Explainable Machine Learning on AmsterdamUMCdb for ICU Discharge Decision Support: Uniting Intensivists and Data Scientists

Long-term survival of traumatic brain injury and intra-cerebral haemorrhage patients: A multicentric observational cohort

PURPOSE

Mortality is often assessed during ICU stay and early after, but rarely at later stage. We aimed to compare the long-term mortality between TBI and ICH patients.

MATERIALS AND METHODS

From an observational cohort, we studied 580 TBI patients and 435 ICH patients, admitted from January 2013 to February 2021 in 3 ICUs and alive at 7-days post-ICU discharge. We performed a Lasso-penalized Cox survival analysis.

RESULTS

We estimated 7-year survival rates at 72.8% (95%CI from 67.3% to 78.7%) for ICH patients and at 84.9% (95%CI from 80.9% to 89.1%) for TBI patients: ICH patients presenting a higher mortality risk than TBI patients. Additionally, we identified variables associated with higher mortality risk (age, ICU length of stay, tracheostomy, low GCS, absence of intracranial pressure monitoring). We also observed anisocoria related with the mortality risk in the early stage after ICU stay.

CONCLUSIONS

In this ICU survivor population with a prolonged follow-up, we highlight an acute risk of death after ICU stay, which seems to last longer in ICH patients. Several variables characteristic of disease severity appeared associated with long-term mortality, raising the hypothesis that the most severe patients deserve closer follow-up after ICU stay.

Artificial intelligence to advance acute and intensive care medicine

PURPOSE OF REVIEW

This review explores recent key advancements in artificial intelligence for acute and intensive care medicine. As artificial intelligence rapidly evolves, this review aims to elucidate its current applications, future possibilities, and the vital challenges that are associated with its integration into emergency medical dispatch, triage, medical consultation and ICUs.

RECENT FINDINGS

The integration of artificial intelligence in emergency medical dispatch (EMD) facilitates swift and accurate assessment. In the emergency department (ED), artificial intelligence driven triage models leverage diverse patient data for improved outcome predictions, surpassing human performance in retrospective studies. Artificial intelligence can streamline medical documentation in the ED and enhances medical imaging interpretation. The introduction of large multimodal generative models showcases the future potential to process varied biomedical data for comprehensive decision support. In the ICU, artificial intelligence applications range from early warning systems to treatment suggestions.

SUMMARY

Despite promising academic strides, widespread artificial intelligence adoption in acute and critical care is hindered by ethical, legal, technical, organizational, and validation challenges. Despite these obstacles, artificial intelligence's potential to streamline clinical workflows is evident. When these barriers are overcome, future advancements in artificial intelligence have the potential to transform the landscape of patient care for acute and intensive care medicine.

[Big data and artificial intelligence in anesthesia : Reality or fiction?]

Big data and artificial intelligence are buzzwords that everyone is talking about and yet always provide a touch of science fiction to the scenery. What is the status of these topics in anesthesia? Are the first robots already rolling through the corridors while doctors are getting bored as all the work has been done? Spoiler alert! We are still far away from achieving this. Initially, paper charts and analogue notes stand in the way of comprehensive digitization. Source systems need to be merged and data standardized, harmonized and validated. Therefore, the friendly android that is rolling towards us, waving and holding a freshly brewed cup of coffee in our thoughts will have to wait; however, a glimpse of the future is already evident in some clinics and the first promising developments are already showing what could be the standard tomorrow. Learning algorithms calculate the length of stay individually for each patient in the intensive care unit (ICU), reducing negative consequences such as readmission and mortality. The field of ultrasound technology for regional anesthesia and closed-loop anesthesia systems is also demonstrating the benefits of artificial intelligence (AI)-assisted technologies in practice. The efforts are diverse and ambitious but they repeatedly collide with privacy challenges and significant capital expenditure, which weigh heavily on an already financially strained healthcare system; however, anyone who listens carefully to the medical staff knows that robots are not what they would expect and the buzzwords big data and artificial intelligence might be less science fiction than initially assumed.

What is the future of artificial intelligence in obstetrics? A qualitative study among healthcare professionals

OBJECTIVE

This work explores the perceptions of obstetrical clinicians about artificial intelligence (AI) in order to bridge the gap in uptake of AI between research and medical practice. Identifying potential areas where AI can contribute to clinical practice, enables AI research to align with the needs of clinicians and ultimately patients.

DESIGN

Qualitative interview study.

SETTING

A national study conducted in the Netherlands between November 2022 and February 2023.

PARTICIPANTS

Dutch clinicians working in obstetrics with varying relevant work experience, gender and age.

ANALYSIS

Thematic analysis of qualitative interview transcripts.

RESULTS

Thirteen gynaecologists were interviewed about hypothetical scenarios of an implemented AI model. Thematic analysis identified two major themes: perceived usefulness and trust. Usefulness involved AI extending human brain capacity in complex pattern recognition and information processing, reducing contextual influence and saving time. Trust required validation, explainability and successful personal experience. This result shows two paradoxes: first, AI is expected to provide added value by surpassing human capabilities, yet also a need to understand the parameters and their influence on predictions for trust and adoption was expressed. Second, participants recognised the value of incorporating numerous parameters into a model, but they also believed that certain contextual factors should only be considered by humans, as it would be undesirable for AI models to use that information.

CONCLUSIONS

Obstetricians' opinions on the potential value of AI highlight the need for clinician-AI researcher collaboration. Trust can be built through conventional means like randomised controlled trials and guidelines. Holistic impact metrics, such as changes in workflow, not just clinical outcomes, should guide AI model development. Further research is needed for evaluating evolving AI systems beyond traditional validation methods.

Critical Bias in Critical Care Devices

Critical care data contain information about the most physiologically fragile patients in the hospital, who require a significant level of monitoring. However, medical devices used for patient monitoring suffer from measurement biases that have been largely underreported. This article explores sources of bias in commonly used clinical devices, including pulse oximeters, thermometers, and sphygmomanometers. Further, it provides a framework for mitigating these biases and key principles to achieve more equitable health care delivery.

Sepsis-induced coagulopathy is associated with new episodes of atrial fibrillation in patients admitted to critical care in sinus rhythm

Background

Sepsis is a life-threatening disease commonly complicated by activation of coagulation and immune pathways. Sepsis-induced coagulopathy (SIC) is associated with micro- and macrothrombosis, but its relation to other cardiovascular complications remains less clear. In this study we explored associations between SIC and the occurrence of atrial fibrillation (AF) in patients admitted to the Intensive Care Unit (ICU) in sinus rhythm. We also aimed to identify predictive factors for the development of AF in patients with and without SIC.

Methods

Data were extracted from the publicly available AmsterdamUMCdb database. Patients with sepsis and documented sinus rhythm on admission to ICU were included. Patients were stratified into those who fulfilled the criteria for SIC and those who did not. Following univariate analysis, logistic regression models were developed to describe the association between routinely documented demographics and blood results and the development of at least one episode of AF. Machine learning methods (gradient boosting machines and random forest) were applied to define the predictive importance of factors contributing to the development of AF.

Results

Age was the strongest predictor for the development of AF in patients with and without SIC. Routine coagulation tests activated Partial Thromboplastin Time (aPTT) and International Normalized Ratio (INR) and C-reactive protein (CRP) as a marker of inflammation were also associated with AF occurrence in SIC-positive and SIC-negative patients. Cardiorespiratory parameters (oxygen requirements and heart rate) showed predictive potential.

Conclusion

Higher INR, elevated CRP, increased heart rate and more severe respiratory failure are risk factors for occurrence of AF in critical illness, suggesting an association between cardiac, respiratory and immune and coagulation pathways. However, age was the most dominant factor to predict the first episodes of AF in patients admitted in sinus rhythm with and without SIC.

Improving Intensive Care Unit Early Readmission Prediction Using Optimized and Explainable Machine Learning

It is of great interest to develop and introduce new techniques to automatically and efficiently analyze the enormous amount of data generated in today's hospitals, using state-of-the-art artificial intelligence methods. Patients readmitted to the ICU in the same hospital stay have a higher risk of mortality, morbidity, longer length of stay, and increased cost. The methodology proposed to predict ICU readmission could improve the patients' care. The objective of this work is to explore and evaluate the potential improvement of existing models for predicting early ICU patient readmission by using optimized artificial intelligence algorithms and explainability techniques. In this work, XGBoost is used as a predictor model, combined with Bayesian techniques to optimize it. The results obtained predicted early ICU readmission (AUROC of 0.92 ± 0.03) improves state-of-the-art consulted works (whose AUROC oscillate between 0.66 and 0.78). Moreover, we explain the internal functioning of the model by using Shapley Additive Explanation-based techniques, allowing us to understand the model internal performance and to obtain useful information, as patient-specific information, the thresholds from which a feature begins to be critical for a certain group of patients, and the feature importance ranking.

Predicting Readmission or Death After Discharge From the ICU: External Validation and Retraining of a Machine Learning Model

OBJECTIVES

Many machine learning (ML) models have been developed for application in the ICU, but few models have been subjected to external validation. The performance of these models in new settings therefore remains unknown. The objective of this study was to assess the performance of an existing decision support tool based on a ML model predicting readmission or death within 7 days after ICU discharge before, during, and after retraining and recalibration.

DESIGN

A gradient boosted ML model was developed and validated on electronic health record data from 2004 to 2021. We performed an independent validation of this model on electronic health record data from 2011 to 2019 from a different tertiary care center.

SETTING

Two ICUs in tertiary care centers in The Netherlands.

PATIENTS

Adult patients who were admitted to the ICU and stayed for longer than 12 hours.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

We assessed discrimination by area under the receiver operating characteristic curve (AUC) and calibration (slope and intercept). We retrained and recalibrated the original model and assessed performance via a temporal validation design. The final retrained model was cross-validated on all data from the new site. Readmission or death within 7 days after ICU discharge occurred in 577 of 10,052 ICU admissions (5.7%) at the new site. External validation revealed moderate discrimination with an AUC of 0.72 (95% CI 0.67-0.76). Retrained models showed improved discrimination with AUC 0.79 (95% CI 0.75-0.82) for the final validation model. Calibration was poor initially and good after recalibration via isotonic regression.

CONCLUSIONS

In this era of expanding availability of ML models, external validation and retraining are key steps to consider before applying ML models to new settings. Clinicians and decision-makers should take this into account when considering applying new ML models to their local settings.

Intensive Care Unit Physicians' Perspectives on Artificial Intelligence-Based Clinical Decision Support Tools: Preimplementation Survey Study

BACKGROUND

Artificial intelligence-based clinical decision support (AI-CDS) tools have great potential to benefit intensive care unit (ICU) patients and physicians. There is a gap between the development and implementation of these tools.

OBJECTIVE

We aimed to investigate physicians' perspectives and their current decision-making behavior before implementing a discharge AI-CDS tool for predicting readmission and mortality risk after ICU discharge.

METHODS

We conducted a survey of physicians involved in decision-making on discharge of patients at two Dutch academic ICUs between July and November 2021. Questions were divided into four domains: (1) physicians' current decision-making behavior with respect to discharging ICU patients, (2) perspectives on the use of AI-CDS tools in general, (3) willingness to incorporate a discharge AI-CDS tool into daily clinical practice, and (4) preferences for using a discharge AI-CDS tool in daily workflows.

RESULTS

Most of the 64 respondents (of 93 contacted, 69%) were familiar with AI (62/64, 97%) and had positive expectations of AI, with 55 of 64 (86%) believing that AI could support them in their work as a physician. The respondents disagreed on whether the decision to discharge a patient was complex (23/64, 36% agreed and 22/64, 34% disagreed); nonetheless, most (59/64, 92%) agreed that a discharge AI-CDS tool could be of value. Significant differences were observed between physicians from the 2 academic sites, which may be related to different levels of involvement in the development of the discharge AI-CDS tool.

CONCLUSIONS

ICU physicians showed a favorable attitude toward the integration of AI-CDS tools into the ICU setting in general, and in particular toward a tool to predict a patient's risk of readmission and mortality within 7 days after discharge. The findings of this questionnaire will be used to improve the implementation process and training of end users.

Leveraging electronic health records for data science: common pitfalls and how to avoid them

Analysis of electronic health records (EHRs) is an increasingly common approach for studying real-world patient data. Use of routinely collected data offers several advantages compared with other study designs, including reduced administrative costs, the ability to update analysis as practice patterns evolve, and larger sample sizes. Methodologically, EHR analysis is subject to distinct challenges because data are not collected for research purposes. In this Viewpoint, we elaborate on the importance of in-depth knowledge of clinical workflows and describe six potential pitfalls to be avoided when working with EHR data, drawing on examples from the literature and our experience. We propose solutions for prevention or mitigation of factors associated with each of these six pitfalls-sample selection bias, imprecise variable definitions, limitations to deployment, variable measurement frequency, subjective treatment allocation, and model overfitting. Ultimately, we hope that this Viewpoint will guide researchers to further improve the methodological robustness of EHR analysis.

Modern Learning from Big Data in Critical Care: Primum Non Nocere

Large and complex data sets are increasingly available for research in critical care. To analyze these data, researchers use techniques commonly referred to as statistical learning or machine learning (ML). The latter is known for large successes in the field of diagnostics, for example, by identification of radiological anomalies. In other research areas, such as clustering and prediction studies, there is more discussion regarding the benefit and efficiency of ML techniques compared with statistical learning. In this viewpoint, we aim to explain commonly used statistical learning and ML techniques and provide guidance for responsible use in the case of clustering and prediction questions in critical care. Clustering studies have been increasingly popular in critical care research, aiming to inform how patients can be characterized, classified, or treated differently. An important challenge for clustering studies is to ensure and assess generalizability. This limits the application of findings in these studies toward individual patients. In the case of predictive questions, there is much discussion as to what algorithm should be used to most accurately predict outcome. Aspects that determine usefulness of ML, compared with statistical techniques, include the volume of the data, the dimensionality of the preferred model, and the extent of missing data. There are areas in which modern ML methods may be preferred. However, efforts should be made to implement statistical frameworks (e.g., for dealing with missing data or measurement error, both omnipresent in clinical data) in ML methods. To conclude, there are important opportunities but also pitfalls to consider when performing clustering or predictive studies with ML techniques. We advocate careful valuation of new data-driven findings. More interaction is needed between the engineer mindset of experts in ML methods, the insight in bias of epidemiologists, and the probabilistic thinking of statisticians to extract as much information and knowledge from data as possible, while avoiding harm.

Development of a Risk Prediction Model for New Episodes of Atrial Fibrillation in Medical-Surgical Critically Ill Patients Using the AmsterdamUMCdb

The occurrence of atrial fibrillation (AF) represents clinical deterioration in acutely unwell patients and leads to increased morbidity and mortality. Prediction of the development of AF allows early intervention. Using the AmsterdamUMCdb, clinically relevant variables from patients admitted in sinus rhythm were extracted over the full duration of the ICU stay or until the first recorded AF episode occurred. Multiple logistic regression was performed to identify risk factors for AF. Input variables were automatically selected by a sequential forward search algorithm using cross-validation. We developed three different models: For the overall cohort, for ventilated patients and non-ventilated patients. 16,144 out of 23,106 admissions met the inclusion criteria. 2,374 (12.8%) patients had at least one AF episode during their ICU stay. Univariate analysis revealed that a higher percentage of AF patients were older than 70 years (60% versus 32%) and died in ICU (23.1% versus 7.1%) compared to non-AF patients. Multivariate analysis revealed age to be the dominant risk factor for developing AF with doubling of age leading to a 10-fold increased risk. Our logistic regression models showed excellent performance with AUC.ROC > 0.82 and > 0.91 in ventilated and non-ventilated cohorts, respectively. Increasing age was the dominant risk factor for the development of AF in both ventilated and non-ventilated critically ill patients. In non-ventilated patients, risk for development of AF was significantly higher than in ventilated patients. Further research is warranted to identify the role of ventilatory settings on risk for AF in critical illness and to optimise predictive models.

Demystifying the Black Box: The Importance of Interpretability of Predictive Models in Neurocritical Care

Neurocritical care patients are a complex patient population, and to aid clinical decision-making, many models and scoring systems have previously been developed. More recently, techniques from the field of machine learning have been applied to neurocritical care patient data to develop models with high levels of predictive accuracy. However, although these recent models appear clinically promising, their interpretability has often not been considered and they tend to be black box models, making it extremely difficult to understand how the model came to its conclusion. Interpretable machine learning methods have the potential to provide the means to overcome some of these issues but are largely unexplored within the neurocritical care domain. This article examines existing models used in neurocritical care from the perspective of interpretability. Further, the use of interpretable machine learning will be explored, in particular the potential benefits and drawbacks that the techniques may have when applied to neurocritical care data. Finding a solution to the lack of model explanation, transparency, and accountability is important because these issues have the potential to contribute to model trust and clinical acceptance, and, increasingly, regulation is stipulating a right to explanation for decisions made by models and algorithms. To ensure that the prospective gains from sophisticated predictive models to neurocritical care provision can be realized, it is imperative that interpretability of these models is fully considered.