Machine learning in critical care: state-of-the-art and a sepsis case study

Improving clinical decision support through interpretable machine learning and error handling in electronic health records

OBJECTIVE

To develop an electronic medical record (EMR) data processing tool that confers clinical context to machine learning (ML) algorithms for error handling, bias mitigation, and interpretability.

MATERIALS AND METHODS

We present Trust-MAPS, an algorithm that translates clinical domain knowledge into high-dimensional, mixed-integer programming models that capture physiological and biological constraints on clinical measurements. EMR data are projected onto this constrained space, effectively bringing outliers to fall within a physiologically feasible range. We then compute the distance of each data point from the constrained space modeling healthy physiology to quantify deviation from the norm. These distances, termed "trust-scores," are integrated into the feature space for downstream ML applications. We demonstrate the utility of Trust-MAPS by training a binary classifier for early sepsis prediction on data from the 2019 PhysioNet Computing in Cardiology Challenge, using the XGBoost algorithm and applying SMOTE for overcoming class-imbalance.

RESULTS

The Trust-MAPS framework shows desirable behavior in handling potential errors and boosting predictive performance. We achieve an area under the receiver operating characteristic curve of 0.91 (95% CI, 0.89-0.92) for predicting sepsis 6 hours before onset-a marked 15% improvement over a baseline model trained without Trust-MAPS.

DISCUSSIONS

Downstream classification performance improves after Trust-MAPS preprocessing, highlighting the bias reducing capabilities of the error-handling projections. Trust-scores emerge as clinically meaningful features that not only boost predictive performance for clinical decision support tasks but also lend interpretability to ML models.

CONCLUSION

This work is the first to translate clinical domain knowledge into mathematical constraints, model cross-vital dependencies, and identify aberrations in high-dimensional medical data. Our method allows for error handling in EMR and confers interpretability and superior predictive power to models trained for clinical decision support.

Machine Learning Models in Sepsis Outcome Prediction for ICU Patients: Integrating Routine Laboratory Tests-A Systematic Review

Background. Sepsis presents significant diagnostic and prognostic challenges, and traditional scoring systems, such as SOFA and APACHE, show limitations in predictive accuracy. Machine learning (ML)-based predictive survival models can support risk assessment and treatment decision-making in the intensive care unit (ICU) by accounting for the numerous and complex factors that influence the outcome in the septic patient. Methods. A systematic literature review of studies published from 2014 to 2024 was conducted using the PubMed database. Eligible studies investigated the development of ML models incorporating commonly available laboratory and clinical data for predicting survival outcomes in adult ICU patients with sepsis. Study selection followed the PRISMA guidelines and relied on predefined inclusion criteria. All records were independently assessed by two reviewers, with conflicts resolved by a third senior reviewer. Data related to study design, methodology, results, and interpretation of the results were extracted in a predefined grid. Results. Overall, 19 studies were identified, encompassing primarily logistic regression, random forests, and neural networks. Most used datasets were US-based (MIMIC-III, MIMIC-IV, and eICU-CRD). The most common variables used in model development were age, albumin levels, lactate levels, and ventilator. ML models demonstrated superior performance metrics compared to conventional methods and traditional scoring systems. The best-performing model was a gradient boosting decision tree, with an area under curve of 0.992, an accuracy of 0.954, and a sensitivity of 0.917. However, several critical limitations should be carefully considered when interpreting the results, such as population selection bias (i.e., single center studies), small sample sizes, limited external validation, and model interpretability. Conclusions. Through real-time integration of routine laboratory and clinical data, ML-based tools can assist clinical decision-making and enhance the consistency and quality of sepsis management across various healthcare contexts, including ICUs with limited resources.

Sepsis mortality prediction with Machine Learning Tecniques

OBJECTIVE

To develop a sepsis death classification model based on machine learning techniques for patients admitted to the Intensive Care Unit (ICU).

DESIGN

Cross-sectional descriptive study.

SETTING

The Intensive Care Units (ICUs) of three Hospitals from Murcia (Spain) and patients from the MIMIC III open-access database.

PATIENTS

180 patients diagnosed with sepsis in the ICUs of three hospitals and a total of 4559 patients from the MIMIC III database.

MAIN VARIABLES OF INTEREST

Age, weight, heart rate, respiratory rate, temperature, lactate levels, partial oxygen saturation, systolic and diastolic blood pressure, pH, urine, and potassium levels.

RESULTS

A random forest classification model was calculated using the local and MIMIC III databases. The sensitivity of the model of our database, considering all the variables classified as important by the random forest, was 95.45%, the specificity was 100%, the accuracy was 96.77%, and an AUC of 95%. . In the case of the model based on the MIMIC III database, the sensitivity was 97.55%, the specificity was 100%, and the precision was 98.28%, with an AUC of 97.3%.

CONCLUSIONS

According to random forest classification in both databases, lactate levels, urine output and variables related to acid.base equilibrium were the most important variable in mortality due to sepsis in the ICU. The potassium levels were more critical in the MIMIC III database than the local database.

The development of neonatal neurointensive care

Brain injury remains one of the major unsolved problems in neonatal care, with survivors at high risk of lifelong neurodisability. It is unlikely that a single intervention can ameliorate neonatal brain injury, given the complex interaction between pathological processes, developmental trajectory, genetic susceptibility, and environmental influences. However, a coordinated, interdisciplinary approach to understand the root cause enables early detection, and diagnosis with enhanced clinical care offering the best chance of improving outcomes and facilitate new lines of neuroprotective treatments. Adult neurointensive care has existed as a speciality in its own right for over 20 years; however, it is only recently that large prospective studies have demonstrated the benefit of this model of care. The 'Neuro-intensive Care Nursery' model originated at the University of California San Francisco in 2008, and since then a growing number of units worldwide have adopted this approach. As well as providing consistent coordinated care for infants from a multidisciplinary team, it provides opportunities for specialist education and training in neonatal neurology, neuromonitoring, neuroimaging and nursing. This review outlines the origins of brain-oriented care of the neonate and the development of the Neuro-NICU (neonatal intensive care unit) and discusses some of the challenges and opportunities in expanding this model of care.

Predictive model of risk factors for 28-day mortality in patients with sepsis or sepsis-associated delirium based on the MIMIC-IV database

Research on the severity and prognosis of sepsis with or without progressive delirium is relatively insufficient. We constructed a prediction model of the risk factors for 28-day mortality in patients who developed sepsis or sepsis-associated delirium. The modeling group of patients diagnosed with Sepsis-3 and patients with progressive delirium of related indicators were selected from the MIMIC-IV database. Relevant independent risk factors were determined and integrated into the prediction model. Receiver operating characteristic (ROC) curves and the Hosmer-Lemeshow (HL) test were used to evaluate the prediction accuracy and goodness-of-fit of the model. Relevant indicators of patients with sepsis or progressive delirium admitted to the intensive care unit (ICU) of a 3A hospital in Xinjiang were collected and included in the verification group for comparative analysis and clinical validation of the prediction model. The total length of stay in the ICU, hemoglobin levels, albumin levels, activated partial thrombin time, and total bilirubin level were the five independent risk factors in constructing a prediction model. The area under the ROC curve of the predictive model (0.904) and the HL test result (χ2 = 8.518) indicate a good fit. This model is valuable for clinical diagnosis and treatment and auxiliary clinical decision-making.

Machine Learning-Based Mortality Prediction Model for Critically Ill Cancer Patients Admitted to the Intensive Care Unit (CanICU)

BACKGROUND

Although cancer patients are increasingly admitted to the intensive care unit (ICU) for cancer- or treatment-related complications, improved mortality prediction remains a big challenge. This study describes a new ML-based mortality prediction model for critically ill cancer patients admitted to ICU.

PATIENTS AND METHODS

We developed CanICU, a machine learning-based 28-day mortality prediction model for adult cancer patients admitted to ICU from Medical Information Mart for Intensive Care (MIMIC) database in the USA (n = 766), Yonsei Cancer Center (YCC, n = 3571), and Samsung Medical Center in Korea (SMC, n = 2563) from 2 January 2008 to 31 December 2017. The accuracy of CanICU was measured using sensitivity, specificity, and area under the receiver operating curve (AUROC).

RESULTS

A total of 6900 patients were included, with a 28-day mortality of 10.2%/12.7%/36.6% and a 1-year mortality of 30.0%/36.6%/58.5% in the YCC, SMC, and MIMIC-III cohort. Nine clinical and laboratory factors were used to construct the classifier using a random forest machine-learning algorithm. CanICU had 96% sensitivity/73% specificity with the area under the receiver operating characteristic (AUROC) of 0.94 for 28-day, showing better performance than current prognostic models, including the Acute Physiology and Chronic Health Evaluation (APACHE) or Sequential Organ Failure Assessment (SOFA) score. Application of CanICU in two external data sets across the countries yielded 79-89% sensitivity, 58-59% specificity, and 0.75-0.78 AUROC for 28-day mortality. The CanICU score was also correlated with one-year mortality with 88-93% specificity.

CONCLUSION

CanICU offers improved performance for predicting mortality in critically ill cancer patients admitted to ICU. A user-friendly online implementation is available and should be valuable for better mortality risk stratification to allocate ICU care for cancer patients.

Performance effectiveness of vital parameter combinations for early warning of sepsis-an exhaustive study using machine learning

Objective

To carry out exhaustive data-driven computations for the performance of noninvasive vital signs heart rate (HR), respiratory rate (RR), peripheral oxygen saturation (SpO2), and temperature (Temp), considered both independently and in all possible combinations, for early detection of sepsis.

Materials and methods

By extracting features interpretable by clinicians, we applied Gradient Boosted Decision Tree machine learning on a dataset of 2630 patients to build 240 models. Validation was performed on a geographically distinct dataset. Relative to onset, predictions were clocked as per 16 pairs of monitoring intervals and prediction times, and the outcomes were ranked.

Results

The combination of HR and Temp was found to be a minimal feature set yielding maximal predictability with area under receiver operating curve 0.94, sensitivity of 0.85, and specificity of 0.90. Whereas HR and RR each directly enhance prediction, the effects of SpO2 and Temp are significant only when combined with HR or RR. In benchmarking relative to standard methods Systemic Inflammatory Response Syndrome (SIRS), National Early Warning Score (NEWS), and quick-Sequential Organ Failure Assessment (qSOFA), Vital-SEP outperformed all 3 of them.

Conclusion

It can be concluded that using intensive care unit data even 2 vital signs are adequate to predict sepsis upto 6 h in advance with promising accuracy comparable to standard scoring methods and other sepsis predictive tools reported in literature. Vital-SEP can be used for fast-track prediction especially in limited resource hospital settings where laboratory based hematologic or biochemical assays may be unavailable, inaccurate, or entail clinically inordinate delays. A prospective study is essential to determine the clinical impact of the proposed sepsis prediction model and evaluate other outcomes such as mortality and duration of hospital stay.

Using model explanations to guide deep learning models towards consistent explanations for EHR data

It has been shown that identical deep learning (DL) architectures will produce distinct explanations when trained with different hyperparameters that are orthogonal to the task (e.g. random seed, training set order). In domains such as healthcare and finance, where transparency and explainability is paramount, this can be a significant barrier to DL adoption. In this study we present a further analysis of explanation (in)consistency on 6 tabular datasets/tasks, with a focus on Electronic Health Records data. We propose a novel deep learning ensemble architecture that trains its sub-models to produce consistent explanations, improving explanation consistency by as much as 315% (e.g. from 0.02433 to 0.1011 on MIMIC-IV), and on average by 124% (e.g. from 0.12282 to 0.4450 on the BCW dataset). We evaluate the effectiveness of our proposed technique and discuss the implications our results have for both industrial applications of DL and explainability as well as future methodological work.

Clinical applications of machine learning in the survival prediction and classification of sepsis: coagulation and heparin usage matter

BACKGROUND

Sepsis is a life-threatening syndrome eliciting highly heterogeneous host responses. Current prognostic evaluation methods used in clinical practice are characterized by an inadequate effectiveness in predicting sepsis mortality. Rapid identification of patients with high mortality risk is urgently needed. The phenotyping of patients will assistant invaluably in tailoring treatments.

METHODS

Machine learning and deep learning technology are used to characterize the patients' phenotype and determine the sepsis severity. The database used in this study is MIMIC-III and MIMIC-IV ('Medical information Mart for intensive care') which is a large, public, and freely available database. The K-means clustering is used to classify the sepsis phenotype. Convolutional neural network (CNN) was used to predict the 28-day survival rate based on 35 blood test variables of the sepsis patients, whereas a double coefficient quadratic multivariate fitting function (DCQMFF) is utilized to predict the 28-day survival rate with only 11 features of sepsis patients.

RESULTS

The patients were grouped into four clusters with a clear survival nomogram. The first cluster (C_1) was characterized by low white blood cell count, low neutrophil, and the highest lymphocyte proportion. C_2 obtained the lowest Sequential Organ Failure Assessment (SOFA) score and the highest survival rate. C_3 was characterized by significantly prolonged PTT, high SIC, and a higher proportion of patients using heparin than the patients in other clusters. The early mortality rate of patients in C_3 was high but with a better long-term survival rate than that in C_4. C_4 contained septic coagulation patients with the worst prognosis, characterized by slightly prolonged partial thromboplastin time (PTT), significantly prolonged prothrombin time (PT), and high septic coagulation disease score (SIC). The survival rate prediction accuracy of CNN and DCQMFF models reached 92% and 82%, respectively. The models were tested on an external dataset (MIMIC-IV) and achieved good performance. A DCQMFF-based application platform was established for fast prediction of the 28-day survival rate.

CONCLUSION

CNN and DCQMFF accurately predicted the sepsis patients' survival, while K-means successfully identified the phenotype groups. The distinct phenotypes associated with survival, and significant features correlated with mortality were identified. The findings suggest that sepsis patients with abnormal coagulation had poor outcomes, abnormal coagulation increase mortality during sepsis. The anticoagulation effects of appropriate heparin sodium treatment may improve extensive micro thrombosis-caused organ failure.

Artificial Intelligence to Improve Health Outcomes in the NICU and PICU: A Systematic Review

CONTEXT

Artificial intelligence (AI) technologies are increasingly used in pediatrics and have the potential to help inpatient physicians provide high-quality care for critically ill children.

OBJECTIVE

We aimed to describe the use of AI to improve any health outcome(s) in neonatal and pediatric intensive care.

DATA SOURCE

PubMed, IEEE Xplore, Cochrane, and Web of Science databases.

STUDY SELECTION

We used peer-reviewed studies published between June 1, 2010, and May 31, 2020, in which researchers described (1) AI, (2) pediatrics, and (3) intensive care. Studies were included if researchers assessed AI use to improve at least 1 health outcome (eg, mortality).

DATA EXTRACTION

Data extraction was conducted independently by 2 researchers. Articles were categorized by direct or indirect impact of AI, defined by the European Institute of Innovation and Technology Health joint report.

RESULTS

Of the 287 publications screened, 32 met inclusion criteria. Approximately 22% (n = 7) of studies revealed a direct impact and improvement in health outcomes after AI implementation. Majority were in prototype testing, and few were deployed into an ICU setting. Among the remaining 78% (n = 25) AI models outperformed standard clinical modalities and may have indirectly influenced patient outcomes. Quantitative assessment of health outcomes using statistical measures, such as area under the receiver operating curve (56%; n = 18) and specificity (38%; n = 12), revealed marked heterogeneity in metrics and standardization.

CONCLUSIONS

Few studies have revealed that AI has directly improved health outcomes for pediatric critical care patients. Further prospective, experimental studies are needed to assess AI's impact by using established implementation frameworks, standardized metrics, and validated outcome measures.

A novel artificial intelligence based intensive care unit monitoring system: using physiological waveforms to identify sepsis

A massive amount of multimodal data are continuously collected in the intensive care unit (ICU) along each patient stay, offering a great opportunity for the development of smart monitoring devices based on artificial intelligence (AI). The two main sources of relevant information collected in the ICU are the electronic health records (EHRs) and vital sign waveforms continuously recorded at the bedside. While EHRs are already widely processed by AI algorithms for prompt diagnosis and prognosis, AI-based assessments of the patients' pathophysiological state using waveforms are less developed, and their use is still limited to real-time monitoring for basic visual vital sign feedback at the bedside. This study uses data from the MIMIC-III database (PhysioNet) to propose a novel AI approach in ICU patient monitoring that incorporates features estimated by a closed-loop cardiovascular model, with the specific goal of identifying sepsis within the first hour of admission. Our top benchmark results (AUROC = 0.92, AUPRC = 0.90) suggest that features derived by cardiovascular control models may play a key role in identifying sepsis, by continuous monitoring performed through advanced multivariate modelling of vital sign waveforms. This work lays foundations for a deeper data integration paradigm which will help clinicians in their decision-making processes. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'.

Burden of Healthcare-Associated Infections in Sicily, Italy: Estimates from the Regional Point Prevalence Surveys 2016-2018

An assessment of the burden of healthcare-associated infections (HAIs) in terms of disability-adjusted life years (DALYs) is useful for comparing and ranking HAIs and to support infection prevention and control strategies. We estimated the burden of healthcare-associated pneumoniae (HAP), bloodstream infection (HA BSI), urinary tract infection (HA UTI), and surgical site infection (SSI) in Sicily, Italy. We used data from 15,642 patients aged 45 years and above, identified during three repeated point prevalence surveys (PPSs) conducted from 2016 to 2018 according to the European Centre for Disease Prevention and Control protocol. The methodology of the Burden of Communicable Diseases in Europe project was employed. The selected HAIs accounted for 8424 DALYs (95% uncertainty interval (UI): 7394-9605) annually in Sicily, corresponding to 344 DALYs per 100,000 inhabitants aged 45 years and above (95% UI: 302-392). Notably, more than 60% of the burden was attributable to HAP, followed by HA BSI, SSI, and HA UTI. The latter had the lowest burden despite a relatively high incidence, whereas HA BSI generated a high burden even through a relatively low incidence. Differences between our estimates and those of European and Italian PPSs encourage the estimation of the burden of HAIs region by region.

A machine learning approach to predict healthcare-associated infections at intensive care unit admission: findings from the SPIN-UTI project

BACKGROUND

Identifying patients at higher risk of healthcare-associated infections (HAIs) in intensive care units (ICUs) represents a major challenge for public health. Machine learning could improve patient risk stratification and lead to targeted infection prevention and control interventions.

AIM

To evaluate the performance of the Simplified Acute Physiology Score (SAPS) II for HAI risk prediction in ICUs, using both traditional statistical and machine learning approaches.

METHODS

Data for 7827 patients from the 'Italian Nosocomial Infections Surveillance in Intensive Care Units' project were used in this study. The Support Vector Machines (SVM) algorithm was applied to classify patients according to sex, patient origin, non-surgical treatment for acute coronary disease, surgical intervention, SAPS II at admission, presence of invasive devices, trauma, impaired immunity, and antibiotic therapy in 48 h preceding ICU admission.

FINDINGS

The performance of SAPS II for predicting HAI risk provides a receiver operating characteristic curve with an area under the curve of 0.612 (P<0.001) and accuracy of 56%. Considering SAPS II along with other characteristics at ICU admission, the SVM classifier was found to have accuracy of 88% and an AUC of 0.90 (P<0.001) for the test set. The predictive ability was lower when considering the same SVM model but with the SAPS II variable removed (accuracy 78%, AUC 0.66).

CONCLUSIONS

This study suggested that the SVM model is a useful tool for early prediction of patients at higher risk of HAIs at ICU admission.

Early Detection of Sepsis With Machine Learning Techniques: A Brief Clinical Perspective

Sepsis is a major cause of death worldwide. Over the past years, prediction of clinically relevant events through machine learning models has gained particular attention. In the present perspective, we provide a brief, clinician-oriented vision on the following relevant aspects concerning the use of machine learning predictive models for the early detection of sepsis in the daily practice: (i) the controversy of sepsis definition and its influence on the development of prediction models; (ii) the choice and availability of input features; (iii) the measure of the model performance, the output, and their usefulness in the clinical practice. The increasing involvement of artificial intelligence and machine learning in health care cannot be disregarded, despite important pitfalls that should be always carefully taken into consideration. In the long run, a rigorous multidisciplinary approach to enrich our understanding in the application of machine learning techniques for the early recognition of sepsis may show potential to augment medical decision-making when facing this heterogeneous and complex syndrome.

Prediction of perinatal death using machine learning models: a birth registry-based cohort study in northern Tanzania

OBJECTIVE

We aimed to determine the key predictors of perinatal deaths using machine learning models compared with the logistic regression model.

DESIGN

A secondary data analysis using the Kilimanjaro Christian Medical Centre (KCMC) Medical Birth Registry cohort from 2000 to 2015. We assessed the discriminative ability of models using the area under the receiver operating characteristics curve (AUC) and the net benefit using decision curve analysis.

SETTING

The KCMC is a zonal referral hospital located in Moshi Municipality, Kilimanjaro region, Northern Tanzania. The Medical Birth Registry is within the hospital grounds at the Reproductive and Child Health Centre.

PARTICIPANTS

Singleton deliveries (n=42 319) with complete records from 2000 to 2015.

PRIMARY OUTCOME MEASURES

Perinatal death (composite of stillbirths and early neonatal deaths). These outcomes were only captured before mothers were discharged from the hospital.

RESULTS

The proportion of perinatal deaths was 3.7%. There were no statistically significant differences in the predictive performance of four machine learning models except for bagging, which had a significantly lower performance (AUC 0.76, 95% CI 0.74 to 0.79, p=0.006) compared with the logistic regression model (AUC 0.78, 95% CI 0.76 to 0.81). However, in the decision curve analysis, the machine learning models had a higher net benefit (ie, the correct classification of perinatal deaths considering a trade-off between false-negatives and false-positives)-over the logistic regression model across a range of threshold probability values.

CONCLUSIONS

In this cohort, there was no significant difference in the prediction of perinatal deaths between machine learning and logistic regression models, except for bagging. The machine learning models had a higher net benefit, as its predictive ability of perinatal death was considerably superior over the logistic regression model. The machine learning models, as demonstrated by our study, can be used to improve the prediction of perinatal deaths and triage for women at risk.

Survival prediction of patients with sepsis from age, sex, and septic episode number alone

Sepsis is a life-threatening condition caused by an exaggerated reaction of the body to an infection, that leads to organ failure or even death. Since sepsis can kill a patient even in just one hour, survival prediction is an urgent priority among the medical community: even if laboratory tests and hospital analyses can provide insightful information about the patient, in fact, they might not come in time to allow medical doctors to recognize an immediate death risk and treat it properly. In this context, machine learning can be useful to predict survival of patients within minutes, especially when applied to few medical features easily retrievable. In this study, we show that it is possible to achieve this goal by applying computational intelligence algorithms to three features of patients with sepsis, recorded at hospital admission: sex, age, and septic episode number. We applied several data mining methods to a cohort of 110,204 admissions of patients, and obtained high prediction scores both on this complete dataset (top precision-recall area under the curve PR AUC = 0.966) and on its subset related to the recent Sepsis-3 definition (top PR AUC = 0.860). Additionally, we tested our models on an external validation cohort of 137 patients, and achieved good results in this case too (top PR AUC = 0.863), confirming the generalizability of our approach. Our results can have a huge impact on clinical settings, allowing physicians to forecast the survival of patients by sex, age, and septic episode number alone.

Exploration of critical care data by using unsupervised machine learning

BACKGROUND AND OBJECTIVE

Identification of subgroups may be useful to understand the clinical characteristics of ICU patients. The purposes of this study were to apply an unsupervised machine learning method to ICU patient data to discover subgroups among them; and to examine their clinical characteristics, therapeutic procedures conducted during the ICU stay, and discharge dispositions.

METHODS

K-means clustering method was used with 1503 observations and 9 types of laboratory test results as features.

RESULTS

Three clusters were identified from this specific population. Blood urea nitrogen, creatinine, potassium, hemoglobin, and red blood cell were distinctive between the clusters. Cluster Three presented the highest blood products transfusion rate (19.8%), followed by Cluster One (15.5%) and cluster Two (9.3%), which was significantly different. Hemodialysis was more frequently provided to Cluster Three while bronchoscopy was done to Cluster One and Two. Cluster Three showed the highest mortality (30.4%), which was more than two-fold compared to Cluster One (14.1%) and Two (12.2%).

CONCLUSION

Three subgroups were identified and their clinical characteristics were compared. These findings may be useful to anticipate treatment strategies and probable outcomes of ICU patients. Unsupervised machine learning may enable ICU multi-dimensional data to be organized and to make sense of the data.

AI in the Intensive Care Unit: Up-to-Date Review

AI is the latest technologic trend that likely will have a huge impact in medicine. AI's potential lies in its ability to process large volumes of data and perform complex pattern analyses. The ICU is an area of medicine that is particularly conducive to AI applications. Much AI ICU research currently is focused on improving high volumes of data on high-risk patients and making clinical workflow more efficient. Emerging topics of AI medicine in the ICU include AI sensors, sepsis prediction, AI in the NICU or SICU, and the legal role of AI in medicine. This review will cover the current applications of AI medicine in the ICU, potential pitfalls, and other AI medicine-related topics relevant for the ICU.

Supervised classification techniques for prediction of mortality in adult patients with sepsis

BACKGROUND

Sepsis mortality is still unacceptably high and an appropriate prognostic tool may increase the accuracy for clinical decisions.

OBJECTIVE

To evaluate several supervised techniques of Artificial Intelligence (AI) for classification and prediction of mortality, in adult patients hospitalized by emergency services with sepsis diagnosis.

METHODS

Secondary data analysis of a prospective cohort in three university hospitals in Medellín, Colombia. We included patients >18 years hospitalized for suspected or confirmed infection and any organ dysfunction according to the Sepsis-related Organ Failure Assessment. The outcome variable was hospital mortality and the prediction variables were grouped into those related to the initial clinical treatment and care or to the direct measurement of physiological disturbances. Four supervised classification techniques were analyzed: the C4.5 Decision Tree, Random Forest, artificial neural networks (ANN) and support vector machine (SVM) models. Their performance was evaluated by the concordance between the observed and predicted outcomes and by the discrimination according to AUC-ROC.

RESULTS

A total of 2510 patients with a median age of 62 years (IQR = 46-74) and an overall hospital mortality rate of 11.5% (n = 289). The best discrimination was provided by the SVM and ANN using physiological variables, with an AUC-ROC of 0.69 (95%CI: 0.62; 0.76) and AUC-ROC of 0.69 (95%CI: 0.61; 0.76) respectively.

CONCLUSION

Deep learning and AI are increasingly used as support tools in clinical medicine. Their performance in a syndrome as complex and heterogeneous as sepsis may be a new horizon in clinical research. SVM and ANN seem promising for improving sepsis classification and prognosis.

Personalized machine learning approach to predict candidemia in medical wards

PURPOSE

Candidemia is a highly lethal infection; several scores have been developed to assist the diagnosis process and recently different models have been proposed. Aim of this work was to assess predictive performance of a Random Forest (RF) algorithm for early detection of candidemia in the internal medical wards (IMWs).

METHODS

A set of 42 potential predictors was acquired in a sample of 295 patients (male: 142, age: 72 ± 15 years; candidemia: 157/295; bacteremia: 138/295). Using tenfold cross-validation, a RF algorithm was compared with a classic stepwise multivariable logistic regression model; discriminative performance was assessed by C-statistics, sensitivity and specificity, while calibration was evaluated by Hosmer-Lemeshow test.

RESULTS

The best tuned RF algorithm demonstrated excellent discrimination (C-statistics = 0.874 ± 0.003, sensitivity = 84.24% ± 0.67%, specificity = 91% ± 2.63%) and calibration (Hosmer-Lemeshow statistics = 12.779 ± 1.369, p = 0.120), markedly greater than the ones guaranteed by the classic stepwise logistic regression (C-statistics = 0.829 ± 0.011, sensitivity = 80.21% ± 1.67%, specificity = 84.81% ± 2.68%; Hosmer-Lemeshow statistics = 38.182 ± 15.983, p < 0.001). In addition, RF suggests a major role of in-hospital antibiotic treatment with microbioma highly impacting antimicrobials (MHIA) that are found as a fundamental risk of candidemia, further enhanced by TPN. When in-hospital MHIA therapy is not performed, PICC is the dominant risk factor for candidemia, again enhanced by TPN. When PICC is not used and MHIA therapy is not performed, the risk of candidemia is minimum, slightly increased by in-hospital antibiotic therapy.

CONCLUSION

RF accurately estimates the risk of candidemia in patients admitted to IMWs. Machine learning technique might help to identify patients at high risk of candidemia, reduce the delay in empirical treatment and improve appropriateness in antifungal prescription.

Data Imbalance in Autism Pre-Diagnosis Classification Systems: An Experimental Study

Machine learning (ML) is a branch of computer science that is rapidly gaining popularity within the healthcare arena due to its ability to explore large datasets to discover useful patterns that can be interepreted for decision-making and prediction. ML techniques are used for the analysis of clinical parameters and their combinations for prognosis, therapy planning and support and patient management and wellbeing. In this research, we investigate a crucial problem associated with medical applications such as autism spectrum disorder (ASD) data imbalances in which cases are far more than just controls in the dataset. In autism diagnosis data, the number of possible instances is linked with one class, i.e. the no ASD is larger than the ASD, and this may cause performance issues such as models favouring the majority class and undermining the minority class. This research experimentally measures the impact of class imbalance issue on the performance of different classifiers on real autism datasets when various data imbalance approaches are utilised in the pre-processing phase. We employ oversampling techniques, such as Synthetic Minority Oversampling (SMOTE), and undersampling with different classifiers including Naive Bayes, RIPPER, C4.5 and Random Forest to measure the impact of these on the performance of the models derived in terms of area under curve and other metrics. Results pinpoint that oversampling techniques are superior to undersampling techniques, at least for the toddlers’ autism dataset that we consider, and suggest that further work should look at incorporating sampling techniques with feature selection to generate models that do not overfit the dataset.

Computational Health Engineering Applied to Model Infectious Diseases and Antimicrobial Resistance Spread

Infectious diseases are the primary cause of mortality worldwide. The dangers of infectious disease are compounded with antimicrobial resistance, which remains the greatest concern for human health. Although novel approaches are under investigation, the World Health Organization predicts that by 2050, septicaemia caused by antimicrobial resistant bacteria could result in 10 million deaths per year. One of the main challenges in medical microbiology is to develop novel experimental approaches, which enable a better understanding of bacterial infections and antimicrobial resistance. After the introduction of whole genome sequencing, there was a great improvement in bacterial detection and identification, which also enabled the characterization of virulence factors and antimicrobial resistance genes. Today, the use of in silico experiments jointly with computational and machine learning offer an in depth understanding of systems biology, allowing us to use this knowledge for the prevention, prediction, and control of infectious disease. Herein, the aim of this review is to discuss the latest advances in human health engineering and their applicability in the control of infectious diseases. An in-depth knowledge of host–pathogen–protein interactions, combined with a better understanding of a host’s immune response and bacterial fitness, are key determinants for halting infectious diseases and antimicrobial resistance dissemination.