Using Machine Learning to Predict Early Onset Acute Organ Failure in Critically Ill Intensive Care Unit Patients With Sickle Cell Disease: Retrospective Study

Machine Learning Predicts Acute Kidney Injury in Hospitalized Patients with Sickle Cell Disease

INTRODUCTION

Acute kidney injury (AKI) is common among hospitalized patients with sickle cell disease (SCD) and contributes to increased morbidity and mortality. Early identification and management of AKI is essential to preventing poor outcomes. We aimed to predict AKI earlier in patients with SCD using a machine-learning model that utilized continuous minute-by-minute physiological data.

METHODS

A total of6,278 adult SCD patient encounters were admitted to inpatient units across five regional hospitals in Memphis, TN, over 3 years, from July 2017 to December 2020. From these, 1,178 patients were selected after filtering for data availability. AKI was identified in 82 (7%) patient encounters, using the 2012 Kidney Disease Improving Global Outcomes (KDIGO) criteria. The remaining 1,096 encounters served as controls. Features derived from five physiological data streams, heart rate, respiratory rate, and blood pressure (systolic, diastolic, and mean), captured every minute from bedside monitors were used. An XGBoost classifier was used for classification.

RESULTS

Our model accurately predicted AKI up to 12 h before onset with an area under the receiver operator curve (AUROC) of 0.91 (95% CI [0.89-0.93]) and up to 48 h before AKI with an AUROC of 0.82 (95% CI [0.80-0.83]). Patients with AKI were more likely to be female (64.6%) and have history of hypertension, pulmonary hypertension, chronic kidney disease, and pneumonia than the control group.

CONCLUSION

XGBoost accurately predicted AKI as early as 12 h before onset in hospitalized SCD patients and may enable the development of innovative prevention strategies.

Current Applications of Artificial Intelligence in Sarcoidosis

PURPOSE

Sarcoidosis is a complex disease which can affect nearly every organ system with manifestations ranging from asymptomatic imaging findings to sudden cardiac death. As such, diagnosis and prognostication are topics of continued investigation. Recent technological advancements have introduced multiple modalities of artificial intelligence (AI) to the study of sarcoidosis. Machine learning, deep learning, and radiomics have predominantly been used to study sarcoidosis.

METHODS

Articles were collected by searching online databases using keywords such as sarcoid, machine learning, artificial intelligence, radiomics, and deep learning. Article titles and abstracts were reviewed for relevance by a single reviewer. Articles written in languages other than English were excluded.

CONCLUSIONS

Machine learning may be used to help diagnose pulmonary sarcoidosis and prognosticate in cardiac sarcoidosis. Deep learning is most comprehensively studied for diagnosis of pulmonary sarcoidosis and has less frequently been applied to prognostication in cardiac sarcoidosis. Radiomics has primarily been used to differentiate sarcoidosis from malignancy. To date, the use of AI in sarcoidosis is limited by the rarity of this disease, leading to small, suboptimal training sets. Nevertheless, there are applications of AI that have been used to study other systemic diseases, which may be adapted for use in sarcoidosis. These applications include discovery of new disease phenotypes, discovery of biomarkers of disease onset and activity, and treatment optimization.

Artificial intelligence in sickle disease

Artificial intelligence (AI) is rapidly becoming an established arm in medical sciences and clinical practice in numerous medical fields. Its implications have been rising and are being widely used in research, diagnostics, and treatment options for many pathologies, including sickle cell disease (SCD). AI has started new ways to improve risk stratification and diagnosing SCD complications early, allowing rapid intervention and reallocation of resources to high-risk patients. We reviewed the literature for established and new AI applications that may enhance management of SCD through advancements in diagnosing SCD and its complications, risk stratification, and the effect of AI in establishing an individualized approach in managing SCD patients in the future. Aim: to review the benefits and drawbacks of resources utilizing AI in clinical practice for improving the management for SCD cases.

An investigation of long-term outcome of rabbit anti-thymocyte globulin and cyclosporine therapy for pediatric severe aplastic anemia

Children with severe aplastic anemia (SAA) face heterogeneous prognoses after immunosuppressive therapy (IST). There are few models that can predict the long-term outcomes of IST for these patients. The objective of this paper is to develop a more effective prediction model for SAA prognosis based on clinical electronic medical records from 203 children with newly diagnosed SAA. In the early stage, a novel model for long-term outcomes of SAA patients with IST was developed using machine-learning techniques. Among the indicators related to long-term efficacy, white blood cell count, lymphocyte count, absolute reticulocyte count, lymphocyte ratio in bone-marrow smears, C-reactive protein, and the level of IL-6, IL-8 and vitamin B12 in the early stage are strongly correlated with long-term efficacy (P < .05). Taken together, we analyzed the long-term outcomes of rabbit anti-thymocyte globulin and cyclosporine therapy for children with SAA through machine-learning techniques, which may shorten the observation period of therapeutic effects and reduce treatment costs and time.

A systematic review of predictive models for hospital-acquired pressure injury using machine learning

AIMS AND OBJECTIVES

To summarize the use of machine learning (ML) for hospital-acquired pressure injury (HAPI) prediction and to systematically assess the performance and construction process of ML models to provide references for establishing high-quality ML predictive models.

BACKGROUND

As an adverse event, HAPI seriously affects patient prognosis and quality of life, and causes unnecessary medical investment. At present, the performance of various scales used to predict HAPIs is still unsatisfactory. As a new statistical tool, ML has been applied to predict HAPIs. However, its performance has varied in different studies; moreover, some deficiencies in the model construction process were observed in each study.

DESIGN

Systematic review.

METHODS

Relevant articles published between 2010-2021 were identified in the PubMed, Web of Science, Scopus, Embase and CINHAL databases. Study selection was performed in accordance with the preferred reporting items for systematic reviews and meta-analysis guidelines. The quality of the included articles was assessed using the prediction model risk of bias assessment tool.

RESULTS

Twenty-three studies out of 1793 articles were considered in this systematic review. The sample size of each study ranged from 149-75353; the prevalence of pressure injuries ranged from 0.5%-49.8%. ML showed good performance for HAPI prediction. However, some deficiencies were observed in terms of data management, data pre-processing and model validation.

CONCLUSIONS

ML, as a powerful decision-making assistance tool, is helpful for the prediction of HAPIs. However, existing studies have been insufficient in terms of data management, data pre-processing and model validation. Future studies should address these issues to establish ML models for HAPI prediction that can be widely used in clinical practice.

RELEVANCE TO CLINICAL PRACTICE

This review highlights that ML is helpful in predicting HAPI; however, in the process of data management, data pre-processing and model validation, some deficiencies still need to be addressed. The ultimate goal of integrating ML into HAPI prediction is to develop a practical clinical decision-making tool. A complete and rigorous model construction process should be followed in future studies to develop high-quality ML models that can be applied in clinical practice.

Phenotypes of sickle cell intensive care admissions: an unsupervised machine learning approach in a single-center retrospective cohort

Sickle cell disease (SCD) is associated with multiple known complications and increased mortality. This study aims to further understand the profile of intensive care unit (ICU) admissions of SCD patients. In this single-center retrospective cohort (approval number 0926-11), we evaluated SCD-related ICU admissions at our hospital in São Paulo, Brazil. Admissions were clustered using clinical data and organ dysfunction at ICU admission. A hierarchical clustering method was used to distinguish phenotypes. From 140 admissions obtained, 125 were included. The mean age was 30 years, 48% were male, and SS genotype was predominant (71.2%). Non-surgical causes of admissions accounted for 85.6% (n = 107). The mean Sequential Organ Failure Assessment score (SOFA) was 4 (IQR 2-7). Vasopressors were required by 12% and mechanical ventilation by 17.6%. After analysis of the average silhouette width, the optimal number of clusters was 3: cluster 1 (n = 69), cluster 2 (n = 25), cluster 3 (n = 31). Cluster 1 had a mean age of 29 years, 87% of SS genotype, and mean SOFA of 4. Cluster 2 had a mean age of 37 years, 80% of SS genotype, and mean SOFA of 8. Cluster 3 had a mean age of 26 years, 29% of SS genotype, and mean SOFA of 3. The need for mechanical ventilation was 11.6%, 44%, and 9.7%, respectively. Mortality was significantly higher in cluster 2 (44%, p = 0.012). This cohort of critical SCD admissions suggested the presence of three different profiles. This can be informative in the ICU setting to identify SCD patients at higher risk of worse outcomes.

Prediction of Poststroke Urinary Tract Infection Risk in Immobile Patients Using Machine Learning: a observational cohort study

BACKGROUND

Urinary tract infection (UTI) is one of major nosocomial infections significantly affecting the outcomes of immobile stroke patients. Previous studies have identified several risk factors, but it's still challenging to accurately estimate personal UTI risk.

OBJECTIVES

We aimed to develop predictive models for UTI risk identification for immobile stroke patients.

METHODS

Research data were collected from our previous multi-centre study. Derivation cohort included 3982 immobile stroke patients collected from November 1, 2015 to June 30, 2016; external validation cohort included 3837 patients collected from November 1, 2016 to July 30, 2017. 6 machine learning models and an ensemble learning model were derived based on 80% of derivation cohort and effectiveness was evaluated with the remaining 20%. We used Shapley additive explanation values to determine feature importance and examine the clinical significance of prediction models.

RESULTS

2.59% (103/3982) patients were diagnosed with UTI in derivation cohort, 1.38% (53/3837) in external cohort. The ensemble learning model performed the best in area under the receiver operating characteristic (ROC) curve in internal validation (82.2%); second best in external validation (80.8%). In addition, the ensemble learning model performed the best sensitivity in both internal and external validation sets (80.9% and 81.1%, respectively). We also identified seven UTI risk factors (pneumonia, glucocorticoid use, female sex, mixed cerebrovascular disease, increased age, prolonged length of stay, and duration of catheterization).

CONCLUSIONS

Our ensemble learning model demonstrated promising performance. Future work should continue to develop a more concise scoring tool based on machine learning models and prospectively examining the model in practical use, thus improving clinical outcomes.

Measuring Pain in Sickle Cell Disease using Clinical Text

Sickle Cell Disease (SCD) is a hereditary disorder of red blood cells in humans. Complications such as pain, stroke, and organ failure occur in SCD as malformed, sickled red blood cells passing through small blood vessels get trapped. Particularly, acute pain is known to be the primary symptom of SCD. The insidious and subjective nature of SCD pain leads to challenges in pain assessment among Medical Practitioners (MPs). Thus, accurate identification of markers of pain in patients with SCD is crucial for pain management. Classifying clinical notes of patients with SCD based on their pain level enables MPs to give appropriate treatment. We propose a binary classification model to predict pain relevance of clinical notes and a multiclass classification model to predict pain level. While our four binary machine learning (ML) classifiers are comparable in their performance, Decision Trees had the best performance for the multiclass classification task achieving 0.70 in F-measure. Our results show the potential clinical text analysis and machine learning offer to pain management in sickle cell patients.