On classifying sepsis heterogeneity in the ICU: insight using machine learning

Association between sub-phenotypes identified using latent class analysis and neurological outcomes in patients with out-of-hospital cardiac arrest in Japan

BACKGROUND

In patients who experience out-of-hospital cardiac arrest (OHCA), it is important to assess the association of sub-phenotypes identified by latent class analysis (LCA) using pre-hospital prognostic factors and factors measurable immediately after hospital arrival with neurological outcomes at 30 days, which would aid in making treatment decisions.

METHODS

This study retrospectively analyzed data obtained from the Japanese OHCA registry between June 2014 and December 2019. The registry included a complete set of data on adult patients with OHCA, which was used in the LCA. The association between the sub-phenotypes and 30-day survival with favorable neurological outcomes was investigated. Furthermore, adjusted odds ratios (ORs) and 95% confidence intervals (CIs) were estimated by multivariate logistic regression analysis using in-hospital data as covariates.

RESULTS

A total of, 22,261 adult patients who experienced OHCA were classified into three sub-phenotypes. The factor with the highest discriminative power upon patient's arrival was Glasgow Coma Scale followed by partial pressure of oxygen. Thirty-day survival with favorable neurological outcome as the primary outcome was evident in 66.0% participants in Group 1, 5.2% in Group 2, and 0.5% in Group 3. The 30-day survival rates were 80.6%, 11.8%, and 1.3% in groups 1, 2, and 3, respectively. Logistic regression analysis revealed that the ORs (95% CI) for 30-day survival with favorable neurological outcomes were 137.1 (99.4-192.2) for Group 1 and 4.59 (3.46-6.23) for Group 2 in comparison to Group 3. For 30-day survival, the ORs (95%CI) were 161.7 (124.2-212.1) for Group 1 and 5.78 (4.78-7.04) for Group 2, compared to Group 3.

CONCLUSIONS

This study identified three sub-phenotypes based on the prognostic factors available immediately after hospital arrival that could predict neurological outcomes and be useful in determining the treatment strategy of patients experiencing OHCA upon their arrival at the hospital.

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.

Soft phenotyping for sepsis via EHR time-aware soft clustering

OBJECTIVE

Sepsis is one of the most serious hospital conditions associated with high mortality. Sepsis is the result of a dysregulated immune response to infection that can lead to multiple organ dysfunction and death. Due to the wide variability in the causes of sepsis, clinical presentation, and the recovery trajectories, identifying sepsis sub-phenotypes is crucial to advance our understanding of sepsis characterization, to choose targeted treatments and optimal timing of interventions, and to improve prognostication. Prior studies have described different sub-phenotypes of sepsis using organ-specific characteristics. These studies applied clustering algorithms to electronic health records (EHRs) to identify disease sub-phenotypes. However, prior approaches did not capture temporal information and made uncertain assumptions about the relationships among the sub-phenotypes for clustering procedures.

METHODS

We developed a time-aware soft clustering algorithm guided by clinical variables to identify sepsis sub-phenotypes using data available in the EHR.

RESULTS

We identified six novel sepsis hybrid sub-phenotypes and evaluated them for medical plausibility. In addition, we built an early-warning sepsis prediction model using logistic regression.

CONCLUSION

Our results suggest that these novel sepsis hybrid sub-phenotypes are promising to provide more accurate information on sepsis-related organ dysfunction and sepsis recovery trajectories which can be important to inform management decisions and sepsis prognosis.

Advances and Challenges in Sepsis Management: Modern Tools and Future Directions

Sepsis, a critical condition marked by systemic inflammation, profoundly impacts both innate and adaptive immunity, often resulting in lymphopenia. This immune alteration can spare regulatory T cells (Tregs) but significantly affects other lymphocyte subsets, leading to diminished effector functions, altered cytokine profiles, and metabolic changes. The complexity of sepsis stems not only from its pathophysiology but also from the heterogeneity of patient responses, posing significant challenges in developing universally effective therapies. This review emphasizes the importance of phenotyping in sepsis to enhance patient-specific diagnostic and therapeutic strategies. Phenotyping immune cells, which categorizes patients based on clinical and immunological characteristics, is pivotal for tailoring treatment approaches. Flow cytometry emerges as a crucial tool in this endeavor, offering rapid, low cost and detailed analysis of immune cell populations and their functional states. Indeed, this technology facilitates the understanding of immune dysfunctions in sepsis and contributes to the identification of novel biomarkers. Our review underscores the potential of integrating flow cytometry with omics data, machine learning and clinical observations to refine sepsis management, highlighting the shift towards personalized medicine in critical care. This approach could lead to more precise interventions, improving outcomes in this heterogeneously affected patient population.

ExpertNet: A Deep Learning Approach to Combined Risk Modeling and Subtyping in Intensive Care Units

Risk models play a crucial role in disease prevention, particularly in intensive care units (ICUs). Diseases often have complex manifestations with heterogeneous subpopulations, or subtypes, that exhibit distinct clinical characteristics. Risk models that explicitly model subtypes have high predictive accuracy and facilitate subtype-specific personalization. Such models combine clustering and classification methods but do not effectively utilize the inferred subtypes in risk modeling. Their limitations include tendency to obtain degenerate clusters and cluster-specific data scarcity leading to insufficient training data for the corresponding classifier. In this article, we develop a new deep learning model for simultaneous clustering and classification, ExpertNet, with novel loss terms and network training strategies that address these limitations. The performance of ExpertNet is evaluated on the tasks of predicting risk of (i) sepsis and (ii) acute respiratory distress syndrome (ARDS), using two large electronic medical records datasets from ICUs. Our extensive experiments show that, in comparison to state-of-the-art baselines for combined clustering and classification, ExpertNet achieves superior accuracy in risk prediction for both ARDS and sepsis; and comparable clustering performance. Visual analysis of the clusters further demonstrates that the clusters obtained are clinically meaningful and a knowledge-distilled model shows significant differences in risk factors across the subtypes. By addressing technical challenges in training neural networks for simultaneous clustering and classification, ExpertNet lays the algorithmic foundation for the future development of subtype-aware risk models.

Using machine learning for process improvement in sepsis management

INTRODUCTION

In the U.S., sepsis afflicts 1.7 million adults, causing 270,000 deaths each year. Early detection of sepsis could decrease the number of deaths by 92,000 annually and decrease hospital expenditures by 1.5 billion USD. Few prior studies and reviews have presented a holistic understanding of the relationship between machine learning and existing process improvement measures. This study, in addition to discussing machine learning and existing process improvements measures, elaborates on the disadvantages and the barriers to integrating machine learning into the clinic. This article synthesizes previous studies to educate healthcare professionals on effectively managing sepsis by leveraging the benefits of machine learning.

METHODS

This study used the PubMed database. Search terms include sepsis antibiotics, sepsis process improvement, sepsis machine learning. Our search criteria included previous studies published between January 1, 2017, and February 1, 2022.

RESULTS/DISCUSSION

Although machine learning algorithms have better predictive capabilities, their effectiveness in the clinical setting is limited as studies show mixed results because the medical staff often fails to intervene. To overcome poor interventional response, clinicians need to work with the facility's IT department to ensure integration into clinical workflow and minimize alert-fatigue. Algorithms should enhance the productivity of clinical teams, not attempt to replace them entirely.

CONCLUSION

Hospitals can employ process improvement measures that effectively utilize machine learning algorithms to ensure integration into clinical workflows. Healthcare professionals can utilize workflow tools in addition to the predictive capabilities of machine learning to enhance clinical decisions in sepsis.

Machine Learning-Based Early Prediction of Sepsis Using Electronic Health Records: A Systematic Review

BACKGROUND

Sepsis, a life-threatening infection-induced inflammatory condition, has significant global health impacts. Timely detection is crucial for improving patient outcomes as sepsis can rapidly progress to severe forms. The application of machine learning (ML) and deep learning (DL) to predict sepsis using electronic health records (EHRs) has gained considerable attention for timely intervention.

METHODS

PubMed, IEEE Xplore, Google Scholar, and Scopus were searched for relevant studies. All studies that used ML/DL to detect or early-predict the onset of sepsis in the adult population using EHRs were considered. Data were extracted and analyzed from all studies that met the criteria and were also evaluated for their quality.

RESULTS

This systematic review examined 1942 articles, selecting 42 studies while adhering to strict criteria. The chosen studies were predominantly retrospective (n = 38) and spanned diverse geographic settings, with a focus on the United States. Different datasets, sepsis definitions, and prevalence rates were employed, necessitating data augmentation. Heterogeneous parameter utilization, diverse model distribution, and varying quality assessments were observed. Longitudinal data enabled early sepsis prediction, and quality criteria fulfillment varied, with inconsistent funding-article quality correlation.

CONCLUSIONS

This systematic review underscores the significance of ML/DL methods for sepsis detection and early prediction through EHR data.

Clinical Sepsis Phenotypes in Critically Ill Patients

Sepsis, defined as the life-threatening dysregulated host response to an infection leading to organ dysfunction, is considered as one of the leading causes of mortality worldwide, especially in intensive care units (ICU). Moreover, sepsis remains an enigmatic clinical syndrome, with complex pathophysiology incompletely understood and a great heterogeneity both in terms of clinical expression, patient response to currently available therapeutic interventions and outcomes. This heterogeneity proves to be a major obstacle in our quest to deliver improved treatment in septic critical care patients; thus, identification of clinical phenotypes is absolutely necessary. Although this might be seen as an extremely difficult task, nowadays, artificial intelligence and machine learning techniques can be recruited to quantify similarities between individuals within sepsis population and differentiate them into distinct phenotypes regarding not only temperature, hemodynamics or type of organ dysfunction, but also fluid status/responsiveness, trajectories in ICU and outcome. Hopefully, we will eventually manage to determine both the subgroup of septic patients that will benefit from a therapeutic intervention and the correct timing of applying the intervention during the disease process.

Extracellular Vesicles from Different Sources of Mesenchymal Stromal Cells Have Distinct Effects on Lung and Distal Organs in Experimental Sepsis

The effects of the administration of mesenchymal stromal cells (MSC) may vary according to the source. We hypothesized that MSC-derived extracellular vesicles (EVs) obtained from bone marrow (BM), adipose (AD), or lung (L) tissues may also lead to different effects in sepsis. We profiled the proteome from EVs as a first step toward understanding their mechanisms of action. Polymicrobial sepsis was induced in C57BL/6 mice by cecal ligation and puncture (SEPSIS) and SHAM (control) animals only underwent laparotomy. Twenty-four hours after surgery, animals in the SEPSIS group were randomized to receive saline or 3 × 10⁶ MSC-derived EVs from BM, AD, or L. The diffuse alveolar damage was decreased with EVs from all three sources. In kidneys, BM-, AD-, and L-EVs reduced edema and expression of interleukin-18. Kidney injury molecule-1 expression decreased only in BM- and L-EVs groups. In the liver, only BM-EVs reduced congestion and cell infiltration. The size and number of EVs from different sources were not different, but the proteome of the EVs differed. BM-EVs were enriched for anti-inflammatory proteins compared with AD-EVs and L-EVs. In conclusion, BM-EVs were associated with less organ damage compared with the other sources of EVs, which may be related to differences detected in their proteome.

A hierarchical multilabel graph attention network method to predict the deterioration paths of chronic hepatitis B patients

OBJECTIVE

Estimating the deterioration paths of chronic hepatitis B (CHB) patients is critical for physicians' decisions and patient management. A novel, hierarchical multilabel graph attention-based method aims to predict patient deterioration paths more effectively. Applied to a CHB patient data set, it offers strong predictive utilities and clinical value.

MATERIALS AND METHODS

The proposed method incorporates patients' responses to medications, diagnosis event sequences, and outcome dependencies to estimate deterioration paths. From the electronic health records maintained by a major healthcare organization in Taiwan, we collect clinical data about 177 959 patients diagnosed with hepatitis B virus infection. We use this sample to evaluate the proposed method's predictive efficacy relative to 9 existing methods, as measured by precision, recall, F-measure, and area under the curve (AUC).

RESULTS

We use 20% of the sample as holdouts to test each method's prediction performance. The results indicate that our method consistently and significantly outperforms all benchmark methods. It attains the highest AUC, with a 4.8% improvement over the best-performing benchmark, as well as 20.9% and 11.4% improvements in precision and F-measures, respectively. The comparative results demonstrate that our method is more effective for predicting CHB patients' deterioration paths than existing predictive methods.

DISCUSSION AND CONCLUSION

The proposed method underscores the value of patient-medication interactions, temporal sequential patterns of distinct diagnosis, and patient outcome dependencies for capturing dynamics that underpin patient deterioration over time. Its efficacious estimates grant physicians a more holistic view of patient progressions and can enhance their clinical decision-making and patient management.

Prediction of Prednisolone Dose Correction Using Machine Learning

Wrong dose, a common prescription error, can cause serious patient harm, especially in the case of high-risk drugs like oral corticosteroids. This study aims to build a machine learning model to predict dose-related prescription modifications for oral prednisolone tablets (i.e., highly imbalanced data with very few positive cases). Prescription data were obtained from the electronic medical records at a single institute. Cluster analysis classified the clinical departments into six clusters with similar patterns of prednisolone prescription. Two patterns of training datasets were created with/without preprocessing by the SMOTE method. Five ML models (SVM, KNN, GB, RF, and BRF) and logistic regression (LR) models were constructed by Python. The model was internally validated by five-fold stratified cross-validation and was validated with a 30% holdout test dataset. Eighty-two thousand five hundred fifty-three prescribing data for prednisolone tablets containing 135 dose-corrected positive cases were obtained. In the original dataset (without SMOTE), only the BRF model showed a good performance (in test dataset, ROC-AUC:0.917, recall: 0.951). In the training dataset preprocessed by SMOTE, performance was improved on all models. The highest performance models with SMOTE were SVM (in test dataset, ROC-AUC: 0.820, recall: 0.659) and BRF (ROC-AUC: 0.814, recall: 0.634). Although the prescribing data for dose-related collection are highly imbalanced, various techniques such as the following have allowed us to build high-performance prediction models: data preprocessing by SMOTE, stratified cross-validation, and BRF classifier corresponding to imbalanced data. ML is useful in complicated dose audits such as oral prednisolone.

Supplementary Information

The online version contains supplementary material available at 10.1007/s41666-023-00128-3.

Integrating Structured and Unstructured EHR Data for Predicting Mortality by Machine Learning and Latent Dirichlet Allocation Method

An ICU is a critical care unit that provides advanced medical support and continuous monitoring for patients with severe illnesses or injuries. Predicting the mortality rate of ICU patients can not only improve patient outcomes, but also optimize resource allocation. Many studies have attempted to create scoring systems and models that predict the mortality of ICU patients using large amounts of structured clinical data. However, unstructured clinical data recorded during patient admission, such as notes made by physicians, is often overlooked. This study used the MIMIC-III database to predict mortality in ICU patients. In the first part of the study, only eight structured variables were used, including the six basic vital signs, the GCS, and the patient's age at admission. In the second part, unstructured predictor variables were extracted from the initial diagnosis made by physicians when the patients were admitted to the hospital and analyzed using Latent Dirichlet Allocation techniques. The structured and unstructured data were combined using machine learning methods to create a mortality risk prediction model for ICU patients. The results showed that combining structured and unstructured data improved the accuracy of the prediction of clinical outcomes in ICU patients over time. The model achieved an AUROC of 0.88, indicating accurate prediction of patient vital status. Additionally, the model was able to predict patient clinical outcomes over time, successfully identifying important variables. This study demonstrated that a small number of easily collectible structured variables, combined with unstructured data and analyzed using LDA topic modeling, can significantly improve the predictive performance of a mortality risk prediction model for ICU patients. These results suggest that initial clinical observations and diagnoses of ICU patients contain valuable information that can aid ICU medical and nursing staff in making important clinical decisions.

Identification of Distinct Clinical Phenotypes of Heterogeneous Mechanically Ventilated ICU Patients Using Cluster Analysis

This retrospective study aimed to derive the clinical phenotypes of ventilated ICU patients to predict the outcomes on the first day of ventilation. Clinical phenotypes were derived from the eICU Collaborative Research Database (eICU) cohort via cluster analysis and were validated in the Medical Information Mart for Intensive Care (MIMIC-IV) cohort. Four clinical phenotypes were identified and compared in the eICU cohort (n = 15,256). Phenotype A (n = 3112) was associated with respiratory disease, had the lowest 28-day mortality (16%), and had a high extubation success rate (~80%). Phenotype B (n = 3335) was correlated with cardiovascular disease, had the second-highest 28-day mortality (28%), and had the lowest extubation success rate (69%). Phenotype C (n = 3868) was correlated with renal dysfunction, had the highest 28-day mortality (28%), and had the second-lowest extubation success rate (74%). Phenotype D (n = 4941) was associated with neurological and traumatic diseases, had the second-lowest 28-day mortality (22%), and had the highest extubation success rate (>80%). These findings were validated in the validation cohort (n = 10,813). Additionally, these phenotypes responded differently to ventilation strategies in terms of duration of treatment, but had no difference in mortality. The four clinical phenotypes unveiled the heterogeneity of ICU patients and helped to predict the 28-day mortality and the extubation success rate.

Machine learning approaches for electronic health records phenotyping: a methodical review

OBJECTIVE

Accurate and rapid phenotyping is a prerequisite to leveraging electronic health records for biomedical research. While early phenotyping relied on rule-based algorithms curated by experts, machine learning (ML) approaches have emerged as an alternative to improve scalability across phenotypes and healthcare settings. This study evaluates ML-based phenotyping with respect to (1) the data sources used, (2) the phenotypes considered, (3) the methods applied, and (4) the reporting and evaluation methods used.

MATERIALS AND METHODS

We searched PubMed and Web of Science for articles published between 2018 and 2022. After screening 850 articles, we recorded 37 variables on 100 studies.

RESULTS

Most studies utilized data from a single institution and included information in clinical notes. Although chronic conditions were most commonly considered, ML also enabled the characterization of nuanced phenotypes such as social determinants of health. Supervised deep learning was the most popular ML paradigm, while semi-supervised and weakly supervised learning were applied to expedite algorithm development and unsupervised learning to facilitate phenotype discovery. ML approaches did not uniformly outperform rule-based algorithms, but deep learning offered a marginal improvement over traditional ML for many conditions.

DISCUSSION

Despite the progress in ML-based phenotyping, most articles focused on binary phenotypes and few articles evaluated external validity or used multi-institution data. Study settings were infrequently reported and analytic code was rarely released.

CONCLUSION

Continued research in ML-based phenotyping is warranted, with emphasis on characterizing nuanced phenotypes, establishing reporting and evaluation standards, and developing methods to accommodate misclassified phenotypes due to algorithm errors in downstream applications.

Timing and Spectrum of Antibiotic Treatment for Suspected Sepsis and Septic Shock: Why so Controversial?

Sepsis guidelines and mandates encourage increasingly aggressive time-to-antibiotic targets for broad-spectrum antimicrobials for suspected sepsis and septic shock. This has caused considerable controversy due to weaknesses in the underlying evidence and fear that overly strict antibiotic deadlines may harm patients by perpetuating or escalating overtreatment. Indeed, a third or more of patients currently treated for sepsis and septic shock have noninfectious or nonbacterial conditions. These patients risk all the potential harms of antibiotics without their possible benefits. Updated Surviving Sepsis Campaign guidelines now emphasize the importance of tailoring antibiotics to each patient's likelihood of infection, risk for drug-resistant pathogens, and severity-of-illness.

G-Sep: A Deep Learning Algorithm for Detection of Long-Term Sepsis Using Bidirectional Gated Recurrent Unit

Sepsis is a common and deadly condition that must be treated eloquently within 19 hours. Numerous deep learning techniques, including Recurrent Neural Networks, Convolution Neural Networks, Long Short-Term Memory, and Gated Recurrent Units, have been suggested for diagnosing long-term sepsis. Regardless, a sizable portion of them are computationally risky and have precision problems. The primary issue described is that output will degrade, and resource utilization will expand proportionately as the volume of dependencies grows. To overcome these issues, we propose a G-Sep technique utilizing Bidirectional Gated Recurrent Unit Algorithm, which consumes much less resource to detect the disease and in a short time with better accuracy than the existing methods to diagnose the sepsis. AI models could assist with distinguishing potential clinical factors and give better than existing conventional low-execution models. The proposed model is implemented utilizing Conda and Tensorflow Framework using the California Inpatient Severe Sepsis (CISS) Patient Dataset. The comparative simulation of the various existing models and the proposed G-Sep model is done using Conda and Tensor frameworks. The simulation results revealed that the proposed model had outperformed other frameworks in terms of mean average precision (mAP), receiver operating characteristic curve (ROC), and Area under the ROC Curve (AUROC) metrics linearly.

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.

A framework for employing longitudinally collected multicenter electronic health records to stratify heterogeneous patient populations on disease history

OBJECTIVE

To facilitate patient disease subset and risk factor identification by constructing a pipeline which is generalizable, provides easily interpretable results, and allows replication by overcoming electronic health records (EHRs) batch effects.

MATERIAL AND METHODS

We used 1872 billing codes in EHRs of 102 880 patients from 12 healthcare systems. Using tools borrowed from single-cell omics, we mitigated center-specific batch effects and performed clustering to identify patients with highly similar medical history patterns across the various centers. Our visualization method (PheSpec) depicts the phenotypic profile of clusters, applies a novel filtering of noninformative codes (Ranked Scope Pervasion), and indicates the most distinguishing features.

RESULTS

We observed 114 clinically meaningful profiles, for example, linking prostate hyperplasia with cancer and diabetes with cardiovascular problems and grouping pediatric developmental disorders. Our framework identified disease subsets, exemplified by 6 "other headache" clusters, where phenotypic profiles suggested different underlying mechanisms: migraine, convulsion, injury, eye problems, joint pain, and pituitary gland disorders. Phenotypic patterns replicated well, with high correlations of ≥0.75 to an average of 6 (2-8) of the 12 different cohorts, demonstrating the consistency with which our method discovers disease history profiles.

DISCUSSION

Costly clinical research ventures should be based on solid hypotheses. We repurpose methods from single-cell omics to build these hypotheses from observational EHR data, distilling useful information from complex data.

CONCLUSION

We establish a generalizable pipeline for the identification and replication of clinically meaningful (sub)phenotypes from widely available high-dimensional billing codes. This approach overcomes datatype problems and produces comprehensive visualizations of validation-ready phenotypes.

Machine Learning Model to Identify Sepsis Patients in the Emergency Department: Algorithm Development and Validation

Accurate stratification of sepsis can effectively guide the triage of patient care and shared decision making in the emergency department (ED). However, previous research on sepsis identification models focused mainly on ICU patients, and discrepancies in model performance between the development and external validation datasets are rarely evaluated. The aim of our study was to develop and externally validate a machine learning model to stratify sepsis patients in the ED. We retrospectively collected clinical data from two geographically separate institutes that provided a different level of care at different time periods. The Sepsis-3 criteria were used as the reference standard in both datasets for identifying true sepsis cases. An eXtreme Gradient Boosting (XGBoost) algorithm was developed to stratify sepsis patients and the performance of the model was compared with traditional clinical sepsis tools; quick Sequential Organ Failure Assessment (qSOFA) and Systemic Inflammatory Response Syndrome (SIRS). There were 8296 patients (1752 (21%) being septic) in the development and 1744 patients (506 (29%) being septic) in the external validation datasets. The mortality of septic patients in the development and validation datasets was 13.5% and 17%, respectively. In the internal validation, XGBoost achieved an area under the receiver operating characteristic curve (AUROC) of 0.86, exceeding SIRS (0.68) and qSOFA (0.56). The performance of XGBoost deteriorated in the external validation (the AUROC of XGBoost, SIRS and qSOFA was 0.75, 0.57 and 0.66, respectively). Heterogeneity in patient characteristics, such as sepsis prevalence, severity, age, comorbidity and infection focus, could reduce model performance. Our model showed good discriminative capabilities for the identification of sepsis patients and outperformed the existing sepsis identification tools. Implementation of the ML model in the ED can facilitate timely sepsis identification and treatment. However, dataset discrepancies should be carefully evaluated before implementing the ML approach in clinical practice. This finding reinforces the necessity for future studies to perform external validation to ensure the generalisability of any developed ML approaches.

Two-Stage Approaches to Accounting for Patient Heterogeneity in Machine Learning Risk Prediction Models in Oncology

PURPOSE

Machine learning models developed from electronic health records data have been increasingly used to predict risk of mortality for general oncology patients. But these models may have suboptimal performance because of patient heterogeneity. The objective of this work is to develop a new modeling approach to predicting short-term mortality that accounts for heterogeneity across multiple subgroups in the presence of a large number of electronic health record predictors.

METHODS

We proposed a two-stage approach to addressing heterogeneity among oncology patients of different cancer types for predicting their risk of mortality. Structured data were extracted from the University of Pennsylvania Health System for 20,723 patients of 11 cancer types, where 1,340 (6.5%) patients were deceased. We first modeled the overall risk for all patients without differentiating cancer types, as is done in the current practice. We then developed cancer type-specific models using the overall risk score as a predictor along with preselected type-specific predictors. The overall and type-specific models were compared with respect to discrimination using the area under the precision-recall curve (AUPRC) and calibration using the calibration slope. We also proposed metrics that characterize the degree of risk heterogeneity by comparing risk predictors in the overall and type-specific models.

RESULTS

The two-stage modeling resulted in improved calibration and discrimination across all 11 cancer types. The improvement in AUPRC was significant for hematologic malignancies including leukemia, lymphoma, and myeloma. For instance, the AUPRC increased from 0.358 to 0.519 (∆ = 0.161; 95% CI, 0.102 to 0.224) and from 0.299 to 0.354 (∆ = 0.055; 95% CI, 0.009 to 0.107) for leukemia and lymphoma, respectively. For all 11 cancer types, the two-stage approach generated well-calibrated risks. A high degree of heterogeneity between type-specific and overall risk predictors was observed for most cancer types.

CONCLUSION

Our two-stage modeling approach that accounts for cancer type-specific risk heterogeneity has improved calibration and discrimination than a model agnostic to cancer types.

Mass Spectrometry Proteotyping-Based Detection and Identification of Staphylococcus aureus, Escherichia coli, and Candida albicans in Blood

Bloodstream infections (BSIs), the presence of microorganisms in blood, are potentially serious conditions that can quickly develop into sepsis and life-threatening situations. When assessing proper treatment, rapid diagnosis is the key; besides clinical judgement performed by attending physicians, supporting microbiological tests typically are performed, often requiring microbial isolation and culturing steps, which increases the time required for confirming positive cases of BSI. The additional waiting time forces physicians to prescribe broad-spectrum antibiotics and empirically based treatments, before determining the precise cause of the disease. Thus, alternative and more rapid cultivation-independent methods are needed to improve clinical diagnostics, supporting prompt and accurate treatment and reducing the development of antibiotic resistance. In this study, a culture-independent workflow for pathogen detection and identification in blood samples was developed, using peptide biomarkers and applying bottom-up proteomics analyses, i.e., so-called "proteotyping". To demonstrate the feasibility of detection of blood infectious pathogens, using proteotyping, Escherichia coli and Staphylococcus aureus were included in the study, as the most prominent bacterial causes of bacteremia and sepsis, as well as Candida albicans, one of the most prominent causes of fungemia. Model systems including spiked negative blood samples, as well as positive blood cultures, without further culturing steps, were investigated. Furthermore, an experiment designed to determine the incubation time needed for correct identification of the infectious pathogens in blood cultures was performed. The results for the spiked negative blood samples showed that proteotyping was 100- to 1,000-fold more sensitive, in comparison with the MALDI-TOF MS-based approach. Furthermore, in the analyses of ten positive blood cultures each of E. coli and S. aureus, both the MALDI-TOF MS-based and proteotyping approaches were successful in the identification of E. coli, although only proteotyping could identify S. aureus correctly in all samples. Compared with the MALDI-TOF MS-based approaches, shotgun proteotyping demonstrated higher sensitivity and accuracy, and required significantly shorter incubation time before detection and identification of the correct pathogen could be accomplished.

Artificial Intelligence for Clinical Decision Support in Sepsis

Sepsis is one of the main causes of death in critically ill patients. Despite the continuous development of medical technology in recent years, its morbidity and mortality are still high. This is mainly related to the delay in starting treatment and non-adherence of clinical guidelines. Artificial intelligence (AI) is an evolving field in medicine, which has been used to develop a variety of innovative Clinical Decision Support Systems. It has shown great potential in predicting the clinical condition of patients and assisting in clinical decision-making. AI-derived algorithms can be applied to multiple stages of sepsis, such as early prediction, prognosis assessment, mortality prediction, and optimal management. This review describes the latest literature on AI for clinical decision support in sepsis, and outlines the application of AI in the prediction, diagnosis, subphenotyping, prognosis assessment, and clinical management of sepsis. In addition, we discussed the challenges of implementing and accepting this non-traditional methodology for clinical purposes.

Critical carE Database for Advanced Research (CEDAR): An automated method to support intensive care units with electronic health record data

Patients treated in an intensive care unit (ICU) are critically ill and require life-sustaining organ failure support. Existing critical care data resources are limited to a select number of institutions, contain only ICU data, and do not enable the study of local changes in care patterns. To address these limitations, we developed the Critical carE Database for Advanced Research (CEDAR), a method for automating extraction and transformation of data from an electronic health record (EHR) system. Compared to an existing gold standard of manually collected data at our institution, CEDAR was statistically similar in most measures, including patient demographics and sepsis-related organ failure assessment (SOFA) scores. Additionally, CEDAR automated data extraction obviated the need for manual collection of 550 variables. Critically, during the spring 2020 COVID-19 surge in New York City, a modified version of CEDAR supported pandemic response efforts, including clinical operations and research. Other academic medical centers may find value in using the CEDAR method to automate data extraction from EHR systems to support ICU activities.

Machine Learning Identifies Complicated Sepsis Course and Subsequent Mortality Based on 20 Genes in Peripheral Blood Immune Cells at 24 H Post-ICU Admission

A complicated clinical course for critically ill patients admitted to the intensive care unit (ICU) usually includes multiorgan dysfunction and subsequent death. Owing to the heterogeneity, complexity, and unpredictability of the disease progression, ICU patient care is challenging. Identifying the predictors of complicated courses and subsequent mortality at the early stages of the disease and recognizing the trajectory of the disease from the vast array of longitudinal quantitative clinical data is difficult. Therefore, we attempted to perform a meta-analysis of previously published gene expression datasets to identify novel early biomarkers and train the artificial intelligence systems to recognize the disease trajectories and subsequent clinical outcomes. Using the gene expression profile of peripheral blood cells obtained within 24 h of pediatric ICU (PICU) admission and numerous clinical data from 228 septic patients from pediatric ICU, we identified 20 differentially expressed genes predictive of complicated course outcomes and developed a new machine learning model. After 5-fold cross-validation with 10 iterations, the overall mean area under the curve reached 0.82. Using a subset of the same set of genes, we further achieved an overall area under the curve of 0.72, 0.96, 0.83, and 0.82, respectively, on four independent external validation sets. This model was highly effective in identifying the clinical trajectories of the patients and mortality. Artificial intelligence systems identified eight out of twenty novel genetic markers (SDC4, CLEC5A, TCN1, MS4A3, HCAR3, OLAH, PLCB1, and NLRP1) that help predict sepsis severity or mortality. While these genes have been previously associated with sepsis mortality, in this work, we show that these genes are also implicated in complex disease courses, even among survivors. The discovery of eight novel genetic biomarkers related to the overactive innate immune system, including neutrophil function, and a new predictive machine learning method provides options to effectively recognize sepsis trajectories, modify real-time treatment options, improve prognosis, and patient survival.

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.

Machine learning-based outcome prediction and novel hypotheses generation for substance use disorder treatment

OBJECTIVE

Substance use disorder is a critical public health issue. Discovering the synergies among factors impacting treatment program success can help governments and treatment facilities develop effective policies. In this work, we propose a novel data analytics approach using machine learning models to discover interaction effects that might be neglected by traditional hypothesis-generating approaches.

MATERIALS AND METHODS

A patient-episode-level substance use treatment discharge dataset and a Federal Bureau of Investigation crime dataset were joined using core-based statistical area codes. Random forests, artificial neural networks, and extreme gradient boosting were applied with a nested cross-validation methodology. Interaction effects were identified based on the machine learning model with the best performance. These interaction effects were analyzed and tested using traditional logistic regression models on unseen data.

RESULTS

In predicting patient completion of a treatment program, extreme gradient boosting performed the best with an area under the curve of 89.31%. Based on our procedure, 73 interaction effects were identified. Among these, 14 were tested using traditional logistic regression models where 12 were statistically significant (P<.05).

CONCLUSIONS

We identified new interaction effects among the length of stay, frequency of substance use, changes in self-help group attendance frequency, and other factors. This work provides insights into the interactions between factors impacting treatment completion. Further traditional statistical analysis can be employed by practitioners and policy makers to test the effects discovered by our novel machine learning approach.

Validation of a machine learning algorithm for early severe sepsis prediction: a retrospective study predicting severe sepsis up to 48 h in advance using a diverse dataset from 461 US hospitals

BACKGROUND

Severe sepsis and septic shock are among the leading causes of death in the United States and sepsis remains one of the most expensive conditions to diagnose and treat. Accurate early diagnosis and treatment can reduce the risk of adverse patient outcomes, but the efficacy of traditional rule-based screening methods is limited. The purpose of this study was to develop and validate a machine learning algorithm (MLA) for severe sepsis prediction up to 48 h before onset using a diverse patient dataset.

METHODS

Retrospective analysis was performed on datasets composed of de-identified electronic health records collected between 2001 and 2017, including 510,497 inpatient and emergency encounters from 461 health centers collected between 2001 and 2015, and 20,647 inpatient and emergency encounters collected in 2017 from a community hospital. MLA performance was compared to commonly used disease severity scoring systems and was evaluated at 0, 4, 6, 12, 24, and 48 h prior to severe sepsis onset.

RESULTS

270,438 patients were included in analysis. At time of onset, the MLA demonstrated an AUROC of 0.931 (95% CI 0.914, 0.948) and a diagnostic odds ratio (DOR) of 53.105 on a testing dataset, exceeding MEWS (0.725, P < .001; DOR 4.358), SOFA (0.716; P < .001; DOR 3.720), and SIRS (0.655; P < .001; DOR 3.290). For prediction 48 h prior to onset, the MLA achieved an AUROC of 0.827 (95% CI 0.806, 0.848) on a testing dataset. On an external validation dataset, the MLA achieved an AUROC of 0.948 (95% CI 0.942, 0.954) at the time of onset, and 0.752 at 48 h prior to onset.

CONCLUSIONS

The MLA accurately predicts severe sepsis onset up to 48 h in advance using only readily available vital signs extracted from the existing patient electronic health records. Relevant implications for clinical practice include improved patient outcomes from early severe sepsis detection and treatment.

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.