Machine Learning and Decision Support in Critical Care

Artificial intelligence and machine learning: Definition of terms and current concepts in critical care research

With increasing computing power, artificial intelligence (AI) and machine learning (ML) have prospered, which facilitate the analysis of large datasets, especially those found in critical care. It is important to define these terminologies, to inform a standardized approach to critical care research. This manuscript hopes to clarify these terms with examples from medical literature. Three major components that are required for a successful ML implementation: (i) reliable dataset, (ii) ML algorithm, and (iii) unbiased model evaluation, are discussed. A reliable dataset can be structured or unstructured with limited noise, outliers, and missing values. ML, a subset of AI, is typically focused on supervised or unsupervised learning tasks in which the output is based on inputs and derived from iterative pattern recognition algorithms, while AI is the overall ability of a machine to "think" or mimic human behavior; and to analyze data free from human influence. Even with successful implementation, advanced AI and ML algorithms have faced challenges in adoption into practice, mainly due to their lack of interpretability, which hinders trust, buy-in, and engagement from clinicians. Consequently, traditional algorithms, such as linear and logistic regression, that may have reduced predictive power but are highly interpretable, continue to be widely used.

The value of artificial intelligence for the treatment of mechanically ventilated intensive care unit patients: An early health technology assessment

PURPOSE

The health and economic consequences of artificial intelligence (AI) systems for mechanically ventilated intensive care unit patients often remain unstudied. Early health technology assessments (HTA) can examine the potential impact of AI systems by using available data and simulations. Therefore, we developed a generic health-economic model suitable for early HTA of AI systems for mechanically ventilated patients.

MATERIALS AND METHODS

Our generic health-economic model simulates mechanically ventilated patients from their hospitalisation until their death. The model simulates two scenarios, care as usual and care with the AI system, and compares these scenarios to estimate their cost-effectiveness.

RESULTS

The generic health-economic model we developed is suitable for estimating the cost-effectiveness of various AI systems. By varying input parameters and assumptions, the model can examine the cost-effectiveness of AI systems across a wide range of different clinical settings.

CONCLUSIONS

Using the proposed generic health-economic model, investors and innovators can easily assess whether implementing a certain AI system is likely to be cost-effective before an exact clinical impact is determined. The results of the early HTA can aid investors and innovators in deployment of AI systems by supporting development decisions, informing value-based pricing, clinical trial design, and selection of target patient groups.

Machine learning in cardiac surgery: a narrative review

Background and Objective

Machine learning (ML) is increasingly being utilized to provide data driven solutions to challenges in medicine. Within the field of cardiac surgery, ML methods have been employed as risk stratification tools to predict a variety of operative outcomes. However, the clinical utility of ML in this domain is unclear. The aim of this review is to provide an overview of ML in cardiac surgery, particularly with regards to its utility in predictive analytics and implications for use in clinical decision support.

Methods

We performed a narrative review of relevant articles indexed in PubMed since 2000 using the MeSH terms "Machine Learning", "Supervised Machine Learning", "Deep Learning", or "Artificial Intelligence" and "Cardiovascular Surgery" or "Thoracic Surgery".

Key Content and Findings

ML methods have been widely used to generate pre-operative risk profiles, consistently resulting in the accurate prediction of clinical outcomes in cardiac surgery. However, improvement in predictive performance over traditional risk metrics has proven modest and current applications in the clinical setting remain limited.

Conclusions

Studies utilizing high volume, multidimensional data such as that derived from electronic health record (EHR) data appear to best demonstrate the advantages of ML methods. Models trained on post cardiac surgery intensive care unit data demonstrate excellent predictive performance and may provide greater clinical utility if incorporated as clinical decision support tools. Further development of ML models and their integration into EHR's may result in dynamic clinical decision support strategies capable of informing clinical care and improving outcomes in cardiac surgery.

Machine learning models for predicting unscheduled return visits of patients with abdominal pain at emergency department and validation during COVID-19 pandemic: A retrospective cohort study

Machine learning (ML) models for predicting 72-hour unscheduled return visits (URVs) for patients with abdominal pain in the emergency department (ED) were developed in a previous study. This study refined the data to adjust previous prediction models and evaluated the model performance in future data validation during the COVID-19 era. We aimed to evaluate the practicality of the ML models and compare the URVs before and during the COVID-19 pandemic. We used electronic health records from Chang Gung Memorial Hospital from 2018 to 2019 as a training dataset, and various machine learning models, including logistic regression (LR), random forest (RF), extreme gradient boosting (XGB), and voting classifier (VC) were developed and subsequently used to validate against the 2020 to 2021 data. The models highlighted several determinants for 72-hour URVs, including patient age, prior ER visits, specific vital signs, and medical interventions. The LR, XGB, and VC models exhibited the same AUC of 0.71 in the testing set, whereas the VC model displayed a higher F1 score (0.21). The XGB model demonstrated the highest specificity (0.99) and precision (0.64) but the lowest sensitivity (0.01). Among these models, the VC model showed the most favorable, balanced, and comprehensive performance. Despite the promising results, the study illuminated challenges in predictive modeling, such as the unforeseen influences of global events, such as the COVID-19 pandemic. These findings not only highlight the significant potential of machine learning in augmenting emergency care but also underline the importance of iterative refinement in response to changing real-world conditions.

Machine learning models for predicting unscheduled return visits to an emergency department: a scoping review

BACKGROUND

Unscheduled return visits (URVs) to emergency departments (EDs) are used to assess the quality of care in EDs. Machine learning (ML) models can incorporate a wide range of complex predictors to identify high-risk patients and reduce errors to save time and cost. However, the accuracy and practicality of such models are questionable. This review compares the predictive power of multiple ML models and examines the effects of multiple research factors on these models' performance in predicting URVs to EDs.

METHODS

We conducted the present scoping review by searching eight databases for data from 2010 to 2023. The criteria focused on eligible articles that used ML to predict ED return visits. The primary outcome was the predictive performances of the ML models, and results were analyzed on the basis of intervals of return visits, patient population, and research scale.

RESULTS

A total of 582 articles were identified through the database search, with 14 articles selected for detailed analysis. Logistic regression was the most widely used method; however, eXtreme Gradient Boosting generally exhibited superior performance. Variations in visit interval, target group, and research scale did not significantly affect the predictive power of the models.

CONCLUSION

This is the first study to summarize the use of ML for predicting URVs in ED patients. The development of practical ML prediction models for ED URVs is feasible, but improving the accuracy of predicting ED URVs to beyond 0.75 remains a challenge. Including multiple data sources and dimensions is key for enabling ML models to achieve high accuracy; however, such inclusion could be challenging within a limited timeframe. The application of ML models for predicting ED URVs may improve patient safety and reduce medical costs by decreasing the frequency of URVs. Further research is necessary to explore the real-world efficacy of ML models.

Predicting long-term neurocognitive outcome after pediatric intensive care unit admission for bronchiolitis-preliminary exploration of the potential of machine learning

PURPOSE

For successful prevention and intervention, it is important to unravel the complex constellation of factors that affect neurocognitive functioning after pediatric intensive care unit (PICU) admission. This study aims (1) to elucidate the potential relevance of patient and PICU-related characteristics for long-term adverse neurocognitive outcome after PICU admission for bronchiolitis, and (2) to perform a preliminary exploration of the potential of machine learning as compared to linear regression to improve neurocognitive outcome prediction in a relatively small sample of children after PICU admission.

METHODS

This cross-sectional observational study investigated 65 children aged 6-12 years with previous PICU admission for bronchiolitis (age ≤ 1 year). They were compared to demographically comparable healthy peers (n = 76) on neurocognitive functioning. Patient and PICU-related characteristics used for the prediction models were as follows: demographic characteristics, perinatal and disease parameters, laboratory results, and intervention characteristics, including hourly validated mechanical ventilation parameters. Neurocognitive outcome was measured by intelligence and computerized neurocognitive testing. Prediction models were developed for each of the neurocognitive outcomes using Regression Trees, k-Nearest Neighbors, and conventional linear regression analysis.

RESULTS

The patient group had lower intelligence than the control group (p < .001, d = -0.59) and poorer performance in neurocognitive functions, i.e., speed and attention (p = .03, d = -0.41) and verbal memory (p < .001, d = -0.60). Lower intelligence was predicted by lower birth weight and lower socioeconomic status (R2 = 25.9%). Poorer performance on the speed and attention domain was predicted by younger age at follow-up (R2 = 53.5%). Poorer verbal memory was predicted by lower birth weight, younger age at follow-up, and greater exposure to acidotic events (R2 = 50.6%). The machine learning models did not reveal added value in terms of model performance as compared to linear regression.

CONCLUSION

The findings of this study suggest that in children with previous PICU admission for bronchiolitis, (1) lower birth weight, younger age at follow-up, and lower socioeconomic status are associated with poorer neurocognitive outcome; and (2) greater exposure to acidotic events during PICU admission is associated with poorer verbal memory outcome. The findings of this study provide no evidence for the added value of machine learning models as compared to linear regression analysis in the prediction of long-term neurocognitive outcome in a relatively small sample of children.

WHAT IS KNOWN

• Adverse neurocognitive outcomes are described in PICU survivors, which are known to interfere with development in other major domains of functioning, such as mental health, academic achievement, and socioeconomic success, highlighting neurocognition as an important outcome after PICU admission. • Machine learning is a rapidly growing field of artificial intelligence that is increasingly applied in health care settings, with great potential to capture the complexity of outcome prediction.

WHAT IS NEW

• This study shows that lower birth weight, lower socioeconomic status, and greater exposure to acidotic events during PICU admission for bronchiolitis are associated with poorer long-term neurocognitive outcome after PICU admission. Results provide no evidence for the added value of machine learning models in a relatively small sample of children. • As bronchiolitis seldom manifests neurologically, the relation between acidotic events and neurocognitive outcome may reflect either potentially harmful effects of acidosis itself or related processes such as hypercapnia or hypoxic and/or ischemic events during PICU admission. This study further highlights the importance of structured follow-up to monitor long-term outcome of children after PICU admission.

Determining Optimal Mean Arterial Blood Pressure Based on Cerebral Autoregulation in Children after Cardiac Surgery

To evaluate the feasibility of continuous determination of the optimal mean arterial blood pressure (opt-MAP) according to cerebral autoregulation and to describe the opt-MAP, the autoregulation limits, and the time spent outside these limits in children within 48 h of cardiac surgery. Cerebral autoregulation was assessed using the correlation coefficient (COx) between cerebral oxygenation and MAP in children following cardiac surgery. Plots depicting the COx according to the MAP were used to determine the opt-MAP using weighted multiple time windows. For each patient, we estimated (1) the time spent with MAP outside the autoregulation limits and (2) the burden of deviation, defined as the area between the MAP curve and the autoregulation limits when the MAP was outside these limits. Fifty-one patients with a median age of 7.1 (IQR 0.7-52.0) months old were included. The opt-MAP was calculated for 94% (IQR 90-96) of the monitored time. The opt-MAP was significantly lower in neonates < 1 month old. The patients spent 24% (18-31) of the time outside of the autoregulation limits, with no significant differences between age groups. Continuous determination of the opt-MAP is feasible in children within the first 48 h following cardiac surgery.

Improving mixed-integer temporal modeling by generating synthetic data using conditional generative adversarial networks: A case study of fluid overload prediction in the intensive care unit

OBJECTIVE

The challenge of mixed-integer temporal data, which is particularly prominent for medication use in the critically ill, limits the performance of predictive models. The purpose of this evaluation was to pilot test integrating synthetic data within an existing dataset of complex medication data to improve machine learning model prediction of fluid overload.

MATERIALS AND METHODS

This retrospective cohort study evaluated patients admitted to an ICU ≥ 72 h. Four machine learning algorithms to predict fluid overload after 48-72 h of ICU admission were developed using the original dataset. Then, two distinct synthetic data generation methodologies (synthetic minority over-sampling technique (SMOTE) and conditional tabular generative adversarial network (CTGAN)) were used to create synthetic data. Finally, a stacking ensemble technique designed to train a meta-learner was established. Models underwent training in three scenarios of varying qualities and quantities of datasets.

RESULTS

Training machine learning algorithms on the combined synthetic and original dataset overall increased the performance of the predictive models compared to training on the original dataset. The highest performing model was the meta-model trained on the combined dataset with 0.83 AUROC while it managed to significantly enhance the sensitivity across different training scenarios.

DISCUSSION

The integration of synthetically generated data is the first time such methods have been applied to ICU medication data and offers a promising solution to enhance the performance of machine learning models for fluid overload, which may be translated to other ICU outcomes. A meta-learner was able to make a trade-off between different performance metrics and improve the ability to identify the minority class.

Machine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis

Background

The health care system is undergoing a shift toward a more patient-centered approach for individuals with chronic and complex conditions, which presents a series of challenges, such as predicting hospital needs and optimizing resources. At the same time, the exponential increase in health data availability has made it possible to apply advanced statistics and artificial intelligence techniques to develop decision-support systems and improve resource planning, diagnosis, and patient screening. These methods are key to automating the analysis of large volumes of medical data and reducing professional workloads.

Objective

This article aims to present a machine learning model and a case study in a cohort of patients with highly complex conditions. The object was to predict mortality within the following 4 years and early mortality over 6 months following diagnosis. The method used easily accessible variables and health care resource utilization information.

Methods

A classification algorithm was selected among 6 models implemented and evaluated using a stratified cross-validation strategy with k=10 and a 70/30 train-test split. The evaluation metrics used included accuracy, recall, precision, F1-score, and area under the receiver operating characteristic (AUROC) curve.

Results

The model predicted patient death with an 87% accuracy, recall of 87%, precision of 82%, F1-score of 84%, and area under the curve (AUC) of 0.88 using the best model, the Extreme Gradient Boosting (XGBoost) classifier. The results were worse when predicting premature deaths (following 6 months) with an 83% accuracy (recall=55%, precision=64% F1-score=57%, and AUC=0.88) using the Gradient Boosting (GRBoost) classifier.

Conclusions

This study showcases encouraging outcomes in forecasting mortality among patients with intricate and persistent health conditions. The employed variables are conveniently accessible, and the incorporation of health care resource utilization information of the patient, which has not been employed by current state-of-the-art approaches, displays promising predictive power. The proposed prediction model is designed to efficiently identify cases that need customized care and proactively anticipate the demand for critical resources by health care providers.

Advancing prognostic precision in pulmonary embolism: A clinical and laboratory-based artificial intelligence approach for enhanced early mortality risk stratification

BACKGROUND

Acute pulmonary embolism (PE) is a critical medical emergency that necessitates prompt identification and intervention. Accurate prognostication of early mortality is vital for recognizing patients at elevated risk for unfavourable outcomes and administering suitable therapy. Machine learning (ML) algorithms hold promise for enhancing the precision of early mortality prediction in PE patients.

OBJECTIVE

To devise an ML algorithm for early mortality prediction in PE patients by employing clinical and laboratory variables.

METHODS

This study utilized diverse oversampling techniques to improve the performance of various machine learning models including ANN, SVM, DT, RF, and AdaBoost for early mortality prediction. Appropriate oversampling methods were chosen for each model based on algorithm characteristics and dataset properties. Predictor variables included four lab tests, eight physiological time series indicators, and two general descriptors. Evaluation used metrics like accuracy, F1_score, precision, recall, Area Under the Curve (AUC) and Receiver Operating Characteristic (ROC) curves, providing a comprehensive view of models' predictive abilities.

RESULTS

The findings indicated that the RF model with random oversampling exhibited superior performance among the five models assessed, achieving elevated accuracy and precision alongside high recall for predicting the death class. The oversampling approaches effectively equalized the sample distribution among the classes and enhanced the models' performance.

CONCLUSIONS

The suggested ML technique can efficiently prognosticate mortality in patients afflicted with acute PE. The RF model with random oversampling can aid healthcare professionals in making well-informed decisions regarding the treatment of patients with acute PE. The study underscores the significance of oversampling methods in managing imbalanced data and emphasizes the potential of ML algorithms in refining early mortality prediction for PE patients.

Machine learning-based prediction models for pressure injury: A systematic review and meta-analysis

Despite the fact that machine learning (ML) algorithms to construct predictive models for pressure injury development are widely reported, the performance of the model remains unknown. The goal of the review was to systematically appraise the performance of ML models in predicting pressure injury. PubMed, Embase, Cochrane Library, Web of Science, CINAHL, Grey literature and other databases were systematically searched. Original journal papers were included which met the inclusion criteria. The methodological quality was assessed independently by two reviewers using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Meta-analysis was performed with Metadisc software, with the area under the receiver operating characteristic curve, sensitivity and specificity as effect measures. Chi-squared and I2 tests were used to assess the heterogeneity. A total of 18 studies were included for the narrative review, and 14 of them were eligible for meta-analysis. The models achieved excellent pooled AUC of 0.94, sensitivity of 0.79 (95% CI [0.78-0.80]) and specificity of 0.87 (95% CI [0.88-0.87]). Meta-regressions did not provide evidence that model performance varied by data or model types. The present findings indicate that ML models show an outstanding performance in predicting pressure injury. However, good-quality studies should be conducted to verify our results and confirm the clinical value of ML in pressure injury development.

Personalized antiseizure medication therapy in critically ill adult patients

Precision medicine has the potential to have a significant impact on both drug development and patient care. It is crucial to not only provide prompt effective antiseizure treatment for critically ill patients after seizures start but also have a proactive mindset and concentrate on epileptogenesis and the underlying cause of the seizures or seizure disorders. Critical illness presents different treatment issues compared with the ambulatory population, which makes it challenging to choose the best antiseizure medications and to administer them at the right time and at the right dose. Since there is a paucity of information available on antiseizure medication dosing in critically ill patients, therapeutic drug monitoring is a useful tool for defining each patient's personal therapeutic range and assisting clinicians in decision-making. Use of pharmacogenomic information relating to pharmacokinetics, hepatic metabolism, and seizure etiology may improve safety and efficacy by individualizing therapy. Studies evaluating the clinical implementation of pharmacogenomic information at the point-of-care and identification of biomarkers are also needed. These studies may make it possible to avoid adverse drug reactions, maximize drug efficacy, reduce drug-drug interactions, and optimize medications for each individual patient. This review will discuss the available literature and provide future insights on precision medicine use with antiseizure therapy in critically ill adult patients.

Improving irregular temporal modeling by integrating synthetic data to the electronic medical record using conditional GANs: a case study of fluid overload prediction in the intensive care unit

Objective

The challenge of irregular temporal data, which is particularly prominent for medication use in the critically ill, limits the performance of predictive models. The purpose of this evaluation was to pilot test integrating synthetic data within an existing dataset of complex medication data to improve machine learning model prediction of fluid overload.

Materials and Methods

This retrospective cohort study evaluated patients admitted to an ICU ≥ 72 hours. Four machine learning algorithms to predict fluid overload after 48-72 hours of ICU admission were developed using the original dataset. Then, two distinct synthetic data generation methodologies (synthetic minority over-sampling technique (SMOTE) and conditional tabular generative adversarial network (CT-GAN)) were used to create synthetic data. Finally, a stacking ensemble technique designed to train a meta-learner was established. Models underwent training in three scenarios of varying qualities and quantities of datasets.

Results

Training machine learning algorithms on the combined synthetic and original dataset overall increased the performance of the predictive models compared to training on the original dataset. The highest performing model was the metamodel trained on the combined dataset with 0.83 AUROC while it managed to significantly enhance the sensitivity across different training scenarios.

Discussion

The integration of synthetically generated data is the first time such methods have been applied to ICU medication data and offers a promising solution to enhance the performance of machine learning models for fluid overload, which may be translated to other ICU outcomes. A meta-learner was able to make a trade-off between different performance metrics and improve the ability to identify the minority class.

Predicting in-hospital outcomes of patients with acute kidney injury

Acute kidney injury (AKI) is prevalent and a leading cause of in-hospital death worldwide. Early prediction of AKI-related clinical events and timely intervention for high-risk patients could improve outcomes. We develop a deep learning model based on a nationwide multicenter cooperative network across China that includes 7,084,339 hospitalized patients, to dynamically predict the risk of in-hospital death (primary outcome) and dialysis (secondary outcome) for patients who developed AKI during hospitalization. A total of 137,084 eligible patients with AKI constitute the analysis set. In the derivation cohort, the area under the receiver operator curve (AUROC) for 24-h, 48-h, 72-h, and 7-day death are 95·05%, 94·23%, 93·53%, and 93·09%, respectively. For dialysis outcome, the AUROC of each time span are 88·32%, 83·31%, 83·20%, and 77·99%, respectively. The predictive performance is consistent in both internal and external validation cohorts. The model can predict important outcomes of patients with AKI, which could be helpful for the early management of AKI.

Machine learning using institution-specific multi-modal electronic health records improves mortality risk prediction for cardiac surgery patients

Background

The Society of Thoracic Surgeons risk scores are widely used to assess risk of morbidity and mortality in specific cardiac surgeries but may not perform optimally in all patients. In a cohort of patients undergoing cardiac surgery, we developed a data-driven, institution-specific machine learning-based model inferred from multi-modal electronic health records and compared the performance with the Society of Thoracic Surgeons models.

Methods

All adult patients undergoing cardiac surgery between 2011 and 2016 were included. Routine electronic health record administrative, demographic, clinical, hemodynamic, laboratory, pharmacological, and procedural data features were extracted. The outcome was postoperative mortality. The database was randomly split into training (development) and test (evaluation) cohorts. Models developed using 4 classification algorithms were compared using 6 evaluation metrics. The performance of the final model was compared with the Society of Thoracic Surgeons models for 7 index surgical procedures.

Results

A total of 6392 patients were included and described by 4016 features. Overall mortality was 3.0% (n = 193). The XGBoost algorithm using only features with no missing data (336 features) yielded the best-performing predictor. When applied to the test set, the predictor performed well (F-measure = 0.775; precision = 0.756; recall = 0.795; accuracy = 0.986; area under the receiver operating characteristic curve = 0.978; area under the precision-recall curve = 0.804). eXtreme Gradient Boosting consistently demonstrated improved performance over the Society of Thoracic Surgeons models when evaluated on index procedures within the test set.

Conclusions

Machine learning models using institution-specific multi-modal electronic health records may improve performance in predicting mortality for individual patients undergoing cardiac surgery compared with the standard-of-care, population-derived Society of Thoracic Surgeons models. Institution-specific models may provide insights complementary to population-derived risk predictions to aid patient-level decision making.

Beyond Conventional Hemodynamic Monitoring-Monitoring to Improve Our Understanding of Disease Process and Interventions

Monitoring the hemodynamic state of patients is a hallmark of any intensive care environment. However, no single monitoring strategy can provide all the necessary data to paint the entire picture of the state of a patient; each monitor has strengths and weaknesses, advantages, and limitations. We review the currently available hemodynamic monitors used in pediatric critical care units using a clinical scenario. This provides the reader with a construct to understand the progression from basic to more advanced monitoring modalities and how they serve to inform the practitioner at the bedside.

Prediction of Acid-Base and Potassium Imbalances in Intensive Care Patients Using Machine Learning Techniques

Acid–base disorders occur when the body’s normal pH is out of balance. They can be caused by problems with kidney or respiratory function or by an excess of acids or bases that the body cannot properly eliminate. Acid–base and potassium imbalances are mechanistically linked because acid–base imbalances can alter the transport of potassium. Both acid–base and potassium imbalances are common in critically ill patients. This study investigated machine learning models for predicting the occurrence of acid–base and potassium imbalances in intensive care patients. We used an institutional dataset of 1089 patients with 87 variables, including vital signs, general appearance, and laboratory results. Gradient boosting (GB) was able to predict nine clinical conditions related to acid–base and potassium imbalances: mortality (AUROC = 0.9822), hypocapnia (AUROC = 0.7524), hypercapnia (AUROC = 0.8228), hypokalemia (AUROC = 0.9191), hyperkalemia (AUROC = 0.9565), respiratory acidosis (AUROC = 0.8125), respiratory alkalosis (AUROC = 0.7685), metabolic acidosis (AUROC = 0.8682), and metabolic alkalosis (AUROC = 0.8284). Some predictions remained relatively robust even when the prediction window was increased. Additionally, the decision-making process was made more interpretable and transparent through the use of SHAP analysis. Overall, the results suggest that machine learning could be a useful tool to gain insight into the condition of intensive care patients and assist in the management of acid–base and potassium imbalances.

Tendency of dynamic vasoactive and inotropic medications data as a robust predictor of mortality in patients with septic shock: An analysis of the MIMIC-IV database

Background

Septic shock patients fundamentally require delicate vasoactive and inotropic agent administration, which could be quantitatively and objectively evaluated by the vasoactive–inotropic score (VIS); however, whether the dynamic trends of high-time-resolution VIS alter the clinical outcomes remains unclear. Thus, this study proposes the term VIS Reduction Rate (VRR) to generalise the tendency of dynamic VIS, to explore the association of VRR and mortality for patients with septic shock.

Methods

We applied dynamic and static VIS data to predict ICU mortality by two models: the long short-term memory (LSTM) deep learning model, and the extreme gradient boosting (XGBoost), respectively. The specific target cohort was extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database by the sophisticated structured query language (SQL). Enrolled patients were divided into four groups by VRR value: ≥50%, 0 ~ 50%, −50% ~ 0, and &lt; −50%. Statistical approaches included pairwise propensity score matching (PSM), Cox proportional hazards regression, and two doubly robust estimation models to ensure the robustness of the results. The primary and secondary outcomes were ICU mortality and in-hospital mortality, respectively.

Results

VRR simplifies the dosing trends of vasoactive and inotropic agents represented by dynamic VIS data while requiring fewer data. In total, 8,887 septic shock patients were included. Compared with the VRR ≥50% group, the 0 ~ 50%, −50% ~ 0, and &lt; −50% groups had significantly higher ICU mortality [hazard ratio (HR) 1.32, 95% confidence interval (CI) 1.17–1.50, p &lt; 0.001; HR 1.79, 95% CI 1.44–2.22, p &lt; 0.001; HR 2.07, 95% CI 1.61–2.66, p &lt; 0.001, respectively] and in-hospital mortality [HR 1.43, 95% CI 1.28–1.60, p &lt; 0.001; HR 1.75, 95% CI 1.45–2.11, p &lt; 0.001; HR 2.00, 95% CI 1.61–2.49, p &lt; 0.001, respectively]. Similar findings were observed in two doubly robust estimation models.

Conclusion

The trends of dynamic VIS in ICU might help intensivists to stratify the prognosis of adult patients with septic shock. A lower decline of VIS was remarkably associated with higher ICU and in-hospital mortality among septic shock patients receiving vasoactive–inotropic therapy for more than 24 h.

Use of artificial intelligence in paediatric anaesthesia: a systematic review

Objectives

Although the development of artificial intelligence (AI) technologies in medicine has been significant, their application to paediatric anaesthesia is not well characterised. As the paediatric operating room is a data-rich environment that requires critical clinical decision-making, this systematic review aims to characterise the current use of AI in paediatric anaesthesia and to identify barriers to the successful integration of such technologies.

Methods

This review was registered with PROSPERO (CRD42022304610), the international registry for systematic reviews. The search strategy was prepared by a librarian and run in five electronic databases (Embase, Medline, Central, Scopus, and Web of Science). Collected articles were screened by two reviewers. Included studies described the use of AI for paediatric anaesthesia (<18 yr old) within the perioperative setting.

Results

From 3313 records identified in the initial search, 40 were included in this review. Identified applications of AI were described for patient risk factor prediction (24 studies; 60%), anaesthetic depth estimation (2; 5%), anaesthetic medication/technique decision guidance (2; 5%), intubation assistance (1; 2.5%), airway device selection (3; 7.5%), physiological variable monitoring (6; 15%), and operating room scheduling (2; 5%). Multiple domains of AI were discussed including machine learning, computer vision, fuzzy logic, and natural language processing.

Conclusion

There is an emerging literature regarding applications of AI for paediatric anaesthesia, and their clinical integration holds potential for ultimately improving patient outcomes. However, multiple barriers to their clinical integration remain including a lack of high-quality input data, lack of external validation/evaluation, and unclear generalisability to diverse settings.

Systematic review protocol

CRD42022304610 (PROSPERO).

Mortality prediction in severe traumatic brain injury using traditional and machine learning algorithms

Prognostic prediction of traumatic brain injury (TBI) in patients is crucial in clinical decision and health care policy making. This study aimed to develop and validate prediction models for in-hospital mortality after severe traumatic brain injury (sTBI). We developed and validated logistic regression (LR), LASSO regression, and machine learning (ML) algorithms including support vector machines (SVM) and XGBoost models. Fifty-four candidate predictors were included. Model performance was expressed in terms of discrimination (C-statistic) and calibration (intercept and slope). For model development, 2804 patients with sTBI in the Collaborative European NeuroTrauma Effectiveness Research in TBI (CENTER-TBI) China Registry study were included. External validation was performed in 1113 patients with sTBI in the CENTER-TBI European Registry study. XGBoost achieved high discrimination in mortality prediction, and it outperformed logistic and LASSO regression. The XGBoost model established in this study also outperformed prediction models currently available, including the International Mission for Prognosis and Analysis of Clinical Trials (IMPACT) core and International Mission for Prognosis and Analysis of Clinical Trials (CRASH) basic models. When including 54 variables, XGBoost and SVM reached C-statistics of 0.87 (95% confidence interval [CI]: 0.81-0.92) and 0.85 (95% CI: 0.79-0.90) at internal validation, and 0.88 (95% CI: 0.87-0.88) and 0.86 (95% CI: 0.85-0.87) at external validation, respectively. A simplified version of XGBoost and SVM using 26 variables selected by recursive feature elimination (RFE) reached C-statistics of 0.87 (95% CI: 0.82-0.92) and 0.86 (95% CI: 0.80-0.91) at internal validation, and 0.87 (95% CI: 0.87-0.88) and 0.87 (95% CI: 0.86-0.87) at external validation, respectively. However, when the number of variables included decreased, the difference between ML and LR diminished. All the prediction models can be accessed via a web-based calculator. Glasgow Coma Scale (GCS) score, age, pupillary light reflex, Injury Severity Score (ISS) for brain region, and the presence of acute subdural hematoma were the five strongest predictors for mortality prediction. The study showed that ML techniques such as XGBoost may capture information hidden in demographic and clinical predictors of patients with sTBI and yield more precise predictions compared with LR approaches.

Using machine learning on clinical data to identify unexpected patterns in groups of COVID-19 patients

As clinicians are faced with a deluge of clinical data, data science can play an important role in highlighting key features driving patient outcomes, aiding in the development of new clinical hypotheses. Insight derived from machine learning can serve as a clinical support tool by connecting care providers with reliable results from big data analysis that identify previously undetected clinical patterns. In this work, we show an example of collaboration between clinicians and data scientists during the COVID-19 pandemic, identifying sub-groups of COVID-19 patients with unanticipated outcomes or who are high-risk for severe disease or death. We apply a random forest classifier model to predict adverse patient outcomes early in the disease course, and we connect our classification results to unsupervised clustering of patient features that may underpin patient risk. The paradigm for using data science for hypothesis generation and clinical decision support, as well as our triaged classification approach and unsupervised clustering methods to determine patient cohorts, are applicable to driving rapid hypothesis generation and iteration in a variety of clinical challenges, including future public health crises.

Leveraging Clinical Informatics and Data Science to Improve Care and Facilitate Research in Pediatric Acute Respiratory Distress Syndrome: From the Second Pediatric Acute Lung Injury Consensus Conference

OBJECTIVES

The use of electronic algorithms, clinical decision support systems, and other clinical informatics interventions is increasing in critical care. Pediatric acute respiratory distress syndrome (PARDS) is a complex, dynamic condition associated with large amounts of clinical data and frequent decisions at the bedside. Novel data-driven technologies that can help screen, prompt, and support clinician decision-making could have a significant impact on patient outcomes. We sought to identify and summarize relevant evidence related to clinical informatics interventions in both PARDS and adult respiratory distress syndrome (ARDS), for the second Pediatric Acute Lung Injury Consensus Conference.

DATA SOURCES

MEDLINE (Ovid), Embase (Elsevier), and CINAHL Complete (EBSCOhost).

STUDY SELECTION

We included studies of pediatric or adult critically ill patients with or at risk of ARDS that examined automated screening tools, electronic algorithms, or clinical decision support systems.

DATA EXTRACTION

Title/abstract review, full text review, and data extraction using a standardized data extraction form.

DATA SYNTHESIS

The Grading of Recommendations Assessment, Development and Evaluation approach was used to identify and summarize evidence and develop recommendations. Twenty-six studies were identified for full text extraction to address the Patient/Intervention/Comparator/Outcome questions, and 14 were used for the recommendations/statements. Two clinical recommendations were generated, related to the use of electronic screening tools and automated monitoring of compliance with best practice guidelines. Two research statements were generated, related to the development of multicenter data collaborations and the design of generalizable algorithms and electronic tools. One policy statement was generated, related to the provision of material and human resources by healthcare organizations to empower clinicians to develop clinical informatics interventions to improve the care of patients with PARDS.

CONCLUSIONS

We present two clinical recommendations and three statements (two research one policy) for the use of electronic algorithms and clinical informatics tools for patients with PARDS based on a systematic review of the literature and expert consensus.

Healthcare Professionals' Expectations of Medical Artificial Intelligence and Strategies for its Clinical Implementation: A Qualitative Study

OBJECTIVES

Although medical artificial intelligence (AI) systems that assist healthcare professionals in critical care settings are expected to improve healthcare, skepticism exists regarding whether their potential has been fully actualized. Therefore, we aimed to conduct a qualitative study with physicians and nurses to understand their needs, expectations, and concerns regarding medical AI; explore their expected responses to recommendations by medical AI that contradicted their judgments; and derive strategies to implement medical AI in practice successfully.

METHODS

Semi-structured interviews were conducted with 15 healthcare professionals working in the emergency room and intensive care unit in a tertiary teaching hospital in Seoul. The data were interpreted using summative content analysis. In total, 26 medical AI topics were extracted from the interviews. Eight were related to treatment recommendation, seven were related to diagnosis prediction, and seven were related to process improvement.

RESULTS

While the participants expressed expectations that medical AI could enhance their patients' outcomes, increase work efficiency, and reduce hospital operating costs, they also mentioned concerns regarding distortions in the workflow, deskilling, alert fatigue, and unsophisticated algorithms. If medical AI decisions contradicted their judgment, most participants would consult other medical staff and thereafter reconsider their initial judgment.

CONCLUSIONS

Healthcare professionals wanted to use medical AI in practice and emphasized that artificial intelligence systems should be trustworthy from the standpoint of healthcare professionals. They also highlighted the importance of alert fatigue management and the integration of AI systems into the workflow.

Feasibility of intelligent drug control in the maintenance phase of general anesthesia based on convolutional neural network

Background

The growth and aging process of the human population has accelerated the increase in surgical procedures. Yet, the demand for increasing operations can be hardly met since the training of anesthesiologists is usually a long-term process. Closed-loop artificial intelligence (AI) model provides the possibility to solve intelligent decision-making for anesthesia auxiliary control and, as such, has allowed breakthroughs in closed-loop control of clinical practices in intensive care units (ICUs). However, applying an open-loop artificial intelligence algorithm to build up personalized medication for anesthesia still needs to be further explored. Currently, anesthesiologists have selected doses of intravenously pumped anesthetic drugs mainly based on the blood pressure and bispectral index (BIS), which can express the depth of anesthesia. Unfortunately, BIS cannot be monitored at some medical centers or operational procedures and only be regulated by blood pressure. As a result, here we aim to inaugurally explore the feasibility of a basic intelligent control system applied to drug delivery in the maintenance phase of general anesthesia, based on a convolutional neural network model with open-loop design, according to AI learning of existing anesthesia protocols.

Methods

A convolutional neural network, combined with both sliding window sampling method and residual learning module, was utilized to establish an "AI anesthesiologist" model for intraoperative dosing of personalized anesthetic drugs (propofol and remifentanil). The fitting degree and difference in pumping dose decision, between the AI anesthesiologist and the clinical anesthesiologist, for these personalized anesthetic drugs were examined during the maintenance phase of anesthesia.

Results

The medication level established by the "AI anesthesiologist" was comparable to that obtained by the clinical anesthesiologist during the maintenance phase of anesthesia.

Conclusion

The application of an open-loop decision-making plan by convolutional neural network showed that intelligent anesthesia control is consistent with the actual anesthesia control, thus providing possibility for further evolution and optimization of auxiliary intelligent control of depth of anesthesia.

Clinical utility of automatic phenotype annotation in unstructured clinical notes: intensive care unit use

OBJECTIVE

Clinical notes contain information that has not been documented elsewhere, including responses to treatment and clinical findings, which are crucial for predicting key outcomes in patients in acute care. In this study, we propose the automatic annotation of phenotypes from clinical notes as a method to capture essential information to predict outcomes in the intensive care unit (ICU). This information is complementary to typically used vital signs and laboratory test results.

METHODS

In this study, we developed a novel phenotype annotation model to extract the phenotypical features of patients, which were then used as input features of predictive models to predict ICU patient outcomes. We demonstrated and validated this approach by conducting experiments on three ICU prediction tasks, including in-hospital mortality, physiological decompensation and length of stay (LOS) for over 24 000 patients using the Medical Information Mart for Intensive Care (MIMIC-III) dataset.

RESULTS

The predictive models incorporating phenotypical information achieved 0.845 (area under the curve-receiver operating characteristic (AUC-ROC)) for in-hospital mortality, 0.839 (AUC-ROC) for physiological decompensation and 0.430 (kappa) for LOS, all of which consistently outperformed the baseline models using only vital signs and laboratory test results. Moreover, we conducted a thorough interpretability study showing that phenotypes provide valuable insights at both the patient and cohort levels.

CONCLUSION

The proposed approach demonstrates that phenotypical information complements traditionally used vital signs and laboratory test results and significantly improves the accuracy of outcome prediction in the ICU.

Explainable Preoperative Automated Machine Learning Prediction Model for Cardiac Surgery-Associated Acute Kidney Injury

BACKGROUND

We aimed to develop and validate an automated machine learning (autoML) prediction model for cardiac surgery-associated acute kidney injury (CSA-AKI).

METHODS

Using 69 preoperative variables, we developed several models to predict post-operative AKI in adult patients undergoing cardiac surgery. Models included autoML and non-autoML types, including decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), and artificial neural network (ANN), as well as a logistic regression prediction model. We then compared model performance using area under the receiver operating characteristic curve (AUROC) and assessed model calibration using Brier score on the independent testing dataset.

RESULTS

The incidence of CSA-AKI was 36%. Stacked ensemble autoML had the highest predictive performance among autoML models, and was chosen for comparison with other non-autoML and multivariable logistic regression models. The autoML had the highest AUROC (0.79), followed by RF (0.78), XGBoost (0.77), multivariable logistic regression (0.77), ANN (0.75), and DT (0.64). The autoML had comparable AUROC with RF and outperformed the other models. The autoML was well-calibrated. The Brier score for autoML, RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.18, 0.18, 0.21, 0.19, 0.19, and 0.18, respectively. We applied SHAP and LIME algorithms to our autoML prediction model to extract an explanation of the variables that drive patient-specific predictions of CSA-AKI.

CONCLUSION

We were able to present a preoperative autoML prediction model for CSA-AKI that provided high predictive performance that was comparable to RF and superior to other ML and multivariable logistic regression models. The novel approaches of the proposed explainable preoperative autoML prediction model for CSA-AKI may guide clinicians in advancing individualized medicine plans for patients under cardiac surgery.

Lifting Hospital Electronic Health Record Data Treasures: Challenges and Opportunities

Electronic health records (EHRs) have been successfully used in data science and machine learning projects. However, most of these data are collected for clinical use rather than for retrospective analysis. This means that researchers typically face many different issues when attempting to access and prepare the data for secondary use. We aimed to investigate how raw EHRs can be accessed and prepared in retrospective data science projects in a disciplined, effective, and efficient way. We report our experience and findings from a large-scale data science project analyzing routinely acquired retrospective data from the Kepler University Hospital in Linz, Austria. The project involved data collection from more than 150,000 patients over a period of 10 years. It included diverse data modalities, such as static demographic data, irregularly acquired laboratory test results, regularly sampled vital signs, and high-frequency physiological waveform signals. Raw medical data can be corrupted in many unexpected ways that demand thorough manual inspection and highly individualized data cleaning solutions. We present a general data preparation workflow, which was shaped in the course of our project and consists of the following 7 steps: obtain a rough overview of the available EHR data, define clinically meaningful labels for supervised learning, extract relevant data from the hospital’s data warehouses, match data extracted from different sources, deidentify them, detect errors and inconsistencies therein through a careful exploratory analysis, and implement a suitable data processing pipeline in actual code. Only few of the data preparation issues encountered in our project were addressed by generic medical data preprocessing tools that have been proposed recently. Instead, highly individualized solutions for the specific data used in one’s own research seem inevitable. We believe that the proposed workflow can serve as a guidance for practitioners, helping them to identify and address potential problems early and avoid some common pitfalls.

Detecting of a Patient's Condition From Clinical Narratives Using Natural Language Representation

The rapid progress in clinical data management systems and artificial intelligence approaches enable the era of personalized medicine. Intensive care units (ICUs) are ideal clinical research environments for such development because they collect many clinical data and are highly computerized. Goal: We designed a retrospective clinical study on a prospective ICU database using clinical natural language to help in the early diagnosis of heart failure in critically ill children. Methods: The methodology consisted of empirical experiments of a learning algorithm to learn the hidden interpretation and presentation of the French clinical note data. This study included 1386 patients' clinical notes with 5444 single lines of notes. There were 1941 positive cases (36% of total) and 3503 negative cases classified by two independent physicians using a standardized approach. Results: The multilayer perceptron neural network outperforms other discriminative and generative classifiers. Consequently, the proposed framework yields an overall classification performance with 89% accuracy, 88% recall, and 89% precision. Conclusions: This study successfully applied learning representation and machine learning algorithms to detect heart failure in a single French institution from clinical natural language. Further work is needed to use the same methodology in other languages and institutions.

Human acute inflammatory recovery is defined by co-regulatory dynamics of white blood cell and platelet populations

Inflammation is the physiologic reaction to cellular and tissue damage caused by trauma, ischemia, infection, and other pathologic conditions. Elevation of white blood cell count (WBC) and altered levels of other acute phase reactants are cardinal signs of inflammation, but the dynamics of these changes and their resolution are not well established. Here we studied inflammatory recovery from trauma, ischemia, and infection by tracking longitudinal dynamics of clinical laboratory measurements in hospitalized patients. We identified a universal recovery trajectory defined by exponential WBC decay and delayed linear growth of platelet count (PLT). Co-regulation of WBC-PLT dynamics is a fundamental mechanism of acute inflammatory recovery and provides a generic approach for identifying high-risk patients: 32x relative risk (RR) of adverse outcomes for cardiac surgery, 9x RR of death from COVID-19, 9x RR of death from sepsis, and 5x RR of death from myocardial infarction.

Data-driven methodology to predict the ICU length of stay: A multicentre study of 99,492 admissions in 109 Brazilian units

PURPOSE

The length of stay (LoS) is one of the most used metrics for resource use in Intensive Care Units (ICU). We propose a structured data-driven methodology to predict the ICU length of stay and the risk of prolonged stay, and its application in a large multicenter Brazilian ICU database.

METHODS

Demographic data, comorbidities, complications, laboratory data, and primary and secondary diagnosis were prospectively collected and retrospectively analysed by a data-driven methodology, which includes eight different machine learning models and a stacking model. The study setting included 109 mixed-type ICUs from 38 Brazilian hospitals and the external validation was performed by 93 medical-surgical ICUs of 55 hospitals in Brazil.

RESULTS

A cohort of 99,492 adult ICU admissions were included from the 01^st of January to the 31^st of December 2019. The stacking model combining Random Forests and Linear Regression presented the best results to predict ICU length of stay (RMSE = 3.82; MAE = 2.52; R² = 0.36). The prediction model for the risk of long stay were accurate to early identify prolonged stay patients (Brier Score = 0.04, AUC = 0.87, PPV = 0.83, NPV = 0.95).

CONCLUSION

The data-driven methodology to predict ICU length of stay and the risk of long-stay proved accurate in a large multicentre cohort of general ICU patients. The proposed models are helpful to predict the individual length of stay and to early identify patients with high risk of prolonged stay.

Towards Secure and Intelligent Internet of Health Things: A Survey of Enabling Technologies and Applications

With the growth of computing and communication technologies, the information processing paradigm of the healthcare environment is evolving. The patient information is stored electronically, making it convenient to store and retrieve patient information remotely when needed. However, evolving the healthcare systems into smart healthcare environments comes with challenges and additional pressures. Internet of Things (IoT) connects things, such as computing devices, through wired or wireless mediums to form a network. There are numerous security vulnerabilities and risks in the existing IoT-based systems due to the lack of intrinsic security technologies. For example, patient medical data, data privacy, data sharing, and convenience are considered imperative for collecting and storing electronic health records (EHR). However, the traditional IoT-based EHR systems cannot deal with these paradigms because of inconsistent security policies and data access structures. Blockchain (BC) technology is a decentralized and distributed ledger that comes in handy in storing patient data and encountering data integrity and confidentiality challenges. Therefore, it is a viable solution for addressing existing IoT data security and privacy challenges. BC paves a tremendous path to revolutionize traditional IoT systems by enhancing data security, privacy, and transparency. The scientific community has shown a variety of healthcare applications based on artificial intelligence (AI) that improve health diagnosis and monitoring practices. Moreover, technology companies and startups are revolutionizing healthcare with AI and related technologies. This study illustrates the implication of integrated technologies based on BC, IoT, and AI to meet growing healthcare challenges. This research study examines the integration of BC technology with IoT and analyzes the advancements of these innovative paradigms in the healthcare sector. In addition, our research study presents a detailed survey on enabling technologies for the futuristic, intelligent, and secure internet of health things (IoHT). Furthermore, this study comprehensively studies the peculiarities of the IoHT environment and the security, performance, and progression of the enabling technologies. First, the research gaps are identified by mapping security and performance benefits inferred by the BC technologies. Secondly, practical issues related to the integration process of BC and IoT devices are discussed. Third, the healthcare applications integrating IoT, BC, and ML in healthcare environments are discussed. Finally, the research gaps, future directions, and limitations of the enabling technologies are discussed.

Research on Digital Technology Use in Cardiology: Bibliometric Analysis

Background

Digital technology uses in cardiology have become a popular research focus in recent years. However, there has been no published bibliometric report that analyzed the corresponding academic literature in order to derive key publishing trends and characteristics of this scientific area.

Objective

We used a bibliometric approach to identify and analyze the academic literature on digital technology uses in cardiology, and to unveil popular research topics, key authors, institutions, countries, and journals. We further captured the cardiovascular conditions and diagnostic tools most commonly investigated within this field.

Methods

The Web of Science electronic database was queried to identify relevant papers on digital technology uses in cardiology. Publication and citation data were acquired directly from the database. Complete bibliographic data were exported to VOSviewer, a dedicated bibliometric software package, and related to the semantic content of titles, abstracts, and keywords. A term map was constructed for findings visualization.

Results

The analysis was based on data from 12,529 papers. Of the top 5 most productive institutions, 4 were based in the United States. The United States was the most productive country (4224/12,529, 33.7%), followed by United Kingdom (1136/12,529, 9.1%), Germany (1067/12,529, 8.5%), China (682/12,529, 5.4%), and Italy (622/12,529, 5.0%). Cardiovascular diseases that had been frequently investigated included hypertension (152/12,529, 1.2%), atrial fibrillation (122/12,529, 1.0%), atherosclerosis (116/12,529, 0.9%), heart failure (106/12,529, 0.8%), and arterial stiffness (80/12,529, 0.6%). Recurring modalities were electrocardiography (170/12,529, 1.4%), angiography (127/12,529, 1.0%), echocardiography (127/12,529, 1.0%), digital subtraction angiography (111/12,529, 0.9%), and photoplethysmography (80/12,529, 0.6%). For a literature subset on smartphone apps and wearable devices, the Journal of Medical Internet Research (20/632, 3.2%) and other JMIR portfolio journals (51/632, 8.0%) were the major publishing venues.

Conclusions

Digital technology uses in cardiology target physicians, patients, and the general public. Their functions range from assisting diagnosis, recording cardiovascular parameters, and patient education, to teaching laypersons about cardiopulmonary resuscitation. This field already has had a great impact in health care, and we anticipate continued growth.

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.

Association between basal platelet count and all-cause mortality in critically ill patients with acute respiratory failure: a secondary analysis from the eICU collaborative research database

BACKGROUND

Evidence regarding the correlation between platelet count and all-cause mortality in critically ill patients with acute respiratory failure (ARF) is limited. Therefore, the aim of the study was to evaluate whether platelet count was associated with all-cause mortality in critical patients with ARF by using the electronic intensive care unit (eICU) Collaborative Research Database (eICU-CRD).

METHODS

In this retrospective multicenter cohort study, the data of 26961 patients with ARF hospitalized in ICUs between 2014 and 2015 were collected. The independent variable was log2 basal platelet count, and the dependent variables were all-cause in-hospital and ICU mortality. Covariates including demographic data, Acute Physiology and Chronic Health Evaluation (APACHE) IV score, supportive treatment, and comorbidities were collected.

RESULTS

In the fully adjusted model, log2 basal platelet count was negatively associated with all-cause mortality both in hospital [RR: 0.87, 95% CI: 0.84-0.91] and in ICU [RR: 0.87, 95% CI: 0.83-0.92]. A non-linear relationship between log2 basal platelet count and all-cause in-hospital and ICU mortality was identified by the nonlinearity test. The inflection points we got were 6.83 and 6.86 respectively (after inverse log2 logarithmic conversion, the platelet counts were 114×10⁹/L and 116×10⁹/L, respectively). On the right side of the inflection point, however, no association was observed between blood platelets and all-cause in-hospital (RR: 0.96, 95% CI: 0.88-1.03) and ICU mortality (RR: 0.97, 95% CI: 0.91-1.04).

CONCLUSIONS

For patients with ARF in ICU, platelet count was negatively associated with all-cause in-hospital and ICU mortality when the platelet count was less than 114×10⁹/L and 116×10⁹/L respectively, but when the platelet count was higher, we failed to observe a correlation between them. The safe ranges of platelet count for hospital stay and ICU stay were 78×10⁹/L-145×10⁹/L and 89×10⁹/L-147×10⁹/L respectively.

Identification of data elements for blood gas analysis dataset: a base for developing registries and artificial intelligence-based systems

Background

One of the challenging decision-making tasks in healthcare centers is the interpretation of blood gas tests. One of the most effective assisting approaches for the interpretation of blood gas analysis (BGA) can be artificial intelligence (AI)-based decision support systems. A primary step to develop intelligent systems is to determine information requirements and automated data input for the secondary analyses. Datasets can help the automated data input from dispersed information systems. Therefore, the current study aimed to identify the data elements required for supporting BGA as a dataset.

Materials and methods

This cross-sectional descriptive study was conducted in Nemazee Hospital, Shiraz, Iran. A combination of literature review, experts’ consensus, and the Delphi technique was used to develop the dataset. A review of the literature was performed on electronic databases to find the dataset for BGA. An expert panel was formed to discuss on, add, or remove the data elements extracted through searching the literature. Delphi technique was used to reach consensus and validate the draft dataset.

Results

The data elements of the BGA dataset were categorized into ten categories, namely personal information, admission details, present illnesses, past medical history, social status, physical examination, paraclinical investigation, blood gas parameter, sequential organ failure assessment (SOFA) score, and sampling technique errors. Overall, 313 data elements, including 172 mandatory and 141 optional data elements were confirmed by the experts for being included in the dataset.

Conclusions

We proposed a dataset as a base for registries and AI-based systems to assist BGA. It helps the storage of accurate and comprehensive data, as well as integrating them with other information systems. As a result, high-quality care is provided and clinical decision-making is improved.

Developing, implementing and governing artificial intelligence in medicine: a step-by-step approach to prevent an artificial intelligence winter

Objective

Although the role of artificial intelligence (AI) in medicine is increasingly studied, most patients do not benefit because the majority of AI models remain in the testing and prototyping environment. The development and implementation trajectory of clinical AI models are complex and a structured overview is missing. We therefore propose a step-by-step overview to enhance clinicians’ understanding and to promote quality of medical AI research.

Methods

We summarised key elements (such as current guidelines, challenges, regulatory documents and good practices) that are needed to develop and safely implement AI in medicine.

Conclusion

This overview complements other frameworks in a way that it is accessible to stakeholders without prior AI knowledge and as such provides a step-by-step approach incorporating all the key elements and current guidelines that are essential for implementation, and can thereby help to move AI from bytes to bedside.

Using Machine Learning to Predict Complications in Pregnancy: A Systematic Review

Introduction: Artificial intelligence is widely used in medical field, and machine learning has been increasingly used in health care, prediction, and diagnosis and as a method of determining priority. Machine learning methods have been features of several tools in the fields of obstetrics and childcare. This present review aims to summarize the machine learning techniques to predict perinatal complications.

Objective: To identify the applicability and performance of machine learning methods used to identify pregnancy complications.

Methods: A total of 98 articles were obtained with the keywords “machine learning,” “deep learning,” “artificial intelligence,” and accordingly as they related to perinatal complications (“complications in pregnancy,” “pregnancy complications”) from three scientific databases: PubMed, Scopus, and Web of Science. These were managed on the Mendeley platform and classified using the PRISMA method.

Results: A total of 31 articles were selected after elimination according to inclusion and exclusion criteria. The features used to predict perinatal complications were primarily electronic medical records (48%), medical images (29%), and biological markers (19%), while 4% were based on other types of features, such as sensors and fetal heart rate. The main perinatal complications considered in the application of machine learning thus far are pre-eclampsia and prematurity. In the 31 studies, a total of sixteen complications were predicted. The main precision metric used is the AUC. The machine learning methods with the best results were the prediction of prematurity from medical images using the support vector machine technique, with an accuracy of 95.7%, and the prediction of neonatal mortality with the XGBoost technique, with 99.7% accuracy.

Conclusion: It is important to continue promoting this area of research and promote solutions with multicenter clinical applicability through machine learning to reduce perinatal complications. This systematic review contributes significantly to the specialized literature on artificial intelligence and women’s health.

Prediction model of acute kidney injury induced by cisplatin in older adults using a machine learning algorithm

Background

Early detection and prediction of cisplatin-induced acute kidney injury (Cis-AKI) are essential for the management of patients on chemotherapy with cisplatin. This study aimed to evaluate the performance of a prediction model for Cis-AKI.

Methods

Japanese patients, who received cisplatin as the first-line chemotherapy at Fujita Health University Hospital, were enrolled in the study. The main metrics for evaluating the machine learning model were the area under the curve (AUC), accuracy, precision, recall, and F-measure. In addition, the rank of contribution as a predictive factor of Cis-AKI was determined by machine learning.

Results

A total of 1,014 and 226 patients were assigned to the development and validation data groups, respectively. The current prediction model showed the highest performance in patients 65 years old and above (AUC: 0.78, accuracy: 0.77, precision: 0.38, recall: 0.70, F-measure: 0.49). The maximum daily cisplatin dose and serum albumin levels contributed the most to the prediction of Cis-AKI.

Conclusion

Our prediction model for Cis-AKI performed effectively in older patients.

Optimising Energy Management in Hybrid Microgrids

This article deals with the optimization of the operation of hybrid microgrids. Both the problem of controlling the management of load sharing between the different generators and energy storage and possible solutions for the integration of the microgrid into the electricity market will be discussed. Solar and wind energy as well as hybrid storage with hydrogen, as renewable sources, will be considered, which allows management of the energy balance on different time scales. The Machine Learning method of Decision Trees, combined with ensemble methods, will also be introduced to study the optimization of microgrids. The conclusions obtained indicate that the development of suitable controllers can facilitate a competitive participation of renewable energies and the integration of microgrids in the electricity system.

Precision Medicine for Hypertension Patients with Type 2 Diabetes via Reinforcement Learning

Precision medicine is a new approach to understanding health and disease based on patient-specific data such as medical diagnoses; clinical phenotype; biologic investigations such as laboratory studies and imaging; and environmental, demographic, and lifestyle factors. The importance of machine learning techniques in healthcare has expanded quickly in the last decade owing to the rising availability of vast multi-modality data and developed computational models and algorithms. Reinforcement learning is an appealing method for developing efficient policies in various healthcare areas where the decision-making process is typically defined by a long period or a sequential process. In our research, we leverage the power of reinforcement learning and electronic health records of South Koreans to dynamically recommend treatment prescriptions, which are personalized based on patient information of hypertension. Our proposed reinforcement learning-based treatment recommendation system decides whether to use mono, dual, or triple therapy according to the state of the hypertension patients. We evaluated the performance of our personalized treatment recommendation model by lowering the occurrence of hypertension-related complications and blood pressure levels of patients who followed our model’s recommendation. With our findings, we believe that our proposed hypertension treatment recommendation model could assist doctors in prescribing appropriate antihypertensive medications.

Machine Learning Models for Predicting Short-Long Length of Stay of COVID-19 Patients

During 2020 and 2021, managing limited healthcare resources and hospital beds has been a fundamental aspect of the fight against the COVID-19 pandemic. Predicting in advance the length of stay, and in particular identifying whether a patient is going to stay in the hospital longer or less than a week, can provide important support in handling resources allocation. However, there have been significant changes in terms of containment measures, virus diffusion, new treatments, vaccines, and new variants of SARS-CoV-2 during the last period. These changes pose several conceptual drift issues that can limit the usefulness of machine learning in this context. In this work, we present a machine learning system trained and tested using data from more than 6000 hospitalised patients in northern Italy, distributed over almost two years of pandemic. We show how machine learning can be effective even by analysing data over this long period of time, also exploiting a model that predicts the patient's outcome in terms of discharge or death. Furthermore, learning from data that also consider deceased patients is a common issue in predicting the length of stay because they have severe conditions similar to patients with a long stay period, but may actually have a very short duration of hospitalisation. For this purpose, we present a method for handling data from alive and deceased patients, exploiting more patient records, increasing the robustness of the model and its performance in this task. Finally, we investigate the features that are most relevant to the prediction of the simplified length of stay.

Wearable multimodal sensors for the detection of behavioral and psychological symptoms of dementia using personalized machine learning models

Introduction

Behavioral and psychological symptoms of dementia (BPSD) signal distress or unmet needs and present a risk to people with dementia and their caregivers. Variability in the expression of these symptoms is a barrier to the performance of digital biomarkers. The aim of this study was to use wearable multimodal sensors to develop personalized machine learning models capable of detecting individual patterns of BPSD.

Methods

Older adults with dementia and BPSD (n = 17) on a dementia care unit wore a wristband during waking hours for up to 8 weeks. The wristband captured motion (accelerometer) and physiological indicators (blood volume pulse, electrodermal activity, and skin temperature). Agitation or aggression events were tracked, and research staff reviewed videos to precisely annotate the sensor data. Personalized machine learning models were developed using 1‐minute intervals and classifying the presence of behavioral symptoms, and behavioral symptoms by type (motor agitation, verbal aggression, or physical aggression).

Results

Behavioral events were rare, representing 3.4% of the total data. Personalized models classified behavioral symptoms with a median area under the receiver operating curve (AUC) of 0.87 (range 0.64–0.95). The relative importance of the different sensor features to the predictive models varied both by individual and behavior type.

Discussion

Patterns of sensor data associated with BPSD are highly individualized, and future studies of the digital phenotyping of these behaviors would benefit from personalization.

A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain

Seventy-two-hour unscheduled return visits (URVs) by emergency department patients are a key clinical index for evaluating the quality of care in emergency departments (EDs). This study aimed to develop a machine learning model to predict 72 h URVs for ED patients with abdominal pain. Electronic health records data were collected from the Chang Gung Research Database (CGRD) for 25,151 ED visits by patients with abdominal pain and a total of 617 features were used for analysis. We used supervised machine learning models, namely logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGB), and voting classifier (VC), to predict URVs. The VC model achieved more favorable overall performance than other models (AUROC: 0.74; 95% confidence interval (CI), 0.69–0.76; sensitivity, 0.39; specificity, 0.89; F1 score, 0.25). The reduced VC model achieved comparable performance (AUROC: 0.72; 95% CI, 0.69–0.74) to the full models using all clinical features. The VC model exhibited the most favorable performance in predicting 72 h URVs for patients with abdominal pain, both for all-features and reduced-features models. Application of the VC model in the clinical setting after validation may help physicians to make accurate decisions and decrease URVs.