A Machine Learning-Based Prediction of Hospital Mortality in Patients With Postoperative Sepsis

Machine learning application for prediction of surgical site infection after posterior cervical surgery

Surgical site infection (SSI) is one of the most common complications of posterior cervical surgery. It is difficult to diagnose in the early stage and may lead to severe consequences such as wound dehiscence and central nervous system infection. This retrospective study included patients who underwent posterior cervical surgery at The Second Affiliated Hospital and Yuying Childrens Hospital of Wenzhou Medical University from September 2018 to June 2022. We employed several machine learning methods, such as the gradient boosting (GB), random forests (RF), artificial neural network (ANN) and other popular machine learning models. To minimize the variability introduced by random splitting, the results underwent 10-fold cross-validation repeated 10 times. Five measurements were averaged across 10 repetitions with 10-fold cross-validation, the RF model achieved the highest AUROC (0.9916), specificity (0.9890) and precision (0.9759). The GB model achieved the highest sensitivity (0.9535) and the KNN achieved the highest sensitivity (0.9958). The application of machine learning techniques facilitated the development of a precise model for predicting SSI after posterior cervical surgery. This dynamic model can be served as a valuable tool for clinicians and patients to assess SSI risk and prevent it in clinical practice.

Predicting sepsis in-hospital mortality with machine learning: a multi-center study using clinical and inflammatory biomarkers

BACKGROUND

This study aimed to develop and validate an interpretable machine-learning model that utilizes clinical features and inflammatory biomarkers to predict the risk of in-hospital mortality in critically ill patients suffering from sepsis.

METHODS

We enrolled all patients diagnosed with sepsis in the Medical Information Mart for Intensive Care IV (MIMIC-IV, v.2.0), eICU Collaborative Research Care (eICU-CRD 2.0), and the Amsterdam University Medical Centers databases (AmsterdamUMCdb 1.0.2). LASSO regression was employed for feature selection. Seven machine-learning methods were applied to develop prognostic models. The optimal model was chosen based on its accuracy, F1 score and area under curve (AUC) in the validation cohort. Moreover, we utilized the SHapley Additive exPlanations (SHAP) method to elucidate the effects of the features attributed to the model and analyze how individual features affect the model's output. Finally, Spearman correlation analysis examined the associations among continuous predictor variables. Restricted cubic splines (RCS) explored potential non-linear relationships between continuous risk factors and in-hospital mortality.

RESULTS

3535 patients with sepsis were eligible for participation in this study. The median age of the participants was 66 years (IQR, 55-77 years), and 56% were male. After selection, 12 of the 45 clinical parameters collected on the first day after ICU admission remained associated with prognosis and were used to develop machine-learning models. Among seven constructed models, the eXtreme Gradient Boosting (XGBoost) model achieved the best performance, with an AUC of 0.94 and an F1 score of 0.937 in the validation cohort. Feature importance analysis revealed that Age, AST, invasive ventilation treatment, and serum urea nitrogen (BUN) were the top four features of the XGBoost model with the most significant impact. Inflammatory biomarkers may have prognostic value. Furthermore, SHAP force analysis illustrated how the constructed model visualized the prediction of the model.

CONCLUSIONS

This study demonstrated the potential of machine-learning approaches for early prediction of outcomes in patients with sepsis. The SHAP method could improve the interoperability of machine-learning models and help clinicians better understand the reasoning behind the outcome.

A predictive model for postoperative adverse outcomes following surgical treatment of acute type A aortic dissection based on machine learning

Acute type A aortic dissection (AAAD) has a high probability of postoperative adverse outcomes (PAO) after emergency surgery, so exploring the risk factors for PAO during hospitalization is key to reducing postoperative mortality and improving prognosis. An artificial intelligence approach was used to build a predictive model of PAO by clinical data-driven machine learning to predict the incidence of PAO after total arch repair for AAAD. This study included 380 patients with AAAD. The clinical features that are associated with PAO were selected using the LASSO regression analysis. Six different machine learning algorithms were tried for modeling, and the performance of each model was analyzed comprehensively using receiver operating characteristic curves, calibration curve, precision recall curve, and decision analysis curves. Explain the optimal model through Shapley Additive Explanation (SHAP) and perform an individualized risk assessment. After comprehensive analysis, the authors believe that the extreme gradient boosting (XGBoost) model is the optimal model, with better performance than other models. The authors successfully built a prediction model for PAO in AAAD patients based on the XGBoost algorithm and interpreted the model with the SHAP method, which helps to identify high-risk AAAD patients at an early stage and to adjust individual patient-related clinical treatment plans in a timely manner.

Early Prediction of Mortality for Septic Patients Visiting Emergency Room Based on Explainable Machine Learning: A Real-World Multicenter Study

BACKGROUND

Worldwide, sepsis is the leading cause of death in hospitals. If mortality rates in patients with sepsis can be predicted early, medical resources can be allocated efficiently. We constructed machine learning (ML) models to predict the mortality of patients with sepsis in a hospital emergency department.

METHODS

This study prospectively collected nationwide data from an ongoing multicenter cohort of patients with sepsis identified in the emergency department. Patients were enrolled from 19 hospitals between September 2019 and December 2020. For acquired data from 3,657 survivors and 1,455 deaths, six ML models (logistic regression, support vector machine, random forest, extreme gradient boosting [XGBoost], light gradient boosting machine, and categorical boosting [CatBoost]) were constructed using fivefold cross-validation to predict mortality. Through these models, 44 clinical variables measured on the day of admission were compared with six sequential organ failure assessment (SOFA) components (PaO2/FIO2 [PF], platelets (PLT), bilirubin, cardiovascular, Glasgow Coma Scale score, and creatinine). The confidence interval (CI) was obtained by performing 10,000 repeated measurements via random sampling of the test dataset. All results were explained and interpreted using Shapley's additive explanations (SHAP).

RESULTS

Of the 5,112 participants, CatBoost exhibited the highest area under the curve (AUC) of 0.800 (95% CI, 0.756-0.840) using clinical variables. Using the SOFA components for the same patient, XGBoost exhibited the highest AUC of 0.678 (95% CI, 0.626-0.730). As interpreted by SHAP, albumin, lactate, blood urea nitrogen, and international normalization ratio were determined to significantly affect the results. Additionally, PF and PLTs in the SOFA component significantly influenced the prediction results.

CONCLUSION

Newly established ML-based models achieved good prediction of mortality in patients with sepsis. Using several clinical variables acquired at the baseline can provide more accurate results for early predictions than using SOFA components. Additionally, the impact of each variable was identified.

Deep learning-based prediction of in-hospital mortality for sepsis

As a serious blood infection disease, sepsis is characterized by a high mortality risk and many complications. Accurate assessment of mortality risk of patients with sepsis can help physicians in Intensive Care Unit make optimal clinical decisions, which in turn can effectively save patients' lives. However, most of the current clinical models used for assessing mortality risk in sepsis patients are based on conventional indicators. Unfortunately, some of the conventional indicators have been shown to be inapplicable in the accurate clinical diagnosis nowadays. Meanwhile, traditional evaluation models only focus on a small amount of personal data, causing misdiagnosis of sepsis patients. We refine the core indicators for mortality risk assessment of sepsis from massive clinical electronic medical records with machine learning, and propose a new mortality risk assessment model, DGFSD, for sepsis patients based on deep learning. The DGFSD model can not only learn individual clinical information about unassessed patients, but also obtain information about the structure of the similarity graph between diagnosed patients and patients to be assessed. Numerous experiments have shown that the accuracy of the DGFSD model is superior to baseline methods, and can significantly improve the efficiency of clinical auxiliary diagnosis.

Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis

BACKGROUND AND OBJECTIVES

Sepsis is accompanied by a considerably high risk of mortality in the short term, despite the availability of recommended mortality risk assessment tools. However, these risk assessment tools seem to have limited predictive value. With the gradual integration of machine learning into clinical practice, some researchers have attempted to employ machine learning for early mortality risk prediction in sepsis patients. Nevertheless, there is a lack of comprehensive understanding regarding the construction of predictive variables using machine learning and the value of various machine learning methods. Thus, we carried out this systematic review and meta-analysis to explore the predictive value of machine learning for sepsis-related death at different time points.

METHODS

PubMed, Embase, Cochrane, and Web of Science databases were searched until August 9th, 2022. The risk of bias in predictive models was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST). We also performed subgroup analysis according to time of death and type of model and summarized current predictive variables used to construct models for sepsis death prediction.

RESULTS

Fifty original studies were included, covering 104 models. The combined Concordance index (C-index), sensitivity, and specificity of machine learning models were 0.799, 0.81, and 0.80 in the training set, and 0.774, 0.71, and 0.68 in the validation set, respectively. Machine learning outperformed conventional clinical scoring tools and showed excellent C-index, sensitivity, and specificity in different subgroups. Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) are the preferred machine learning models because they showed more favorable accuracy with similar modeling variables. This study found that lactate was the most frequent predictor but was seriously ignored by current clinical scoring tools.

CONCLUSION

Machine learning methods demonstrate relatively favorable accuracy in predicting the mortality risk in sepsis patients. Given the limitations in accuracy and applicability of existing prediction scoring systems, there is an opportunity to explore updates based on existing machine learning approaches. Specifically, it is essential to develop or update more suitable mortality risk assessment tools based on the specific contexts of use, such as emergency departments, general wards, and intensive care units.

PARSE: A personalized clinical time-series representation learning framework via abnormal offsets analysis

BACKGROUND AND OBJECTIVE

Clinical risk prediction of patients is an important research issue in the field of healthcare, which is of great significance for the diagnosis, treatment and prevention of diseases. In recent years, a large number of deep learning-based methods have been proposed for clinical prediction by mining relevant features of patients' health condition from historical Electronic Health Records (EHRs) data. However, most of these existing methods only focus on discovering the time series characteristics of physiological indexes such as laboratory tests and physical examinations, and fail to comprehensively consider the deviation degree of these physiological indexes from the normal range and their stability, thus greatly limiting the prediction performance.

METHODS

We propose a personalized clinical time-series representation learning framework via abnormal offsets analysis named PARSE for clinical risk prediction. In PARSE, while extracting relevant temporal features from the original EHR data, we further capture relevant features of abnormal condition as complementary information from the absolute offset of each physiological index's observed values from its normal value and the relative offset between each physiological index's observed values in two adjacent time steps. Finally, an adaptive fusion module is introduced to effectively integrate the above features to obtain the personalized patient's representations for clinical risk prediction.

RESULTS

We conduct an in-hospital mortality prediction task on two public real-world datasets. PARSE achieves the highest F1 scores of 48.1% and 40.3%, outperforming the state-of-the-art methods with a boost of 2.4% and 6.2% on two datasets respectively. Furthermore, the results of ablation experiments demonstrate that the two abnormal offsets and the proposed adaptive fusion method are contributing.

CONCLUSIONS

PARSE can better extract the risk-related information from the EHRs data and improve the personalization of the patients' representations. Each part of PARSE improves the final prediction performance independently.

Phenotyping cardiogenic shock that showed different clinical outcomes and responses to vasopressor use: a latent profile analysis from MIMIC-IV database

Background

Cardiogenic shock (CS) is increasingly recognized as heterogeneous in its severity and response to therapies. This study aimed to identify CS phenotypes and their responses to the use of vasopressors.

Method

The current study included patients with CS complicating acute myocardial infarction (AMI) at the time of admission from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Laboratory and clinical variables were collected and used to conduct latent profile (LPA) analysis. Furthermore, we used a multivariable logistic regression (LR) model to explore the independent association between the use of vasopressors and endpoints.

Result

A total of 630 eligible patients with CS after AMI were enrolled in the study. The LPA identified three profiles of CS: profile 1 (n = 259, 37.5%) was considered as the baseline group; profile 2 (n = 261, 37.8%) was characterized by advanced age, more comorbidities, and worse renal function; and profile 3 (n = 170, 24.6%) was characterized by systemic inflammatory response syndrome (SIRS)-related indexes and acid-base balance disturbance. Profile 3 showed the highest all-cause in-hospital mortality rate (45.9%), followed by profile 2 (43.3%), and profile 1 (16.6%). The LR analyses showed that the phenotype of CS was an independent prognostic factor for outcomes, and profiles 2 and 3 were significantly associated with a higher risk of in-hospital mortality (profile 2: odds ratio [OR] 3.95, 95% confidence interval [CI] 2.61-5.97, p < 0.001; profile 3: OR 3.90, 95%CI 2.48-6.13, p < 0.001) compared with profile 1. Vasopressor use was associated with an improved risk of in-hospital mortality for profile 2 (OR: 2.03, 95% CI: 1.15-3.60, p = 0.015) and profile 3 (OR: 2.91, 95% CI: 1.02-8.32, p = 0.047), respectively. The results of vasopressor use showed no significance for profile 1.

Conclusion

Three phenotypes of CS were identified, which showed different outcomes and responses to vasopressor use.

Machine learning prognosis model based on patient-reported outcomes for chronic heart failure patients after discharge

BACKGROUND

Patient-reported outcomes (PROs) can be obtained outside hospitals and are of great significance for evaluation of patients with chronic heart failure (CHF). The aim of this study was to establish a prediction model using PROs for out-of-hospital patients.

METHODS

CHF-PRO were collected in 941 patients with CHF from a prospective cohort. Primary endpoints were all-cause mortality, HF hospitalization, and major adverse cardiovascular events (MACEs). To establish prognosis models during the two years follow-up, six machine learning methods were used, including logistic regression, random forest classifier, extreme gradient boosting (XGBoost), light gradient boosting machine, naive bayes, and multilayer perceptron. Models were established in four steps, namely, using general information as predictors, using four domains of CHF-PRO, using both of them and adjusting the parameters. The discrimination and calibration were then estimated. Further analyze were performed for the best model. The top prediction variables were further assessed. The Shapley additive explanations (SHAP) method was used to explain black boxes of the models. Moreover, a self-made web-based risk calculator was established to facilitate the clinical application.

RESULTS

CHF-PRO showed strong prediction value and improved the performance of the models. Among the approaches, XGBoost of the parameter adjustment model had the highest prediction performance with an area under the curve of 0.754 (95% CI: 0.737 to 0.761) for death, 0.718 (95% CI: 0.717 to 0.721) for HF rehospitalization and 0.670 (95% CI: 0.595 to 0.710) for MACEs. The four domains of CHF-PRO, especially the physical domain, showed the most significant impact on the prediction of outcomes.

CONCLUSION

CHF-PRO showed strong prediction value in the models. The XGBoost models using variables based on CHF-PRO and the patient's general information provide prognostic assessment for patients with CHF. The self-made web-based risk calculator can be conveniently used to predict the prognosis for patients after discharge.

CLINICAL TRIAL REGISTRATION

URL: http://www.chictr.org.cn/index.aspx ; Unique identifier: ChiCTR2100043337.

Exploring a global interpretation mechanism for deep learning networks when predicting sepsis

The purpose of this study is to identify additional clinical features for sepsis detection through the use of a novel mechanism for interpreting black-box machine learning models trained and to provide a suitable evaluation for the mechanism. We use the publicly available dataset from the 2019 PhysioNet Challenge. It has around 40,000 Intensive Care Unit (ICU) patients with 40 physiological variables. Using Long Short-Term Memory (LSTM) as the representative black-box machine learning model, we adapted the Multi-set Classifier to globally interpret the black-box model for concepts it learned about sepsis. To identify relevant features, the result is compared against: (i) features used by a computational sepsis expert, (ii) clinical features from clinical collaborators, (iii) academic features from literature, and (iv) significant features from statistical hypothesis testing. Random Forest was found to be the computational sepsis expert because it had high accuracies for solving both the detection and early detection, and a high degree of overlap with clinical and literature features. Using the proposed interpretation mechanism and the dataset, we identified 17 features that the LSTM used for sepsis classification, 11 of which overlaps with the top 20 features from the Random Forest model, 10 with academic features and 5 with clinical features. Clinical opinion suggests, 3 LSTM features have strong correlation with some clinical features that were not identified by the mechanism. We also found that age, chloride ion concentration, pH and oxygen saturation should be investigated further for connection with developing sepsis. Interpretation mechanisms can bolster the incorporation of state-of-the-art machine learning models into clinical decision support systems, and might help clinicians to address the issue of early sepsis detection. The promising results from this study warrants further investigation into creation of new and improvement of existing interpretation mechanisms for black-box models, and into clinical features that are currently not used in clinical assessment of sepsis.

Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study

BACKGROUND

Risk stratification plays an essential role in the decision making for sepsis management, as existing approaches can hardly satisfy the need to assess this heterogeneous population. We aimed to develop and validate a machine learning model to predict in-hospital mortality in critically ill patients with sepsis.

METHODS

Adult patients fulfilling the definition of Sepsis-3 were included at a large tertiary medical center. Relevant clinical features were extracted within the first 24 h in ICU, re-classified into different genres, and utilized for model development under three strategies: "Basic + Lab", "Basic + Intervention", and "Whole" feature sets. Extreme gradient boosting (XGBoost) was compared with logistic regression (LR) and established severity scores. Temporal validation was conducted using admissions from 2017 to 2019.

RESULTS

The final cohort included 24,272 patients, of which 4013 patients formed the test cohort for temporal validation. The trained and fine-tuned XGBoost model with the whole feature set showed the best discriminatory ability in the test cohort with AUROC as 0.85, significantly higher than the XGBoost "Basic + Lab" model (0.83), the LR "Whole" model (0.82), SOFA (0.63), SAPS-II (0.73), and LODS score (0.74). The performance in varying subgroups remained robust, and predictors, such as increased urine output and supplemental oxygen therapy, were crucially correlated with improved survival when interpretability was explored.

CONCLUSIONS

We developed and validated a novel XGBoost-based model and demonstrated significantly improved performance to LR and other scores in predicting the mortality risks of sepsis patients in the hospital using features in the first 24 h.

Prediction of motor function in patients with traumatic brain injury using genetic algorithms modified back propagation neural network: A data-based study

Objective

Traumatic brain injury (TBI) is one of the leading causes of death and disability worldwide. In this study, the characteristics of the patients, who were admitted to the China Rehabilitation Research Center, were elucidated in the TBI database, and a prediction model based on the Fugl-Meyer assessment scale (FMA) was established using this database.

Methods

A retrospective analysis of 463 TBI patients, who were hospitalized from June 2016 to June 2020, was performed. The data of the patients used for this study included the age and gender of the patients, course of TBI, complications, and concurrent dysfunctions, which were assessed using FMA and other measures. The information was collected at the time of admission to the hospital and 1 month after hospitalization. After 1 month, a prediction model, based on the correlation analyses and a 1-layer genetic algorithms modified back propagation (GA-BP) neural network with 175 patients, was established to predict the FMA. The correlations between the predicted and actual values of 58 patients (prediction set) were described.

Results

Most of the TBI patients, included in this study, had severe conditions (70%). The main causes of the TBI were car accidents (56.59%), while the most common complication and dysfunctions were hydrocephalus (46.44%) and cognitive and motor dysfunction (65.23 and 63.50%), respectively. A total of 233 patients were used in the prediction model, studying the 11 prognostic factors, such as gender, course of the disease, epilepsy, and hydrocephalus. The correlation between the predicted and the actual value of 58 patients was R ² = 0.95.

Conclusion

The genetic algorithms modified back propagation neural network can predict motor function in patients with traumatic brain injury, which can be used as a reference for risk and prognosis assessment and guide clinical decision-making.

Data and model bias in artificial intelligence for healthcare applications in New Zealand

Introduction

Developments in Artificial Intelligence (AI) are adopted widely in healthcare. However, the introduction and use of AI may come with biases and disparities, resulting in concerns about healthcare access and outcomes for underrepresented indigenous populations. In New Zealand, Māori experience significant inequities in health compared to the non-Indigenous population. This research explores equity concepts and fairness measures concerning AI for healthcare in New Zealand.

Methods

This research considers data and model bias in NZ-based electronic health records (EHRs). Two very distinct NZ datasets are used in this research, one obtained from one hospital and another from multiple GP practices, where clinicians obtain both datasets. To ensure research equality and fair inclusion of Māori, we combine expertise in Artificial Intelligence (AI), New Zealand clinical context, and te ao Māori. The mitigation of inequity needs to be addressed in data collection, model development, and model deployment. In this paper, we analyze data and algorithmic bias concerning data collection and model development, training and testing using health data collected by experts. We use fairness measures such as disparate impact scores, equal opportunities and equalized odds to analyze tabular data. Furthermore, token frequencies, statistical significance testing and fairness measures for word embeddings, such as WEAT and WEFE frameworks, are used to analyze bias in free-form medical text. The AI model predictions are also explained using SHAP and LIME.

Results

This research analyzed fairness metrics for NZ EHRs while considering data and algorithmic bias. We show evidence of bias due to the changes made in algorithmic design. Furthermore, we observe unintentional bias due to the underlying pre-trained models used to represent text data. This research addresses some vital issues while opening up the need and opportunity for future research.

Discussions

This research takes early steps toward developing a model of socially responsible and fair AI for New Zealand's population. We provided an overview of reproducible concepts that can be adopted toward any NZ population data. Furthermore, we discuss the gaps and future research avenues that will enable more focused development of fairness measures suitable for the New Zealand population's needs and social structure. One of the primary focuses of this research was ensuring fair inclusions. As such, we combine expertise in AI, clinical knowledge, and the representation of indigenous populations. This inclusion of experts will be vital moving forward, proving a stepping stone toward the integration of AI for better outcomes in healthcare.

Explainable Machine-Learning Model for Prediction of In-Hospital Mortality in Septic Patients Requiring Intensive Care Unit Readmission

INTRODUCTION

Septic patients requiring intensive care unit (ICU) readmission are at high risk of mortality, but research focusing on the association of ICU readmission due to sepsis and mortality is limited. The aim of this study was to develop and validate a machine learning (ML) model for predicting in-hospital mortality in septic patients readmitted to the ICU using routinely available clinical data.

METHODS

The data used in this study were obtained from the Medical Information Mart for Intensive Care (MIMIC-IV, v1.0) database, between 2008 and 2019. The study cohort included patients with sepsis requiring ICU readmission. The data were randomly split into a training (75%) data set and a validation (25%) data set. Nine popular ML models were developed to predict mortality in septic patients readmitted to the ICU. The model with the best accuracy and area under the curve (A.C.) in the validation cohort was defined as the optimal model and was selected for further prediction studies. The SHAPELY Additive explanations (SHAP) values and Local Interpretable Model-Agnostic Explanation (LIME) methods were used to improve the interpretability of the optimal model.

RESULTS

A total of 1117 septic patients who had required ICU readmission during the study period were enrolled in the study. Of these participants, 434 (38.9%) were female, and the median (interquartile range [IQR]) age was 68.6 (58.4-79.2) years. The median (IQR) ICU interval duration was 2.60 (0.64-5.78) days. After feature selection, 31 of 47 clinical factors were ultimately chosen for use in model construction. Of the nine ML models tested, the best performance was achieved with the random forest (RF) model, with an A.C. of 0.81, an accuracy of 85% and a precision of 62% in the validation cohort. The SHAP summary analysis revealed that Glasgow Coma Scale score, urine output, blood urea nitrogen, lactate, platelet count and systolic blood pressure were the top six most important factors contributing to the RF model. Additionally, the LIME method demonstrated how the RF model works in terms of explaining risk of death prediction in septic patients requiring ICU readmission.

CONCLUSION

The ML models reported here showed a good prognostic prediction ability in septic patients requiring ICU readmission. Of the features selected, the parameters related to organ perfusion made the largest contribution to outcome prediction during ICU readmission in septic patients.

Development and internal validation of a machine-learning-developed model for predicting 1-year mortality after fragility hip fracture

Background

Fragility hip fracture increases morbidity and mortality in older adult patients, especially within the first year. Identification of patients at high risk of death facilitates modification of associated perioperative factors that can reduce mortality. Various machine learning algorithms have been developed and are widely used in healthcare research, particularly for mortality prediction. This study aimed to develop and internally validate 7 machine learning models to predict 1-year mortality after fragility hip fracture.

Methods

This retrospective study included patients with fragility hip fractures from a single center (Siriraj Hospital, Bangkok, Thailand) from July 2016 to October 2018. A total of 492 patients were enrolled. They were randomly categorized into a training group (344 cases, 70%) or a testing group (148 cases, 30%). Various machine learning techniques were used: the Gradient Boosting Classifier (GB), Random Forests Classifier (RF), Artificial Neural Network Classifier (ANN), Logistic Regression Classifier (LR), Naive Bayes Classifier (NB), Support Vector Machine Classifier (SVM), and K-Nearest Neighbors Classifier (KNN). All models were internally validated by evaluating their performance and the area under a receiver operating characteristic curve (AUC).

Results

For the testing dataset, the accuracies were GB model = 0.93, RF model = 0.95, ANN model = 0.94, LR model = 0.91, NB model = 0.89, SVM model = 0.90, and KNN model = 0.90. All models achieved high AUCs that ranged between 0.81 and 0.99. The RF model also provided a negative predictive value of 0.96, a positive predictive value of 0.93, a specificity of 0.99, and a sensitivity of 0.68.

Conclusions

Our machine learning approach facilitated the successful development of an accurate model to predict 1-year mortality after fragility hip fracture. Several machine learning algorithms (eg, Gradient Boosting and Random Forest) had the potential to provide high predictive performance based on the clinical parameters of each patient. The web application is available at www.hipprediction.com. External validation in a larger group of patients or in different hospital settings is warranted to evaluate the clinical utility of this tool.

Trial registration

Thai Clinical Trials Registry (22 February 2021; reg. no. TCTR20210222003).

Supplementary Information

The online version contains supplementary material available at 10.1186/s12877-022-03152-x.

Machine Learning Methods for Predicting Long-Term Mortality in Patients After Cardiac Surgery

Objective:

This study aims to construct and validate several machine learning (ML) algorithms to predict long-term mortality and identify risk factors in unselected patients post-cardiac surgery.

Methods

The Medical Information Mart for Intensive Care (MIMIC-III) database was used to perform a retrospective administrative database study. Candidate predictors consisted of the demographics, comorbidity, vital signs, laboratory test results, scoring systems, and treatment information on the first day of ICU admission. Four-year mortality was set as the study outcome. We used the ML methods of logistic regression (LR), artificial neural network (NNET), naïve bayes (NB), gradient boosting machine (GBM), adapting boosting (Ada), random forest (RF), bagged trees (BT), and eXtreme Gradient Boosting (XGB). The prognostic capacity and clinical utility of these ML models were compared using the area under the receiver operating characteristic curves (AUC), calibration curves, and decision curve analysis (DCA).

Results

Of 7,368 patients in MIMIC-III included in the final cohort, a total of 1,337 (18.15%) patients died during a 4-year follow-up. Among 65 variables extracted from the database, a total of 25 predictors were selected using recursive feature elimination and included in the subsequent analysis. The Ada model performed best among eight models in both discriminatory ability with the highest AUC of 0.801 and goodness of fit (visualized by calibration curve). Moreover, the DCA shows that the net benefit of the RF, Ada, and BT models surpassed that of other ML models for almost all threshold probability values. Additionally, through the Ada technique, we determined that red blood cell distribution width (RDW), blood urea nitrogen (BUN), SAPS II, anion gap (AG), age, urine output, chloride, creatinine, congestive heart failure, and SOFA were the Top 10 predictors in the feature importance rankings.

Conclusions

The Ada model performs best in predicting 4-year mortality after cardiac surgery among the eight ML models, which might have significant application in the development of early warning systems for patients following operations.

A time-incorporated SOFA score-based machine learning model for predicting mortality in critically ill patients: A multicenter, real-world study

BACKGROUND

Organ dysfunction (OD) assessment is essential in intensive care units (ICUs). However, current OD assessment scores merely describe the number and the severity of each OD, without evaluating the duration of organ injury. The objective of this study is to develop and validate a machine learning model based on the Sequential Organ Failure Assessment (SOFA) score for the prediction of mortality in critically ill patients.

MATERIAL AND METHODS

Data from the eICU Collaborative Research Database and Medical Information Mart for Intensive Care (MIMIC) -III were mixed for model development. The MIMIC-IV and Nanjing Jinling Hospital Surgical ICU database were used as external test set A and set B, respectively. The outcome of interest was in-ICU mortality. A modified SOFA model incorporating time-dimension (T-SOFA) was stepwise developed to predict ICU mortality using extreme gradient boosting (XGBoost), support vector machine, random forest and logistic regression algorithms. Time-dimensional features were calculated based on six consecutive SOFA scores collected every 12 h within the first three days of admission. The predictive performance was assessed with the area under the receiver operating characteristic curves (AUROC) and calibration plot.

RESULTS

A total of 82,132 patients from the real-world datasets were included in this study, and 7,494 patients (9.12%) died during their ICU stay. The T-SOFA M3 that incorporated the time-dimension features and age, using the XGBoost algorithm, significantly outperformed the original SOFA score in the validation set (AUROC 0.800 95% CI [0.787-0.813] vs. 0.693 95% CI [0.678-0.709], p < 0.01). Good discrimination and calibration were maintained in the test set A and B, with AUROC of 0.803, 95% CI [0.791-0.815] and 0.830, 95% CI [0.789-0.870], respectively.

CONCLUSIONS

The time-incorporated T-SOFA model could significantly improve the prediction performance of the original SOFA score and is of potential for identifying high-risk patients in future clinical application.

Interpretable Machine Learning for Early Prediction of Prognosis in Sepsis: A Discovery and Validation Study

Introduction

This study aimed to develop and validate an interpretable machine-learning model based on clinical features for early predicting in-hospital mortality in critically ill patients with sepsis.

Methods

We enrolled all patients with sepsis in the Medical Information Mart for Intensive Care IV (MIMIC-IV, v.1.0) database from 2008 to 2019. Lasso regression was used for feature selection. Seven machine-learning methods were applied to develop the models. The best model was selected based on its accuracy and area under curve (AUC) in the validation cohort. Furthermore, we employed the SHapley Additive exPlanations (SHAP) method to illustrate the effects of the features attributed to the model, and to analyze how the individual features affect the output of the model, and to visualize the Shapley value for a single individual.

Results

In total, 8,817 patients with sepsis were eligible for participation, the median age was 66.8 years (IQR, 55.9–77.1 years), and 3361 of 8817 participants (38.1%) were women. After selection, 25 of a total 57 clinical parameters collected on day 1 after ICU admission remained associated with prognosis and were used for developing the machine-learning models. Among seven constructed models, the eXtreme Gradient Boosting (XGBoost) model achieved the best performance with an AUC of 0.884 and an accuracy of 89.5% in the validation cohort. Feature importance analysis showed that Glasgow Coma Scale (GCS) score, blood urea nitrogen, respiratory rate, urine output, and age were the top 5 features of the XGBoost model with the greatest impact. Furthermore, SHAP force analysis illustrated how the constructed model visualized the individualized prediction of death.

Conclusions

We have demonstrated the potential of machine-learning approaches for predicting outcome early in patients with sepsis. The SHAP method could improve the interpretability of machine-learning models and help clinicians better understand the reasoning behind the outcome.

Graphical abstract

Supplementary Information

The online version contains supplementary material available at 10.1007/s40121-022-00628-6.

Sepsis-Associated Coagulopathy Predicts Hospital Mortality in Critically Ill Patients With Postoperative Sepsis

BACKGROUND

The incidence of coagulopathy, which was responsible for poor outcomes, was commonly seen among patients with sepsis. In the current study, we aim to determine whether the presence of sepsis-associated coagulopathy (SAC) predicts the clinical outcomes among critically ill patients with postoperative sepsis.

METHODS

We conducted a single-center retrospective cohort study by including patients with sepsis admitted to surgical ICU of Chinese PLA General Hospital from January 1, 2014 to December 31, 2018. Baseline characteristics and clinical outcomes were compared with respect to the presence of SAC. Kaplan-Meier analysis was applied to calculate survival rate, and Log-rank test was carried out to compare the differences between two groups. Furthermore, multivariable Cox and logistic and linear regression analysis were performed to assess the relationship between SAC and clinical outcomes, including hospital mortality, development of septic shock, and length of hospital stay (LOS), respectively. Additionally, both sensitivity and subgroup analyses were performed to further testify the robustness of our findings.

RESULTS

A total of 175 patients were included in the current study. Among all included patients, 41.1% (72/175) ICU patients were identified as having SAC. In-hospital mortality rates were significantly higher in the SAC group when compared to that of the No SAC group (37.5% vs. 11.7%; p < 0.001). By performing univariable and multivariable regression analyses, presence of SAC was demonstrated to significantly correlate with an increased in-hospital mortality for patients with sepsis in surgical ICU [Hazard ratio (HR), 3.75; 95% Confidence interval (CI), 1.90-7.40; p < 0.001]. Meanwhile, a complication of SAC was found to be the independent predictor of the development of septic shock [Odds ratio (OR), 4.11; 95% CI, 1.81-9.32; p = 0.001], whereas it was not significantly associated with prolonged hospital LOS (OR, 0.97; 95% CI, 0.83-1.14; p = 0.743).

CONCLUSION

The presence of SAC was significantly associated with increased risk of in-hospital death and septic shock among postoperative patients with sepsis admitted to ICU. Moreover, there was no statistical difference of hospital LOS between the SAC and no SAC groups.

Application of machine learning tools: Potential and useful approach for the prediction of type 2 diabetes mellitus based on the gut microbiome profile

The gut microbiota plays an important role in the regulation of the immune system and the metabolism of the host. The aim of the present study was to characterize the gut microbiota of patients with type 2 diabetes mellitus (T2DM). A total of 118 participants with newly diagnosed T2DM and 89 control subjects were recruited in the present study; six clinical parameters were collected and the quantity of 10 different types of bacteria was assessed in the fecal samples using quantitative PCR. Taking into consideration the six clinical variables and the quantity of the 10 different bacteria, 3 predictive models were established in the training set and test set, and evaluated using a confusion matrix, area under the receiver operating characteristic curve (AUC) values, sensitivity (recall), specificity, accuracy, positive predictive value and negative predictive value (npv). The abundance of Bacteroides, Eubacterium rectale and Roseburia inulinivorans was significantly lower in the T2DM group compared with the control group. However, the abundance of Enterococcus was significantly higher in the T2DM group compared with the control group. In addition, Faecalibacterium prausnitzii, Enterococcus and Roseburia inulinivorans were significantly associated with sex status while Bacteroides, Bifidobacterium, Enterococcus and Roseburia inulinivorans were significantly associated with older age. In the training set, among the three models, support vector machine (SVM) and XGboost models obtained AUC values of 0.72 and 0.70, respectively. In the test set, only SVM obtained an AUC value of 0.77, and the precision and specificity were both above 0.77, whereas the accuracy, recall and npv were above 0.60. Furthermore, Bifidobacterium, age and Roseburia inulinivorans played pivotal roles in the model. In conclusion, the SVM model exhibited the highest overall predictive power, thus the combined use of machine learning tools with gut microbiome profiling may be a promising approach for improving early prediction of T2DM in the near feature.

ACEI/ARB Medication During ICU Stay Decrease All-Cause In-hospital Mortality in Critically Ill Patients With Hypertension: A Retrospective Cohort Study Based on Machine Learning

Background: Hypertension is a rather common comorbidity among critically ill patients and hospital mortality might be higher among critically ill patients with hypertension (SBP ≥ 140 mmHg and/or DBP ≥ 90 mmHg). This study aimed to explore the association between ACEI/ARB medication during ICU stay and all-cause in-hospital mortality in these patients.

Methods: A retrospective cohort study was conducted based on data from Medical Information Mart for Intensive Care IV (MIMIC-IV) database, which consisted of more than 40,000 patients in ICU between 2008 and 2019 at Beth Israel Deaconess Medical Center. Adults diagnosed with hypertension on admission and those had high blood pressure (SBP ≥ 140 mmHg and/or DBP ≥ 90 mmHg) during ICU stay were included. The primary outcome was all-cause in-hospital mortality. Patients were divided into ACEI/ARB treated and non-treated group during ICU stay. Propensity score matching (PSM) was used to adjust potential confounders. Nine machine learning models were developed and validated based on 37 clinical and laboratory features of all patients. The model with the best performance was selected based on area under the receiver operating characteristic curve (AUC) followed by 5-fold cross-validation. After hyperparameter optimization using Grid and random hyperparameter search, a final LightGBM model was developed, and Shapley Additive exPlanations (SHAP) values were calculated to evaluate feature importance of each feature. The features closely associated with hospital mortality were presented as significant features.

Results: A total of 15,352 patients were enrolled in this study, among whom 5,193 (33.8%) patients were treated with ACEI/ARB. A significantly lower all-cause in-hospital mortality was observed among patients treated with ACEI/ARB (3.9 vs. 12.7%) as well as a lower 28-day mortality (3.6 vs. 12.2%). The outcome remained consistent after propensity score matching. Among nine machine learning models, the LightGBM model had the highest AUC = 0.9935. The SHAP plot was employed to make the model interpretable based on LightGBM model after hyperparameter optimization, showing that ACEI/ARB use was among the top five significant features, which were associated with hospital mortality.

Conclusions: The use of ACEI/ARB in critically ill patients with hypertension during ICU stay is related to lower all-cause in-hospital mortality, which was independently associated with increased survival in a large and heterogeneous cohort of critically ill hypertensive patients with or without kidney dysfunction.

Machine learning in perioperative medicine: a systematic review

Background

Risk stratification plays a central role in anesthetic evaluation. The use of Big Data and machine learning (ML) offers considerable advantages for collection and evaluation of large amounts of complex health-care data. We conducted a systematic review to understand the role of ML in the development of predictive post-surgical outcome models and risk stratification.

Methods

Following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines, we selected the period of the research for studies from 1 January 2015 up to 30 March 2021. A systematic search in Scopus, CINAHL, the Cochrane Library, PubMed, and MeSH databases was performed; the strings of research included different combinations of keywords: “risk prediction,” “surgery,” “machine learning,” “intensive care unit (ICU),” and “anesthesia” “perioperative.” We identified 36 eligible studies. This study evaluates the quality of reporting of prediction models using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) checklist.

Results

The most considered outcomes were mortality risk, systemic complications (pulmonary, cardiovascular, acute kidney injury (AKI), etc.), ICU admission, anesthesiologic risk and prolonged length of hospital stay. Not all the study completely followed the TRIPOD checklist, but the quality was overall acceptable with 75% of studies (Rev #2, comm #minor issue) showing an adherence rate to TRIPOD more than 60%. The most frequently used algorithms were gradient boosting (n = 13), random forest (n = 10), logistic regression (LR; n = 7), artificial neural networks (ANNs; n = 6), and support vector machines (SVM; n = 6). Models with best performance were random forest and gradient boosting, with AUC > 0.90.

Conclusions

The application of ML in medicine appears to have a great potential. From our analysis, depending on the input features considered and on the specific prediction task, ML algorithms seem effective in outcomes prediction more accurately than validated prognostic scores and traditional statistics. Thus, our review encourages the healthcare domain and artificial intelligence (AI) developers to adopt an interdisciplinary and systemic approach to evaluate the overall impact of AI on perioperative risk assessment and on further health care settings as well.

Predictive value of lymphocyte-to-monocyte ratio in critically Ill patients with atrial fibrillation: A propensity score matching analysis

Background

Inflammation plays a key role in the initiation and progression of atrial fibrillation (AF). Lymphocyte‐to‐monocyte ratio (LMR) has been proved to be a reliable predictor of many inflammation‐associated diseases, but little data are available on the relationship between LMR and AF. We aimed to evaluate the predictive value of LMR in predicting all‐cause mortality among AF patients.

Methods

Data of patients diagnosed with AF were retrieved from the Medical Information Mart for Intensive Care‐III (MIMIC‐III) database. X‐tile analysis was used to calculate the optimal cutoff value for LMR. The Cox regression model was used to assess the association of LMR and 28‐day, 90‐day, and 1‐year mortality. Additionally, a propensity score matching (PSM) method was performed to minimize the impact of potential confounders.

Results

A total of 3567 patients hospitalized with AF were enrolled in this study. The X‐tile software indicated that the optimal cutoff value of LMR was 2.67. A total of 1127 pairs were generated, and all the covariates were well balanced after PSM. The Cox proportional‐hazards model showed that patients with the low LMR (≤2.67) had a higher 1‐year all‐cause mortality than those with the high LMR (>2.67) in the study cohort before PSM (HR = 1.640, 95% CI: 1.437–1.872, p < 0.001) and after PSM (HR = 1.279, 95% CI: 1.094–1.495, p = 0.002). The multivariable Cox regression analysis for 28‐day and 90‐day mortality yielded similar results.

Conclusions

The lower LMR (≤2.67) was associated with a higher risk of 28‐day, 90‐day, and 1‐year all‐cause mortality, which might serve as an independent predictor in AF patients.

Predicting COVID-19 mortality risk in Toronto, Canada: a comparison of tree-based and regression-based machine learning methods

BACKGROUND

Coronavirus disease (COVID-19) presents an unprecedented threat to global health worldwide. Accurately predicting the mortality risk among the infected individuals is crucial for prioritizing medical care and mitigating the healthcare system's burden. The present study aimed to assess the predictive accuracy of machine learning methods to predict the COVID-19 mortality risk.

METHODS

We compared the performance of classification tree, random forest (RF), extreme gradient boosting (XGBoost), logistic regression, generalized additive model (GAM) and linear discriminant analysis (LDA) to predict the mortality risk among 49,216 COVID-19 positive cases in Toronto, Canada, reported from March 1 to December 10, 2020. We used repeated split-sample validation and k-steps-ahead forecasting validation. Predictive models were estimated using training samples, and predictive accuracy of the methods for the testing samples was assessed using the area under the receiver operating characteristic curve, Brier's score, calibration intercept and calibration slope.

RESULTS

We found XGBoost is highly discriminative, with an AUC of 0.9669 and has superior performance over conventional tree-based methods, i.e., classification tree or RF methods for predicting COVID-19 mortality risk. Regression-based methods (logistic, GAM and LASSO) had comparable performance to the XGBoost with slightly lower AUCs and higher Brier's scores.

CONCLUSIONS

XGBoost offers superior performance over conventional tree-based methods and minor improvement over regression-based methods for predicting COVID-19 mortality risk in the study population.

Machine learning identification of specific changes in myeloid cell phenotype during bloodstream infections

The early identification of bacteremia is critical for ensuring appropriate treatment of nosocomial infections in intensive care unit (ICU) patients. The aim of this study was to use flow cytometric data of myeloid cells as a biomarker of bloodstream infection (BSI). An eight-color antibody panel was used to identify seven monocyte and two dendritic cell subsets. In the learning cohort, immunophenotyping was applied to (1) control subjects, (2) postoperative heart surgery patients, as a model of noninfectious inflammatory responses, and (3) blood culture-positive patients. Of the complex changes in the myeloid cell phenotype, a decrease in myeloid and plasmacytoid dendritic cell numbers, increase in CD14⁺CD16⁺ inflammatory monocyte numbers, and upregulation of neutrophils CD64 and CD123 expression were prominent in BSI patients. An extreme gradient boosting (XGBoost) algorithm called the “infection detection and ranging score” (iDAR), ranging from 0 to 100, was developed to identify infection-specific changes in 101 phenotypic variables related to neutrophils, monocytes and dendritic cells. The tenfold cross-validation achieved an area under the receiver operating characteristic (AUROC) of 0.988 (95% CI 0.985–1) for the detection of bacteremic patients. In an out-of-sample, in-house validation, iDAR achieved an AUROC of 0.85 (95% CI 0.71–0.98) in differentiating localized from bloodstream infection and 0.95 (95% CI 0.89–1) in discriminating infected from noninfected ICU patients. In conclusion, a machine learning approach was used to translate the changes in myeloid cell phenotype in response to infection into a score that could identify bacteremia with high specificity in ICU patients.

Machine Learning Models for Predicting In-Hospital Mortality in Acute Aortic Dissection Patients

Background: Acute aortic dissection is a potentially fatal cardiovascular disorder associated with high mortality. However, current predictive models show a limited ability to efficiently and flexibly detect this mortality risk, and have been unable to discover a relationship between the mortality rate and certain variables. Thus, this study takes an artificial intelligence approach, whereby clinical data-driven machine learning was utilized to predict the in-hospital mortality of acute aortic dissection. Methods: Patients diagnosed with acute aortic dissection between January 2015 to December 2018 were voluntarily enrolled from the Second Xiangya Hospital of Central South University in the study. The diagnosis was defined by magnetic resonance angiography or computed tomography angiography, with an onset time of the symptoms being within 14 days. The analytical variables included demographic characteristics, physical examination, symptoms, clinical condition, laboratory results, and treatment strategies. The machine learning algorithms included logistic regression, decision tree, K nearest neighbor, Gaussian naive bayes, and extreme gradient boost (XGBoost). Evaluation of the predictive performance of the models was mainly achieved using the area under the receiver operating characteristic curve. SHapley Additive exPlanation was also implemented to interpret the final prediction model. Results: A total of 1,344 acute aortic dissection patients were recruited, including 1,071 (79.7%) patients in the survivor group and 273 (20.3%) patients in non-survivor group. The extreme gradient boost model was found to be the most effective model with the greatest area under the receiver operating characteristic curve (0.927, 95% CI: 0.860-0.968). The three most significant aspects of the extreme gradient boost importance matrix plot were treatment, type of acute aortic dissection, and ischemia-modified albumin levels. In the SHapley Additive exPlanation summary plot, medical treatment, type A acute aortic dissection, and higher ischemia-modified albumin level were shown to increase the risk of hospital-based mortality.

Development and validation of a novel blending machine learning model for hospital mortality prediction in ICU patients with Sepsis

Background

Early prediction of hospital mortality is crucial for ICU patients with sepsis. This study aimed to develop a novel blending machine learning (ML) model for hospital mortality prediction in ICU patients with sepsis.

Methods

Two ICU databases were employed: eICU Collaborative Research Database (eICU-CRD) and Medical Information Mart for Intensive Care III (MIMIC-III). All adult patients who fulfilled Sepsis-3 criteria were identified. Samples from eICU-CRD constituted training set and samples from MIMIC-III constituted test set. Stepwise logistic regression model was used for predictor selection. Blending ML model which integrated nine sorts of basic ML models was developed for hospital mortality prediction in ICU patients with sepsis. Model performance was evaluated by various measures related to discrimination or calibration.

Results

Twelve thousand five hundred fifty-eight patients from eICU-CRD were included as the training set, and 12,095 patients from MIMIC-III were included as the test set. Both the training set and the test set showed a hospital mortality of 17.9%. Maximum and minimum lactate, maximum and minimum albumin, minimum PaO2/FiO2 and age were important predictors identified by both random forest and extreme gradient boosting algorithm. Blending ML models based on corresponding set of predictors presented better discrimination than SAPS II (AUROC, 0.806 vs. 0.771; AUPRC 0.515 vs. 0.429) and SOFA (AUROC, 0.742 vs. 0.706; AUPRC 0.428 vs. 0.381) on the test set. In addition, calibration curves showed that blending ML models had better calibration than SAPS II.

Conclusions

The blending ML model is capable of integrating different sorts of basic ML models efficiently, and outperforms conventional severity scores in predicting hospital mortality among septic patients in ICU.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13040-021-00276-5.

Machine Learning Prediction Models for Mechanically Ventilated Patients: Analyses of the MIMIC-III Database

Background: Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the Simplified Acute Physiology Score II (SAPS II), Oxford Acute Severity of Illness Score (OASIS), and Sequential Organ Failure Assessment (SOFA), widely used in the general ICU population. We aimed to establish prediction scores on mechanically ventilated patients with the combination of these disease severity scores and other features available on the first day of admission.

Methods: A retrospective administrative database study from the Medical Information Mart for Intensive Care (MIMIC-III) database was conducted. The exposures of interest consisted of the demographics, pre-ICU comorbidity, ICU diagnosis, disease severity scores, vital signs, and laboratory test results on the first day of ICU admission. Hospital mortality was used as the outcome. We used the machine learning methods of k-nearest neighbors (KNN), logistic regression, bagging, decision tree, random forest, Extreme Gradient Boosting (XGBoost), and neural network for model establishment. A sample of 70% of the cohort was used for the training set; the remaining 30% was applied for testing. Areas under the receiver operating characteristic curves (AUCs) and calibration plots would be constructed for the evaluation and comparison of the models' performance. The significance of the risk factors was identified through models and the top factors were reported.

Results: A total of 28,530 subjects were enrolled through the screening of the MIMIC-III database. After data preprocessing, 25,659 adult patients with 66 predictors were included in the model analyses. With the training set, the models of KNN, logistic regression, decision tree, random forest, neural network, bagging, and XGBoost were established and the testing set obtained AUCs of 0.806, 0.818, 0.743, 0.819, 0.780, 0.803, and 0.821, respectively. The calibration curves of all the models, except for the neural network, performed well. The XGBoost model performed best among the seven models. The top five predictors were age, respiratory dysfunction, SAPS II score, maximum hemoglobin, and minimum lactate.

Conclusion: The current study indicates that models with the risk of factors on the first day could be successfully established for predicting mortality in ventilated patients. The XGBoost model performs best among the seven machine learning models.

MGP-AttTCN: An interpretable machine learning model for the prediction of sepsis

With a mortality rate of 5.4 million lives worldwide every year and a healthcare cost of more than 16 billion dollars in the USA alone, sepsis is one of the leading causes of hospital mortality and an increasing concern in the ageing western world. Recently, medical and technological advances have helped re-define the illness criteria of this disease, which is otherwise poorly understood by the medical society. Together with the rise of widely accessible Electronic Health Records, the advances in data mining and complex nonlinear algorithms are a promising avenue for the early detection of sepsis. This work contributes to the research effort in the field of automated sepsis detection with an open-access labelling of the medical MIMIC-III data set. Moreover, we propose MGP-AttTCN: a joint multitask Gaussian Process and attention-based deep learning model to early predict the occurrence of sepsis in an interpretable manner. We show that our model outperforms the current state-of-the-art and present evidence that different labelling heuristics lead to discrepancies in task difficulty. For instance, when predicting sepsis five hours prior to onset on our new realistic labels, our proposed model achieves an area under the ROC curve of 0.660 and an area under the PR curve of 0.483, whereas the (less interpretable) previous state-of-the-art model (MGP-TCN) achieves 0.635 AUROC and 0.460 AUPR and the popular commercial InSight model achieves 0.490 AUROC and 0.359 AUPR.

Identify the Characteristics of Metabolic Syndrome and Non-obese Phenotype: Data Visualization and a Machine Learning Approach

Introduction: A third of the world's population is classified as having Metabolic Syndrome (MetS). Traditional diagnostic criteria for MetS are based on three or more of five components. However, the outcomes of patients with different combinations of specific metabolic components are undefined. It is challenging to be discovered and introduce treatment in advance for intervention, since the related research is still insufficient.

Methods: This retrospective cohort study attempted to establish a method of visualizing metabolic components by using unsupervised machine learning and treemap technology to discover the relations between predicting factors and different metabolic components. Several supervised machine-learning models were used to explore significant predictors of MetS and to construct a powerful prediction model for preventive medicine.

Results: The random forest had the best performance with accuracy and c-statistic of 0.947 and 0.921, respectively, and found that body mass index, glycated hemoglobin, and controlled attenuation parameter (CAP) score were the optimal primary predictors of MetS. In treemap, high triglyceride level plus high fasting blood glucose or large waist circumference group had higher CAP scores (>260) than other groups. Moreover, 32.2% of patients with high CAP scores during 3 years of follow-up had metabolic diseases are observed. This reveals that the CAP score may be used for detecting MetS, especially for the non-obese MetS phenotype.

Conclusions: Machine learning and data visualization can illustrate the complicated relationships between metabolic components and potential risk factors for MetS.

Application of Machine Learning in Intensive Care Unit (ICU) Settings Using MIMIC Dataset: Systematic Review

Modern Intensive Care Units (ICUs) provide continuous monitoring of critically ill patients susceptible to many complications affecting morbidity and mortality. ICU settings require a high staff-to-patient ratio and generates a sheer volume of data. For clinicians, the real-time interpretation of data and decision-making is a challenging task. Machine Learning (ML) techniques in ICUs are making headway in the early detection of high-risk events due to increased processing power and freely available datasets such as the Medical Information Mart for Intensive Care (MIMIC). We conducted a systematic literature review to evaluate the effectiveness of applying ML in the ICU settings using the MIMIC dataset. A total of 322 articles were reviewed and a quantitative descriptive analysis was performed on 61 qualified articles that applied ML techniques in ICU settings using MIMIC data. We assembled the qualified articles to provide insights into the areas of application, clinical variables used, and treatment outcomes that can pave the way for further adoption of this promising technology and possible use in routine clinical decision-making. The lessons learned from our review can provide guidance to researchers on application of ML techniques to increase their rate of adoption in healthcare.

Prediction of Sepsis in COVID-19 Using Laboratory Indicators

Background

The outbreak of coronavirus disease 2019 (COVID-19) has become a global public health concern. Many inpatients with COVID-19 have shown clinical symptoms related to sepsis, which will aggravate the deterioration of patients’ condition. We aim to diagnose Viral Sepsis Caused by SARS-CoV-2 by analyzing laboratory test data of patients with COVID-19 and establish an early predictive model for sepsis risk among patients with COVID-19.

Methods

This study retrospectively investigated laboratory test data of 2,453 patients with COVID-19 from electronic health records. Extreme gradient boosting (XGBoost) was employed to build four models with different feature subsets of a total of 69 collected indicators. Meanwhile, the explainable Shapley Additive ePlanation (SHAP) method was adopted to interpret predictive results and to analyze the feature importance of risk factors.

Findings

The model for classifying COVID-19 viral sepsis with seven coagulation function indicators achieved the area under the receiver operating characteristic curve (AUC) 0.9213 (95% CI, 89.94–94.31%), sensitivity 97.17% (95% CI, 94.97–98.46%), and specificity 82.05% (95% CI, 77.24–86.06%). The model for identifying COVID-19 coagulation disorders with eight features provided an average of 3.68 (±) 4.60 days in advance for early warning prediction with 0.9298 AUC (95% CI, 86.91–99.04%), 82.22% sensitivity (95% CI, 67.41–91.49%), and 84.00% specificity (95% CI, 63.08–94.75%).

Interpretation

We found that an abnormality of the coagulation function was related to the occurrence of sepsis and the other routine laboratory test represented by inflammatory factors had a moderate predictive value on coagulopathy, which indicated that early warning of sepsis in COVID-19 patients could be achieved by our established model to improve the patient’s prognosis and to reduce mortality.

Role of Artificial Intelligence (AI) in Surgery: Introduction, General Principles, and Potential Applications

AI (Artificial intelligence) is an interdisciplinary field aimed at the development of algorithms to endow machines with the capability of executing cognitive tasks. The number of publications regarding AI and surgery has increased dramatically over the last two decades. This phenomenon can partly be explained by the exponential growth in computing power available to the largest AI training runs. AI can be classified into different sub-domains with extensive potential clinical applications in the surgical setting. AI will increasingly become a major component of clinical practice in surgery. The aim of the present Narrative Review is to give a general introduction and summarized overview of AI, as well as to present additional remarks on potential surgical applications and future perspectives in surgery.