Multicenter validation of a machine-learning algorithm for 48-h all-cause mortality prediction.

In order to evaluate mortality predictions based on boosted trees, this retrospective study uses electronic medical record data from three academic health centers for inpatients 18 years or older with at least one observation of each vital sign. Predictions were made 12, 24, and 48 hours before death. Models fit to training data from each institution were evaluated using hold-out test data from the same institution, and from the other institutions. Gradient-boosted trees (GBT) were compared to regularized logistic regression (LR) predictions, support vector machine (SVM) predictions, quick Sepsis-Related Organ Failure Assessment (qSOFA), and Modified Early Warning Score (MEWS) using area under the receiver operating characteristic curve (AUROC). For training and testing GBT on data from the same institution, the average AUROCs were 0.96, 0.95, and 0.94 across institutional test sets for 12-, 24-, and 48-hour predictions, respectively. When trained and tested on data from different hospitals, GBT AUROCs achieved up to 0.98, 0.96, and 0.96, for 12-, 24-, and 48-hour predictions, respectively. Average AUROC for 48-hour predictions for LR, SVM, MEWS, and qSOFA were 0.85, 0.79, 0.86 and 0.82, respectively. GBT predictions may help identify patients who would benefit from increased clinical care.

Prediction of Acute Kidney Injury With a Machine Learning Algorithm Using Electronic Health Record Data.

BACKGROUND: A major problem in treating acute kidney injury (AKI) is that clinical criteria for recognition are markers of established kidney damage or impaired function; treatment before such damage manifests is desirable. Clinicians could intervene during what may be a crucial stage for preventing permanent kidney injury if patients with incipient AKI and those at high risk of developing AKI could be identified. OBJECTIVE: In this study, we evaluate a machine learning algorithm for early detection and prediction of AKI. DESIGN: We used a machine learning technique, boosted ensembles of decision trees, to train an AKI prediction tool on retrospective data taken from more than 300 000 inpatient encounters. SETTING: Data were collected from inpatient wards at Stanford Medical Center and intensive care unit patients at Beth Israel Deaconess Medical Center. PATIENTS: Patients older than the age of 18 whose hospital stays lasted between 5 and 1000 hours and who had at least one documented measurement of heart rate, respiratory rate, temperature, serum creatinine (SCr), and Glasgow Coma Scale (GCS). MEASUREMENTS: We tested the algorithm's ability to detect AKI at onset and to predict AKI 12, 24, 48, and 72 hours before onset. METHODS: We tested AKI detection and prediction using the National Health Service (NHS) England AKI Algorithm as a gold standard. We additionally tested the algorithm's ability to detect AKI as defined by the Kidney Disease: Improving Global Outcomes (KDIGO) guidelines. We compared the algorithm's 3-fold cross-validation performance to the Sequential Organ Failure Assessment (SOFA) score for AKI identification in terms of area under the receiver operating characteristic (AUROC). RESULTS: The algorithm demonstrated high AUROC for detecting and predicting NHS-defined AKI at all tested time points. The algorithm achieves AUROC of 0.872 (95% confidence interval [CI], 0.867-0.878) for AKI detection at time of onset. For prediction 12 hours before onset, the algorithm achieves an AUROC of 0.800 (95% CI, 0.792-0.809). For 24-hour predictions, the algorithm achieves AUROC of 0.795 (95% CI, 0.785-0.804). For 48-hour and 72-hour predictions, the algorithm achieves AUROC values of 0.761 (95% CI, 0.753-0.768) and 0.728 (95% CI, 0.719-0.737), respectively. LIMITATIONS: Because of the retrospective nature of this study, we cannot draw any conclusions about the impact the algorithm's predictions will have on patient outcomes in a clinical setting. CONCLUSIONS: The results of these experiments suggest that a machine learning-based AKI prediction tool may offer important prognostic capabilities for determining which patients are likely to suffer AKI, potentially allowing clinicians to intervene before kidney damage manifests.

CONTEXTE: Une des principales difficultés liées au traitement de l'insuffisance rénale aiguë (IRA) est le fait que les critères cliniques diagnostiques sont des marqueurs d'une lésion ou d'une dysfonction rénale déjà établie. Il est souhaitable d'intervenir avant une telle issue. En dépistant les patients à risque d'IRA ou atteints d'IRA débutante, les cliniciens seraient en mesure d'intervenir précocement et ainsi prévenir les lésions rénales permanentes. OBJECTIF DE L'ÉTUDE: L'étude visait à évaluer un algorithme d'apprentissage automatique destiné à la prédiction des cas d'IRA et à sa détection précoce. TYPE D'ÉTUDE: Nous avons employé une technique d'apprentissage automatique, soit des ensembles d'arbres décisionnels amplifiés, pour entrainer un outil de prédiction de l'IRA à partir de données rétrospectives provenant de plus de 300 000 consultations auprès de patients hospitalisés. CADRE DE L'ÉTUDE: Les données ont été colligées à partir des dossiers des unités d'hospitalisation du centre médical de l'université Stanford et de l'unité des soins intensifs du centre médical Beth Israel Deaconess. PARTICIPANTS: Ont été inclus dans l'étude tous les patients adultes dont l'hospitalisation avait duré de 5 à 1 000 heures et pour lesquels on disposait d'au moins une mesure parmi les suivantes : pouls, rythme respiratoire, température corporelle, taux de créatinine sérique (SCr) et score de Glasgow. MESURES: Nous avons testé l'efficacité de l'algorithme à détecter l'IRA dès son apparition, et à la prédire 12, 24, 48 et 72 heures avant qu'elle ne se manifeste. MÉTHODOLOGIE: L'algorithme du NHS England a servi de référence pour tester l'efficacité de notre algorithme de prédiction et de détection de l'IRA. Nous avons également testé l'efficacité de notre algorithme à détecter l'IRA telle que définie par les Recommandations de Bonnes Pratiques Cliniques du KDIGO (Kidney Disease: Improving Global Outcomes). Nous avons utilisé la surface sous la courbe ROC (Receiver Operating Characteristic) pour comparer le score SOFA à l'efficacité de validation croisée tripartite de notre algorithme. RÉSULTATS: L'algorithme a démontré une SSROC (surface sous la courbe ROC) élevée pour la détection et la prédiction de l'IRA (telle que définie par le NHS) pour tous les moments testés. En détection de la maladie à son apparition, l'algorithme a obtenu une SSROC de 0,872 (IC 95 % : 0,867-0,878). En prédiction, l'algorithme a obtenu une SSROC de 0,800 (IC 95 % : 0,792-0,809) à 12 heures, de 0,795 à 24 heures (IC 95 % : 0,785-0,804), de 0,761 (IC 95 % : 0,753-0,768) à 48 heures et de 0,728 (IC 95 % : 0,719-0,737) à 72 heures avant l'apparition des premiers symptômes. LIMITES DE L'ÉTUDE: La nature rétrospective de l'étude ne nous permet pas de tirer de conclusions sur les conséquences qu'auront les prédictions de l'algorithme sur les résultats cliniques des patients. CONCLUSION: Les résultats de nos essais laissent supposer qu'un outil de prédiction de l'IRA fondé sur l'apprentissage automatique pourrait offrir d'importantes fonctions pronostiques pour détecter les patients susceptibles de développer une IRA en vue d'une intervention précoce.

Using electronic health record collected clinical variables to predict medical intensive care unit mortality.

BACKGROUND: Clinical decision support systems are used to help predict patient stability and mortality in the Intensive Care Unit (ICU). Accurate patient information can assist clinicians with patient management and in allocating finite resources. However, systems currently in common use have limited predictive value in the clinical setting. The increasing availability of Electronic Health Records (EHR) provides an opportunity to use medical information for more accurate patient stability and mortality prediction in the ICU. OBJECTIVE: Develop and evaluate an algorithm which more accurately predicts patient mortality in the ICU, using the correlations between widely available clinical variables from the EHR. METHODS: We have developed an algorithm, AutoTriage, which uses eight common clinical variables from the EHR to assign patient mortality risk scores. Each clinical variable produces a subscore, and combinations of two or three discretized clinical variables also produce subscores. A combination of weighted subscores produces the overall score. We validated the performance of this algorithm in a retrospective study on the MIMIC III medical ICU dataset. RESULTS: AutoTriage 12 h mortality prediction yields an Area Under Receiver Operating Characteristic value of 0.88 (95% confidence interval 0.86 to 0.88). At a sensitivity of 80%, AutoTriage maintains a specificity of 81% with a diagnostic odds ratio of 16.26. CONCLUSIONS: Through the multidimensional analysis of the correlations between eight common clinical variables, AutoTriage provides an improvement in the specificity and sensitivity of patient mortality prediction over existing prediction methods.

High-performance detection and early prediction of septic shock for alcohol-use disorder patients.

BACKGROUND: The presence of Alcohol Use Disorder (AUD) complicates the medical conditions of patients and increases the difficulty of detecting and predicting the onset of septic shock for patients in the ICU. METHODS: We have developed a high-performance sepsis prediction algorithm, InSight, which outperforms existing methods for AUD patient populations. InSight analyses a combination of singlets, doublets, and triplets of clinical measurements over time to generate a septic shock risk score. AUD patients obtained from the MIMIC III database were used in this retrospective study to train InSight and compare performance with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score (SAPS II), and the Systemic Inflammatory Response Syndrome (SIRS) for septic shock prediction and detection. RESULTS: From 4-fold cross validation, InSight performs particularly well on diagnostic odds ratio and demonstrates a relatively high Area Under the Receiver Operating Characteristic (AUROC) metric. Four hours prior to onset, InSight had an average AUROC of 0.815, and at the time of onset, InSight had an average AUROC value of 0.965. When applied to patient populations where AUD may complicate prediction methods of sepsis, InSight outperforms existing diagnostic tools. CONCLUSIONS: Analysis of the higher order correlations and trends between relevant clinical measurements using the InSight algorithm leads to more accurate detection and prediction of septic shock, even in cases where diagnosis may be confounded by AUD.

Modular genetic regulatory networks increase organization during pattern formation.

Studies have shown that genetic regulatory networks (GRNs) consist of modules that are densely connected subnetworks that function quasi-autonomously. Modules may be recognized motifs that comprise of two or three genes with particular regulatory functions and connectivity or be purely structural and identified through connection density. It is unclear what evolutionary and developmental advantages modular structure and in particular motifs provide that have led to this enrichment. This study seeks to understand how modules within developmental GRNs influence the complexity of multicellular patterns that emerge from the dynamics of the regulatory networks. We apply an algorithmic complexity to measure the organization of the patterns. A computational study was performed by creating Boolean intracellular networks within a simulated epithelial field of embryonic cells, where each cell contains the same network and communicates with adjacent cells using contact-mediated signaling. Intracellular networks with random connectivity were compared to those with modular connectivity and with motifs. Results show that modularity effects network dynamics and pattern organization significantly. In particular: (1) modular connectivity alone increases complexity in network dynamics and patterns; (2) bistable switch motifs simplify both the pattern and network dynamics; (3) all other motifs with feedback loops increase multicellular pattern complexity while simplifying the network dynamics; (4) negative feedback loops affect the dynamics complexity more significantly than positive feedback loops.

A computational approach to mortality prediction of alcohol use disorder inpatients.

BACKGROUND: Health information technologies can assist clinicians in the Intensive Care Unit (ICU) by providing additional analysis of patient stability. However, because patient diagnoses can be confounded by chronic alcohol use, the predictive value of existing systems is suboptimal. Through the use of Electronic Health Records (EHR), we have developed computer software called AutoTriage to generate accurate predictions through multi-dimensional analysis of clinical variables. We analyze the performance of AutoTriage on the Alcohol Use Disorder (AUD) subpopulation in this study, and build on results we reported for AutoTriage performance on the general population in previous work. METHODS: AUD-related ICD-9 codes were used to obtain a patient population from MIMIC III ICU dataset for a retrospective study. Patient mortality risk score is generated through analysis of eight EHR-based clinical variables. The score is determined by combining weighted subscores, each of which are obtained from singlets, doublets or triplets of one or more of the eight continuous-valued clinical variable inputs. A temporally updating risk score is computed with a continuously revised 12-hour mortality prediction. RESULTS: Among AUD patients, in a non-overlapping test set, AutoTriage outperforms existing systems with an Area Under Receiver Operating Characteristic (AUROC) value of 0.934 for 12-h mortality prediction. At a sensitivity of 90%, AutoTriage achieves a specificity of 80%, positive predictive value of 40%, negative predictive value of 89%, and an Odds Ratio of 36. CONCLUSIONS: For mortality prediction, AutoTriage demonstrates improvements in both the accuracy and the Odds Ratio over current systems among the AUD patient population.

Maximizing Kolmogorov Complexity for accurate and robust bright field cell segmentation.

BACKGROUND: Analysis of cellular processes with microscopic bright field defocused imaging has the advantage of low phototoxicity and minimal sample preparation. However bright field images lack the contrast and nuclei reporting available with florescent approaches and therefore present a challenge to methods that segment and track the live cells. Moreover, such methods must be robust to systemic and random noise, variability in experimental configuration, and the multiple unknowns in the biological system under study. RESULTS: A new method called maximal-information is introduced that applies a non-parametric information theoretic approach to segment bright field defocused images. The method utilizes a combinatorial optimization strategy to select specific defocused images from each image stack such that set complexity, a Kolmogorov complexity measure, is maximized. Differences among these selected images are then applied to initialize and guide a level set based segmentation algorithm. The performance of the method is compared with a recent approach that uses a fixed defocused image selection strategy over an image data set of embryonic kidney cells (HEK 293T) from multiple experiments. Results demonstrate that the adaptive maximal-information approach significantly improves precision and recall of segmentation over the diversity of data sets. CONCLUSIONS: Integrating combinatorial optimization with non-parametric Kolmogorov complexity has been shown to be effective in extracting information from microscopic bright field defocused images. The approach is application independent and has the potential to be effective in processing a diversity of noisy and redundant high throughput biological data.

Kolmogorov complexity of epithelial pattern formation: the role of regulatory network configuration.

The tissues of multicellular organisms are made of differentiated cells arranged in organized patterns. This organization emerges during development from the coupling of dynamic intra- and intercellular regulatory networks. This work applies the methods of information theory to understand how regulatory network structure both within and between cells relates to the complexity of spatial patterns that emerge as a consequence of network operation. A computational study was performed in which undifferentiated cells were arranged in a two dimensional lattice, with gene expression in each cell regulated by identical intracellular randomly generated Boolean networks. Cell-cell contact signalling between embryonic cells is modeled as coupling among intracellular networks so that gene expression in one cell can influence the expression of genes in adjacent cells. In this system, the initially identical cells differentiate and form patterns of different cell types. The complexity of network structure, temporal dynamics and spatial organization is quantified through the Kolmogorov-based measures of normalized compression distance and set complexity. Results over sets of random networks that operate in the ordered, critical and chaotic domains demonstrate that: (1) ordered and critical networks tend to create the most information-rich patterns; (2) signalling configurations in which cell-to-cell communication is non-directional mostly produce simple patterns irrespective of the internal network domain; and (3) directional signalling configurations, similar to those that function in planar cell polarity, produce the most complex patterns, but only when the intracellular networks function in non-chaotic domains.