Development and external validation of a machine learning model for the prediction of persistent acute kidney injury stage 3 in multi-centric, multi-national intensive care cohorts.

BACKGROUND: The aim of this retrospective cohort study was to develop and validate on multiple international datasets a real-time machine learning model able to accurately predict persistent acute kidney injury (AKI) in the intensive care unit (ICU). METHODS: We selected adult patients admitted to ICU classified as AKI stage 2 or 3 as defined by the "Kidney Disease: Improving Global Outcomes" criteria. The primary endpoint was the ability to predict AKI stage 3 lasting for at least 72 h while in the ICU. An explainable tree regressor was trained and calibrated on two tertiary, urban, academic, single-center databases and externally validated on two multi-centers databases. RESULTS: A total of 7759 ICU patients were enrolled for analysis. The incidence of persistent stage 3 AKI varied from 11 to 6% in the development and internal validation cohorts, respectively and 19% in external validation cohorts. The model achieved area under the receiver operating characteristic curve of 0.94 (95% CI 0.92-0.95) in the US external validation cohort and 0.85 (95% CI 0.83-0.88) in the Italian external validation cohort. CONCLUSIONS: A machine learning approach fed with the proper data pipeline can accurately predict onset of Persistent AKI Stage 3 during ICU patient stay in retrospective, multi-centric and international datasets. This model has the potential to improve management of AKI episodes in ICU if implemented in clinical practice.

A scoping review of machine learning for sepsis prediction- feature engineering strategies and model performance: a step towards explainability.

BACKGROUND: Sepsis, an acute and potentially fatal systemic response to infection, significantly impacts global health by affecting millions annually. Prompt identification of sepsis is vital, as treatment delays lead to increased fatalities through progressive organ dysfunction. While recent studies have delved into leveraging Machine Learning (ML) for predicting sepsis, focusing on aspects such as prognosis, diagnosis, and clinical application, there remains a notable deficiency in the discourse regarding feature engineering. Specifically, the role of feature selection and extraction in enhancing model accuracy has been underexplored. OBJECTIVES: This scoping review aims to fulfill two primary objectives: To identify pivotal features for predicting sepsis across a variety of ML models, providing valuable insights for future model development, and To assess model efficacy through performance metrics including AUROC, sensitivity, and specificity. RESULTS: The analysis included 29 studies across diverse clinical settings such as Intensive Care Units (ICU), Emergency Departments, and others, encompassing 1,147,202 patients. The review highlighted the diversity in prediction strategies and timeframes. It was found that feature extraction techniques notably outperformed others in terms of sensitivity and AUROC values, thus indicating their critical role in improving sepsis prediction models. CONCLUSION: Key dynamic indicators, including vital signs and critical laboratory values, are instrumental in the early detection of sepsis. Applying feature selection methods significantly boosts model precision, with models like Random Forest and XG Boost showing promising results. Furthermore, Deep Learning models (DL) reveal unique insights, spotlighting the pivotal role of feature engineering in sepsis prediction, which could greatly benefit clinical practice.

Machine learning derived serum creatinine trajectories in acute kidney injury in critically ill patients with sepsis.

BACKGROUND: Current classification for acute kidney injury (AKI) in critically ill patients with sepsis relies only on its severity-measured by maximum creatinine which overlooks inherent complexities and longitudinal evaluation of this heterogenous syndrome. The role of classification of AKI based on early creatinine trajectories is unclear. METHODS: This retrospective study identified patients with Sepsis-3 who developed AKI within 48-h of intensive care unit admission using Medical Information Mart for Intensive Care-IV database. We used latent class mixed modelling to identify early creatinine trajectory-based classes of AKI in critically ill patients with sepsis. Our primary outcome was development of acute kidney disease (AKD). Secondary outcomes were composite of AKD or all-cause in-hospital mortality by day 7, and AKD or all-cause in-hospital mortality by hospital discharge. We used multivariable regression to assess impact of creatinine trajectory-based classification on outcomes, and eICU database for external validation. RESULTS: Among 4197 patients with AKI in critically ill patients with sepsis, we identified eight creatinine trajectory-based classes with distinct characteristics. Compared to the class with transient AKI, the class that showed severe AKI with mild improvement but persistence had highest adjusted risks for developing AKD (OR 5.16; 95% CI 2.87-9.24) and composite 7-day outcome (HR 4.51; 95% CI 2.69-7.56). The class that demonstrated late mild AKI with persistence and worsening had highest risks for developing composite hospital discharge outcome (HR 2.04; 95% CI 1.41-2.94). These associations were similar on external validation. CONCLUSIONS: These 8 classes of AKI in critically ill patients with sepsis, stratified by early creatinine trajectories, were good predictors for key outcomes in patients with AKI in critically ill patients with sepsis independent of their AKI staging.

Incorporating preoperative frailty to assist in early prediction of postoperative pneumonia in elderly patients with hip fractures: an externally validated online interpretable machine learning model.

BACKGROUND: This study aims to implement a validated prediction model and application medium for postoperative pneumonia (POP) in elderly patients with hip fractures in order to facilitate individualized intervention by clinicians. METHODS: Employing clinical data from elderly patients with hip fractures, we derived and externally validated machine learning models for predicting POP. Model derivation utilized a registry from Nanjing First Hospital, and external validation was performed using data from patients at the Fourth Affiliated Hospital of Nanjing Medical University. The derivation cohort was divided into the training set and the testing set. The least absolute shrinkage and selection operator (LASSO) and multivariable logistic regression were used for feature screening. We compared the performance of models to select the optimized model and introduced SHapley Additive exPlanations (SHAP) to interpret the model. RESULTS: The derivation and validation cohorts comprised 498 and 124 patients, with 14.3% and 10.5% POP rates, respectively. Among these models, Categorical boosting (Catboost) demonstrated superior discrimination ability. AUROC was 0.895 (95%CI: 0.841-0.949) and 0.835 (95%CI: 0.740-0.930) on the training and testing sets, respectively. At external validation, the AUROC amounted to 0.894 (95% CI: 0.821-0.966). The SHAP method showed that CRP, the modified five-item frailty index (mFI-5), and ASA body status were among the top three important predicators of POP. CONCLUSION: Our model's good early prediction ability, combined with the implementation of a network risk calculator based on the Catboost model, was anticipated to effectively distinguish high-risk POP groups, facilitating timely intervention.

Artificial intelligence/machine learning for epilepsy and seizure diagnosis.

Accurate seizure and epilepsy diagnosis remains a challenging task due to the complexity and variability of manifestations, which can lead to delayed or missed diagnosis. Machine learning (ML) and artificial intelligence (AI) is a rapidly developing field, with growing interest in integrating and applying these tools to aid clinicians facing diagnostic uncertainties. ML algorithms, particularly deep neural networks, are increasingly employed in interpreting electroencephalograms (EEG), neuroimaging, wearable data, and seizure videos. This review discusses the development and testing phases of AI/ML tools, emphasizing the importance of generalizability and interpretability in medical applications, and highlights recent publications that demonstrate the current and potential utility of AI to aid clinicians in diagnosing epilepsy. Current barriers of AI integration in patient care include dataset availability and heterogeneity, which limit studies' quality, interpretability, comparability, and generalizability. ML and AI offer substantial promise in improving the accuracy and efficiency of epilepsy diagnosis. The growing availability of diverse datasets, enhanced processing speed, and ongoing efforts to standardize reporting contribute to the evolving landscape of AI applications in clinical care.

Predictors of mechanical ventilation and mortality in critically ill patients with COVID-19 pneumonia / Predictores de ventilación mecánica y mortalidad en pacientes críticos con neumonía por COVID-19

Objective To determine if potential predictors for invasive mechanical ventilation (IMV) are also determinants for mortality in COVID-19-associated acute respiratory distress syndrome (C-ARDS). Design Single center highly detailed longitudinal observational study. Setting Tertiary hospital ICU: two first COVID-19 pandemic waves, Madrid, Spain. Patients or participants : 280 patients with C-ARDS, not requiring IMV on admission. Interventions None. Main variables of interest : Target: endotracheal intubation and IMV, mortality. Predictors: demographics, hourly evolution of oxygenation, clinical data, and laboratory results. Results The time between symptom onset and ICU admission, the APACHE II score, the ROX index, and procalcitonin levels in blood were potential predictors related to both IMV and mortality. The ROX index was the most significant predictor associated with IMV, while APACHE II, LDH, and DaysSympICU were the most with mortality. Conclusions According to the results of the analysis, there are significant predictors linked with IMV and mortality in C-ARDS patients, including the time between symptom onset and ICU admission, the severity of the COVID-19 waves, and several clinical and laboratory measures. These findings may help clinicians to better identify patients at risk for IMV and mortality and improve their management. (AU)

Objetivo Determinar si las variables clínicas independientes que condicionan el inicio de ventilación mecánica invasiva (VMI) son los mismos que condicionan la mortalidad en el síndrome de distrés respiratorio agudo asociado con COVID-19 (C-SDRA). Diseño Estudio observacional longitudinal en un solo centro. Ámbito UCI, hospital terciario: primeras dos olas de COVID-19 en Madrid, España. Pacientes o participantes 280 pacientes con C-SDRA que no requieren VMI al ingreso en UCI. Intervenciones Ninguna. Principales variables de interés Objetivo: VMI y Mortalidad. Predictores: demográficos, variables clínicas, resultados de laboratorio y evolución de la oxigenación. Resultados El tiempo entre el inicio de los síntomas y el ingreso en la UCI, la puntuación APACHE II, el índice ROX y los niveles de procalcitonina en sangre eran posibles predictores relacionados tanto con la IMV como con la mortalidad. El índice ROX fue el predictor más significativo asociada con la IMV, mientras que APACHE II, LDH y DaysSympICU fueron los más influyentes en la mortalidad. Conclusiones Según los resultados obtenidos se identifican predictores significativos vinculados con la VMI y mortalidad en pacientes con C-ARDS, incluido el tiempo entre el inicio de los síntomas y el ingreso en la UCI, la gravedad de las olas de COVID-19 y varias medidas clínicas y de laboratorio. Estos hallazgos pueden ayudar a los médicos a identificar mejor a los pacientes en riesgo de IMV y mortalidad y mejorar su manejo. (AU)

Revisión sistemática de la aplicación de algoritmos de «machine learning» en la esclerosis múltiple / A systematic review of the application of machine-learning algorithms in multiple sclerosis

Introducción: La aplicación de la inteligencia artificial y en particular de algoritmos de aprendizaje automático o «machine learning» (ML) constituye un desafío y al mismo tiempo una gran oportunidad en diversas disciplinas científicas, técnicas y clínicas. Las aplicaciones específicas en el estudio de la esclerosis múltiple (EM) no han sido una excepción mostrando un creciente interés en los últimos años. Objetivo: Realizar una revisión sistemática de la aplicación de algoritmos de ML en la EM. Material y métodos: Empleando el motor de búsqueda de libre acceso PubMed que accede a la base de datos MEDLINE, se seleccionaron aquellos estudios que incluyeran simultáneamente los dos siguientes conceptos de búsqueda: «machine learning» y «multiple sclerosis». Se rechazaron aquellos estudios que fueran revisiones, estuvieran en otro idioma que no fuera el castellano o el inglés, y aquellos trabajos que tuvieran un carácter técnico y no fueran aplicados para la EM. Se seleccionaron como válidos 76 artículos y fueron rechazados 38. Conclusiones: Tras la revisión de los estudios seleccionados, se pudo observar que la aplicación del ML en la EM se concentró en cuatro categorías: 1) clasificación de subtipos de pacientes dentro de la enfermedad; 2) diagnóstico del paciente frente a controles sanos u otras enfermedades; 3) predicción de la evolución o de la respuesta a intervenciones terapéuticas y por último 4) otros enfoques. Los resultados hallados hasta la fecha muestran que los diferentes algoritmos de ML pueden ser un gran apoyo para el profesional sanitario tanto en la clínica como en la investigación de la EM.(AU)

Introduction: The applications of artificial intelligence, and in particular automatic learning or “machine learning” (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years. Objective: We present a systematic review of the application of ML algorithms in MS. Materials and methods: We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords “machine learning” and “multiple sclerosis.” We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected. Conclusions: After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.(AU)

Inteligencia artificial en enfermedades infecciosas / Artificial intelligence in infectious diseases

Estamos asistiendo a una verdadera revolución tecnológi-ca en el campo de la salud. Los procesos basados en la aplicación de la inteligencia artificial (IA) y el aprendizaje automático (AA) están llegando progresivamente a todas las áreas disciplinares, y su aplicación en el campo de las enfermedades infecciosas es ya vertiginoso, acelerado por la pandemia de COVID-19.Hoy disponemos de herramientas que no solamente pue-den asistir o llevar adelante el proceso de toma de deci-siones basadas en guías o algoritmos, sino que también pueden modificar su desempeño a partir de los procesos previamente realizados. Desde la optimización en la identificación de microorganis-mos resistentes, la selección de candidatos a participar en ensayos clínicos, la búsqueda de nuevos agentes terapéu-ticos antimicrobianos, el desarrollo de nuevas vacunas, la predicción de futuras epidemias y pandemias, y el segui-miento clínico de pacientes con enfermedades infecciosas hasta la asignación de recursos en el curso de manejo de un brote son actividades que hoy ya pueden valerse de la inteligencia artificial para obtener un mejor resultado. El desarrollo de la IA tiene un potencial de aplicación expo-nencial y sin dudas será uno de los determinantes principa-les que moldearán la actividad médica del futuro cercano.Sin embargo, la maduración de esta tecnología, necesaria para su inserción definitiva en las actividades cotidianas del cuidado de la salud, requiere la definición de paráme-tros de referencia, sistemas de validación y lineamientos regulatorios que todavía no existen o son aún solo inci-pientes

We are in the midst of a true technological revolution in healthcare. Processes based upon artificial intelligence and machine learning are progressively touching all disciplinary areas, and its implementation in the field of infectious diseases is astonishing, accelerated by the COVID-19 pandemic. Today we have tools that can not only assist or carry on decision-making processes based upon guidelines or algorithms, but also modify its performance from the previously completed tasks. From optimization of the identification of resistant pathogens, selection of candidates for participating in clinical trials, the search of new antimicrobial therapeutic agents, the development of new vaccines, the prediction of future epidemics and pandemics, the clinical follow up of patients suffering infectious diseases up to the resource allocation in the management of an outbreak, are all current activities that can apply artificial intelligence in order to improve their final outcomes.This development has an exponential possibility of application, and is undoubtedly one of the main determinants that will shape medical activity in the future.Notwithstanding the maturation of this technology that is required for its definitive insertion in day-to-day healthcare activities, should be accompanied by definition of reference parameters, validation systems and regulatory guidelines that do not exist yet or are still in its initial stages

Aprendizaje automático para la toma de decisiones en cardiología: una revisión narrativa para ayudar a recorrer el nuevo panorama / Machine learning for decision-making in cardiology: a narrative review to aid navigating the new landscape

El aprendizaje automático (machine learning) en cardiología es cada vez más frecuente en la literatura médica, pero los modelos de aprendizaje automático aún no han producido un cambio generalizado de la práctica clínica. En parte esto se debe a que el lenguaje utilizado para describir el aprendizaje automático procede de la informática y resulta menos familiar a los lectores de revistas clínicas. En esta revisión narrativa se proporcionan, en primer lugar, algunas orientaciones sobre cómo leer las revistas de aprendizaje automático y, a continuación, orientaciones adicionales para quienes se plantean iniciar un estudio utilizando el aprendizaje automático. Por último, se ilustra el estado actual de la técnica con breves resúmenes de 5 artículos que van desde un modelo de aprendizaje automático muy sencillo hasta otros muy sofisticados.(AU)

Machine learning in cardiology is becoming more commonplace in the medical literature; however, machine learning models have yet to result in a widespread change in practice. This is partly due to the language used to describe machine, which is derived from computer science and may be unfamiliar to readers of clinical journals. In this narrative review, we provide some guidance on how to read machine learning journals and additional guidance for investigators considering instigating a study using machine learning. Finally, we illustrate the current state of the art with brief summaries of 5 articles describing models that range from the very simple to the highly sophisticated.(AU)