematically from database establishment to March 12, 2022 for studies developing or validating at least one ML predictive model for death in ACS patients. We used PROBAST to assess the risk of bias in the reported predictive models and a random-effects model to assess the pooled C-index and accuracy of these models.

RESULTS

Fifty papers were included, involving 216 ML prediction models, 119 of which were externally validated. The combined C-index of the ML models in the validation cohort predicting the in-hospital mortality, 30-day mortality, 3- or 6-month mortality, and 1 year or above mortality in ACS patients were 0.8633 (95% CI 0.8467-0.8802), 0.8296 (95% CI 0.8134-0.8462), 0.8205 (95% CI 0.7881-0.8541), and 0.8197 (95% CI 0.8042-0.8354), respectively, with the corresponding combined accuracy of 0.8569 (95% CI 0.8411-0.8715), 0.8282 (95% CI 0.7922-0.8591), 0.7303 (95% CI 0.7184-0.7418), and 0.7837 (95% CI 0.7455-0.8175), indicating that the ML models were relatively excellent in predicting ACS mortality at different times. Furthermore, common predictors of death in ML models included age, sex, systolic blood pressure, serum creatinine, Killip class, heart rate, diastolic blood pressure, blood glucose, and hemoglobin.

CONCLUSIONS

The ML models had excellent predictive power for mortality in ACS, and the methodologies may need to be addressed before they can be used in clinical practice.

Machine learning-based models to predict one-year mortality among Chinese older patients with coronary artery disease combined with impaired glucose tolerance or diabetes mellitus

PURPOSE

An accurate prediction of survival prognosis is beneficial to guide clinical decision-making. This prospective study aimed to develop a model to predict one-year mortality among older patients with coronary artery disease (CAD) combined with impaired glucose tolerance (IGT) or diabetes mellitus (DM) using machine learning techniques.

METHODS

A total of 451 patients with CAD combined with IGT and DM were finally enrolled, and those patients randomly split 70:30 into training cohort (n = 308) and validation cohort (n = 143).

RESULTS

The one-year mortality was 26.83%. The least absolute shrinkage and selection operator (LASSO) method and ten-fold cross-validation identified that seven characteristics were significantly associated with one-year mortality with creatine, N-terminal pro-B-type natriuretic peptide (NT-proBNP), and chronic heart failure being risk factors and hemoglobin, high density lipoprotein cholesterol, albumin, and statins being protective factors. The gradient boosting machine model outperformed other models in terms of Brier score (0.114) and area under the curve (0.836). The gradient boosting machine model also showed favorable calibration and clinical usefulness based on calibration curve and clinical decision curve. The Shapley Additive exPlanations (SHAP) found that the top three features associated with one-year mortality were NT-proBNP, albumin, and statins. The web-based application could be available at https://starxueshu-online-application1-year-mortality-main-49cye8.streamlitapp.com/ .

CONCLUSIONS

This study proposes an accurate model to stratify patients with a high risk of one-year mortality. The gradient boosting machine model demonstrates promising prediction performance. Some interventions to affect NT-proBNP and albumin levels, and statins, are beneficial to improve survival outcome among patients with CAD combined with IGT or DM.

Hybrid XGBoost model with hyperparameter tuning for prediction of liver disease with better accuracy

BACKGROUND

Liver disease indicates any pathology that can harm or destroy the liver or prevent it from normal functioning. The global community has recently witnessed an increase in the mortality rate due to liver disease. This could be attributed to many factors, among which are human habits, awareness issues, poor healthcare, and late detection. To curb the growing threats from liver disease, early detection is critical to help reduce the risks and improve treatment outcome. Emerging technologies such as machine learning, as shown in this study, could be deployed to assist in enhancing its prediction and treatment.

AIM

To present a more efficient system for timely prediction of liver disease using a hybrid eXtreme Gradient Boosting model with hyperparameter tuning with a view to assist in early detection, diagnosis, and reduction of risks and mortality associated with the disease.

METHODS

The dataset used in this study consisted of 416 people with liver problems and 167 with no such history. The data were collected from the state of Andhra Pradesh, India, through https://www.kaggle.com/datasets/uciml/indian-liver-patient-records. The population was divided into two sets depending on the disease state of the patient. This binary information was recorded in the attribute "is_patient".

RESULTS

The results indicated that the chi-square automated interaction detection and classification and regression trees models achieved an accuracy level of 71.36% and 73.24%, respectively, which was much better than the conventional method. The proposed solution would assist patients and physicians in tackling the problem of liver disease and ensuring that cases are detected early to prevent it from developing into cirrhosis (scarring) and to enhance the survival of patients. The study showed the potential of machine learning in health care, especially as it concerns disease prediction and monitoring.

CONCLUSION

This study contributed to the knowledge of machine learning application to health and to the efforts toward combating the problem of liver disease. However, relevant authorities have to invest more into machine learning research and other health technologies to maximize their potential.

A functional outcome prediction model of acute traumatic spinal cord injury based on extreme gradient boost

OBJECTIVE

We aimed to construct a nonlinear regression model through Extreme Gradient Boost (XGBoost) to predict functional outcome 1 year after surgical decompression for patients with acute spinal cord injury (SCI) and explored the importance of predictors in predicting the functional outcome.

METHODS

We prospectively enrolled 249 patients with acute SCI from 5 primary orthopedic centers from June 1, 2016, to June 1, 2020. We identified a total of 6 predictors with three aspects: (1) clinical characteristics, including age, American Spinal Injury Association (ASIA) Impairment Scale (AIS) at admission, level of injury and baseline ASIA motor score (AMS); (2) MR imaging, mainly including Brain and Spinal Injury Center (BASIC) score; (3) surgical timing, specifically comparing whether surgical decompression was received within 24 h or not. We assessed the SCIM score at 1 year after the operation as the functional outcome index. XGBoost was used to build a nonlinear regression prediction model through the method of boosting integrated learning.

RESULTS

We successfully constructed a nonlinear regression prediction model through XGBoost and verified the credibility. There is no significant difference between actual SCIM and nonlinear prediction model (t = 0.86, P = 0.394; Mean ± SD: 3.31 ± 2.8). The nonlinear model is superior to the traditional linear model (t = 6.57, P < 0.001). AMS and age played the most important roles in constructing predictive models. There is an obvious correlation between AIS, AMS and BASIC score.

CONCLUSION

We verified the feasibility of using XGBoost to construct a nonlinear regression prediction model for the functional outcome of patients with acute SCI, and proved that the predictive performance of the nonlinear model is better than the traditional linear regression prediction model. Age and baseline AMS play the most important role in predicting the functional outcome. We also found a significant correlation between AIS at admission, baseline AMS and BASIC score.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT03103516.

Cardiac Biomarkers in 2022 – a Vital Tool for Emergency Care

The role of cardiac biomarkers in diagnosing acute myocardial infarction is undoubted. In the 2020 guidelines of the European Society of Cardiology, the measurement of cardiac peptides to gain prognostic information has a class IIa indication in all patients with ACS. In emergency care, ruling out a non-ST elevation myocardial infarction requires documentation of normal levels of cardiac biomarkers, which remain stable or have very small variations within several hours. This review aims to summarize the current knowledge and recent progresses in the field of cardiac biomarker discovery, from their routine use in emergency rooms to their prognostic roles in modern risk assessment tools. Integrated approaches combining cardiac troponin with other biomarkers of ventricular dysfunction or inflammation, or with modern cardiac imaging in emergency care are also presented, as well as the role of modern algorithms for serial troponin measurement in the modern management of emergency departments.