State of the art review: the data revolution in critical care

[Data-driven intensive care: a lack of comprehensive datasets]

Intensive care units provide a data-rich environment with the potential to generate datasets in the realm of big data, which could be utilized to train powerful machine learning (ML) models. However, the currently available datasets are too small and exhibit too little diversity due to their limitation to individual hospitals. This lack of extensive and varied datasets is a primary reason for the limited generalizability and resulting low clinical utility of current ML models. Often, these models are based on data from single centers and suffer from poor external validity. There is an urgent need for the development of large-scale, multicentric, and multinational datasets. Ensuring data protection and minimizing re-identification risks pose central challenges in this process. The "Amsterdam University Medical Center database (AmsterdamUMCdb)" and the "Salzburg Intensive Care database (SICdb)" demonstrate that open access datasets are possible in Europe while complying with the data protection regulations of the General Data Protection Regulation (GDPR). Another challenge in building intensive care datasets is the absence of semantic definitions in the source data and the heterogeneity of data formats. Establishing binding industry standards for the semantic definition is crucial to ensure seamless semantic interoperability between datasets.

Overview and Clinical Applications of Artificial Intelligence and Machine Learning in Cardiac Anesthesiology

Artificial intelligence- (AI) and machine learning (ML)-based applications are becoming increasingly pervasive in the healthcare setting. This has in turn challenged clinicians, hospital administrators, and health policymakers to understand such technologies and develop frameworks for safe and sustained clinical implementation. Within cardiac anesthesiology, challenges and opportunities for AI/ML to support patient care are presented by the vast amounts of electronic health data, which are collected rapidly, interpreted, and acted upon within the periprocedural area. To address such challenges and opportunities, in this article, the authors review 3 recent applications relevant to cardiac anesthesiology, including depth of anesthesia monitoring, operating room resource optimization, and transthoracic/transesophageal echocardiography, as conceptual examples to explore strengths and limitations of AI/ML within healthcare, and characterize this evolving landscape. Through reviewing such applications, the authors introduce basic AI/ML concepts and methodologies, as well as practical considerations and ethical concerns for initiating and maintaining safe clinical implementation of AI/ML-based algorithms for cardiac anesthesia patient care.

Comparing Open-Access Database and Traditional Intensive Care Studies Using Machine Learning: Bibliometric Analysis Study

BACKGROUND

Intensive care research has predominantly relied on conventional methods like randomized controlled trials. However, the increasing popularity of open-access, free databases in the past decade has opened new avenues for research, offering fresh insights. Leveraging machine learning (ML) techniques enables the analysis of trends in a vast number of studies.

OBJECTIVE

This study aims to conduct a comprehensive bibliometric analysis using ML to compare trends and research topics in traditional intensive care unit (ICU) studies and those done with open-access databases (OADs).

METHODS

We used ML for the analysis of publications in the Web of Science database in this study. Articles were categorized into "OAD" and "traditional intensive care" (TIC) studies. OAD studies were included in the Medical Information Mart for Intensive Care (MIMIC), eICU Collaborative Research Database (eICU-CRD), Amsterdam University Medical Centers Database (AmsterdamUMCdb), High Time Resolution ICU Dataset (HiRID), and Pediatric Intensive Care database. TIC studies included all other intensive care studies. Uniform manifold approximation and projection was used to visualize the corpus distribution. The BERTopic technique was used to generate 30 topic-unique identification numbers and to categorize topics into 22 topic families.

RESULTS

A total of 227,893 records were extracted. After exclusions, 145,426 articles were identified as TIC and 1301 articles as OAD studies. TIC studies experienced exponential growth over the last 2 decades, culminating in a peak of 16,378 articles in 2021, while OAD studies demonstrated a consistent upsurge since 2018. Sepsis, ventilation-related research, and pediatric intensive care were the most frequently discussed topics. TIC studies exhibited broader coverage than OAD studies, suggesting a more extensive research scope.

CONCLUSIONS

This study analyzed ICU research, providing valuable insights from a large number of publications. OAD studies complement TIC studies, focusing on predictive modeling, while TIC studies capture essential qualitative information. Integrating both approaches in a complementary manner is the future direction for ICU research. Additionally, natural language processing techniques offer a transformative alternative for literature review and bibliometric analysis.

Research on Multimodal Fusion of Temporal Electronic Medical Records

The surge in deep learning-driven EMR research has centered on harnessing diverse data forms. Yet, the amalgamation of diverse modalities within time series data remains an underexplored realm. This study probes a multimodal fusion approach, merging temporal and non-temporal clinical notes along with tabular data. We leveraged data from 1271 myocardial infarction and 6450 stroke inpatients at a Beijing tertiary hospital. Our dataset encompassed static, and time series note data, coupled with static and time series table data. The temporal data underwent a preprocessing phase, padding to a 30-day interval, and segmenting into 3-day sub-sequences. These were fed into a long short-term memory (LSTM) network for sub-sequence representation. Multimodal attention gates were implemented for both static and temporal subsequence representations, culminating in fused representations. An attention-backtracking module was introduced for the latter, adept at capturing enduring dependencies in temporal fused representations. The concatenated results were channeled into an LSTM to yield the ultimate fused representation. Initially, two note modalities were designated as primary modes, and subsequently, the proposed fusion model was compared with comparative models including recent models such as Crossformer. The proposed model consistently exhibited superior predictive prowess in both tasks. Removing the attention-backtracking module led to performance decline. The proposed model consistently shows excellent predictive capabilities in both tasks. The proposed method not only effectively integrates data from the four modalities, but also has a good understanding of how to handle irregular time series data and lengthy clinical texts. An effective method is provided, which is expected to be more widely used in multimodal medical data representation.

Advancing prognostic precision in pulmonary embolism: A clinical and laboratory-based artificial intelligence approach for enhanced early mortality risk stratification

BACKGROUND

Acute pulmonary embolism (PE) is a critical medical emergency that necessitates prompt identification and intervention. Accurate prognostication of early mortality is vital for recognizing patients at elevated risk for unfavourable outcomes and administering suitable therapy. Machine learning (ML) algorithms hold promise for enhancing the precision of early mortality prediction in PE patients.

OBJECTIVE

To devise an ML algorithm for early mortality prediction in PE patients by employing clinical and laboratory variables.

METHODS

This study utilized diverse oversampling techniques to improve the performance of various machine learning models including ANN, SVM, DT, RF, and AdaBoost for early mortality prediction. Appropriate oversampling methods were chosen for each model based on algorithm characteristics and dataset properties. Predictor variables included four lab tests, eight physiological time series indicators, and two general descriptors. Evaluation used metrics like accuracy, F1_score, precision, recall, Area Under the Curve (AUC) and Receiver Operating Characteristic (ROC) curves, providing a comprehensive view of models' predictive abilities.

RESULTS

The findings indicated that the RF model with random oversampling exhibited superior performance among the five models assessed, achieving elevated accuracy and precision alongside high recall for predicting the death class. The oversampling approaches effectively equalized the sample distribution among the classes and enhanced the models' performance.

CONCLUSIONS

The suggested ML technique can efficiently prognosticate mortality in patients afflicted with acute PE. The RF model with random oversampling can aid healthcare professionals in making well-informed decisions regarding the treatment of patients with acute PE. The study underscores the significance of oversampling methods in managing imbalanced data and emphasizes the potential of ML algorithms in refining early mortality prediction for PE patients.

Accounting for clustering in automated variable selection using hospital data: a comparison of different LASSO approaches

BACKGROUND

Automated feature selection methods such as the Least Absolute Shrinkage and Selection Operator (LASSO) have recently gained importance in the prediction of quality-related outcomes as well as the risk-adjustment of quality indicators in healthcare. The methods that have been used so far, however, do not account for the fact that patient data are typically nested within hospitals.

METHODS

Therefore, we aimed to demonstrate how to account for the multilevel structure of hospital data with LASSO and compare the results of this procedure with a LASSO variant that ignores the multilevel structure of the data. We used three different data sets (from acute myocardial infarcation, COPD, and stroke patients) with two dependent variables (one numeric and one binary), on which different LASSO variants with and without consideration of the nested data structure were applied. Using a 20-fold sub-sampling procedure, we tested the predictive performance of the different LASSO variants and examined differences in variable importance.

RESULTS

For the metric dependent variable Duration Stay, we found that inserting hospitals led to better predictions, whereas for the binary variable Mortality, all methods performed equally well. However, in some instances, the variable importances differed greatly between the methods.

CONCLUSION

We showed that it is possible to take the multilevel structure of data into account in automated predictor selection and that this leads, at least partly, to better predictive performance. From the perspective of variable importance, including the multilevel structure is crucial to select predictors in an unbiased way under consideration of the structural differences between hospitals.

Implementing Artificial Intelligence: Assessing the Cost and Benefits of Algorithmic Decision-Making in Critical Care

This article provides an overview of the most useful artificial intelligence algorithms developed in critical care, followed by a comprehensive outline of the benefits and limitations. We begin by describing how nurses and physicians might be aided by these new technologies. We then move to the possible changes in clinical guidelines with personalized medicine that will allow tailored therapies and probably will increase the quality of the care provided to patients. Finally, we describe how artificial intelligence models can unleash researchers' minds by proposing new strategies, by increasing the quality of clinical practice, and by questioning current knowledge and understanding.

Artificial Intelligence Models in Health Information Exchange: A Systematic Review of Clinical Implications

Electronic health record (EHR) systems collate patient data, and the integration and standardization of documents through Health Information Exchange (HIE) play a pivotal role in refining patient management. Although the clinical implications of AI in EHR systems have been extensively analyzed, its application in HIE as a crucial source of patient data is less explored. Addressing this gap, our systematic review delves into utilizing AI models in HIE, gauging their predictive prowess and potential limitations. Employing databases such as Scopus, CINAHL, Google Scholar, PubMed/Medline, and Web of Science and adhering to the PRISMA guidelines, we unearthed 1021 publications. Of these, 11 were shortlisted for the final analysis. A noticeable preference for machine learning models in prognosticating clinical results, notably in oncology and cardiac failures, was evident. The metrics displayed AUC values ranging between 61% and 99.91%. Sensitivity metrics spanned from 12% to 96.50%, specificity from 76.30% to 98.80%, positive predictive values varied from 83.70% to 94.10%, and negative predictive values between 94.10% and 99.10%. Despite variations in specific metrics, AI models drawing on HIE data unfailingly showcased commendable predictive proficiency in clinical verdicts, emphasizing the transformative potential of melding AI with HIE. However, variations in sensitivity highlight underlying challenges. As healthcare's path becomes more enmeshed with AI, a well-rounded, enlightened approach is pivotal to guarantee the delivery of trustworthy and effective AI-augmented healthcare solutions.

Discrepancy between perceptions and acceptance of clinical decision support Systems: implementation of artificial intelligence for vancomycin dosing

BACKGROUND

Artificial intelligence (AI) tools are more effective if accepted by clinicians. We developed an AI-based clinical decision support system (CDSS) to facilitate vancomycin dosing. This qualitative study assesses clinicians' perceptions regarding CDSS implementation.

METHODS

Thirteen semi-structured interviews were conducted with critical care pharmacists, at Mayo Clinic (Rochester, MN), from March through April 2020. Eight clinical cases were discussed with each pharmacist (N = 104). Following initial responses, we revealed the CDSS recommendations to assess participants' reactions and feedback. Interviews were audio-recorded, transcribed, and summarized.

RESULTS

The participants reported considerable time and effort invested daily in individualizing vancomycin therapy for hospitalized patients. Most pharmacists agreed that such a CDSS could favorably affect (N = 8, 62%) or enhance (9, 69%) their ability to make vancomycin dosing decisions. In case-based evaluations, pharmacists' empiric doses differed from the CDSS recommendation in most cases (88/104, 85%). Following revealing the CDSS recommendations, we noted 78% (69/88) discrepant doses. In discrepant cases, pharmacists indicated they would not alter their recommendations. The reasons for declining the CDSS recommendation were general distrust of CDSS, lack of dynamic evaluation and in-depth analysis, inability to integrate all clinical data, and lack of a risk index.

CONCLUSION

While pharmacists acknowledged enthusiasm about the advantages of AI-based models to improve drug dosing, they were reluctant to integrate the tool into clinical practice. Additional research is necessary to determine the optimal approach to implementing CDSS at the point of care acceptable to clinicians and effective at improving patient outcomes.

The truth Hertz-synchronization of electroencephalogram signals with physiological waveforms recorded in an intensive care unit

Objective.The ability to synchronize continuous electroencephalogram (cEEG) signals with physiological waveforms such as electrocardiogram (ECG), invasive pressures, photoplethysmography and other signals can provide meaningful insights regarding coupling between brain activity and other physiological subsystems. Aligning these datasets is a particularly challenging problem because device clocks handle time differently and synchronization protocols may be undocumented or proprietary.Approach.We used an ensemble-based model to detect the timestamps of heartbeat artefacts from ECG waveforms recorded from inpatient bedside monitors and from cEEG signals acquired using a different device. Vectors of inter-beat intervals were matched between both datasets and robust linear regression was applied to measure the relative time offset between the two datasets as a function of time.Main Results.The timing error between the two unsynchronized datasets ranged between -84 s and +33 s (mean 0.77 s, median 4.31 s, IQR25-4.79 s, IQR75 11.38s). Application of our method improved the relative alignment to within ± 5ms for more than 61% of the dataset. The mean clock drift between the two datasets was 418.3 parts per million (ppm) (median 414.6 ppm, IQR25 411.0 ppm, IQR75 425.6 ppm). A signal quality index was generated that described the quality of alignment for each cEEG study as a function of time.Significance.We developed and tested a method to retrospectively time-align two clinical waveform datasets acquired from different devices using a common signal. The method was applied to 33,911h of signals collected in a paediatric critical care unit over six years, demonstrating that the method can be applied to long-term recordings collected under clinical conditions. The method can account for unknown clock drift rates and the presence of discontinuities caused by clock resynchronization events.

Machine learning prediction models and nomogram to predict the risk of in-hospital death for severe DKA: A clinical study based on MIMIC-IV, eICU databases, and a college hospital ICU

AIM

To establish a prediction model and assess the risk factors for severe diabetic ketoacidosis (DKA) in adult patients during the ICU.

INTRODUCTION

With DKA hospitalization rates consistently increasing, in-hospital mortality has become a growing concern.

METHODS

DKA patients aged >18 years old in the US-based critical care database (Medical Information Mart for Intensive Care (MIMIC-IV)) were considered. Independent risk factors for in-hospital mortality were screened using extreme gradient boosting (XGBoost) and the Bayesian information criterion (BIC) optimal subset regression. One predictive model was developed using machine learning extreme gradient boosting (XGBoost), and the other one was a nomogram based on logistic regression to estimate risks of in-hospital mortality with severe DKA. Established models were assessed by using internal validation and external validation. The MIMIC-IV was split into training and testing samples in a 7:3 ratio. The eICU Collaborative Research Database and admissions data from the department of critical care medicine of the first affiliated hospital of Harbin medical university were used for independent validation. The discriminatory ability of the model was determined by illustrating a receiver operating curve (ROC) and calculating the C-index. Meanwhile, the calibration plot and Hosmer-Lemeshow goodness-of-fit test (HL test) was conducted to evaluate the performance of our new build model. Decision curve analysis (DCA) was performed to assess the clinical net benefit. Net Reclassification Improvement (NRI) was used to compare the predictive power of the two models.

RESULTS

A multivariable model that included acute physiology score III (APS III), the highest levels of blood plasma osmolality (osmolarity_max), minimum osmolarity (osmolarity_min)/osmolarity _max, vasopressor, and the highest levels of blood lactate was represented as the nomogram. The C- index of the nomogram model was 0.915 (95% CI: 0.966-0.864) in the training dataset and 0.971 (95% CI: 0.992-0.950) in the internal validation. The nomogram's sensitivity was well according to all data's HL test (P > 0.05). DCA showed that our model was clinically valuable. The XGB (extreme gradient boosting) model achieved an AUC (area under the curve) of 0.950 (95% CI, 0.920-0.980); however, the nomogram model made was more effective than XGB based on NRI.

CONCLUSION

The predictive XGB and nomogram models for predicting in-hospital patient deaths with DKA were effective. The forecast models can help clinical physicians promptly identify patients at high risk of DKA, prevent in-hospital deaths, and promptly intervene.

Structural causal model with expert augmented knowledge to estimate the effect of oxygen therapy on mortality in the ICU

Recent advances in causal inference techniques, more specifically, in the theory of structural causal models, provide the framework for identifying causal effects from observational data in cases where the causal graph is identifiable, i.e., the data generation mechanism can be recovered from the joint distribution. However, no such studies have been performed to demonstrate this concept with a clinical example. We present a complete framework to estimate the causal effects from observational data by augmenting expert knowledge in the model development phase and with a practical clinical application. Our clinical application entails a timely and essential research question, the effect of oxygen therapy intervention in the intensive care unit (ICU). The result of this project is helpful in a variety of disease conditions, including severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) patients in the ICU. We used data from the MIMIC-III database, a widely used health care database in the machine learning community with 58,976 admissions from an ICU in Boston, MA, to estimate the oxygen therapy effect on morality. We also identified the model's covariate-specific effect on oxygen therapy for more personalized intervention.

Computational Simulation of Virtual Patients Reduces Dataset Bias and Improves Machine Learning-Based Detection of ARDS from Noisy Heterogeneous ICU Datasets

Goal: Machine learning (ML) technologies that leverage large-scale patient data are promising tools predicting disease evolution in individual patients. However, the limited generalizability of ML models developed on single-center datasets, and their unproven performance in real-world settings, remain significant constraints to their widespread adoption in clinical practice. One approach to tackle this issue is to base learning on large multi-center datasets. However, such heterogeneous datasets can introduce further biases driven by data origin, as data structures and patient cohorts may differ between hospitals. Methods: In this paper, we demonstrate how mechanistic virtual patient (VP) modeling can be used to capture specific features of patients' states and dynamics, while reducing biases introduced by heterogeneous datasets. We show how VP modeling can be used for data augmentation through identification of individualized model parameters approximating disease states of patients with suspected acute respiratory distress syndrome (ARDS) from observational data of mixed origin. We compare the results of an unsupervised learning method (clustering) in two cases: where the learning is based on original patient data and on data derived in the matching procedure of the VP model to real patient data. Results: More robust cluster configurations were observed in clustering using the model-derived data. VP model-based clustering also reduced biases introduced by the inclusion of data from different hospitals and was able to discover an additional cluster with significant ARDS enrichment. Conclusions: Our results indicate that mechanistic VP modeling can be used to significantly reduce biases introduced by learning from heterogeneous datasets and to allow improved discovery of patient cohorts driven exclusively by medical conditions.

Development and validation of outcome prediction models for acute kidney injury patients undergoing continuous renal replacement therapy

Object

This study aimed to develop and validate a set of practical predictive tools that reliably estimate the 28-day prognosis of acute kidney injury patients undergoing continuous renal replacement therapy.

Methods

The clinical data of acute kidney injury patients undergoing continuous renal replacement therapy were extracted from the Medical Information Mart for Intensive Care IV database with structured query language and used as the development cohort. An all-subset regression was used for the model screening. Predictive models were constructed via a logistic regression, and external validation of the models was performed using independent external data.

Results

Clinical prediction models were developed with clinical data from 1,148 patients and validated with data from 121 patients. The predictive model based on seven predictors (age, vasopressor use, red cell volume distribution width, lactate, white blood cell count, platelet count, and phosphate) exhibited good predictive performance, as indicated by a C-index of 0.812 in the development cohort, 0.811 in the internal validation cohort and 0.768 in the external validation cohort.

Conclusions

The model reliably predicted the 28-day prognosis of acute kidney injury patients undergoing continuous renal replacement therapy. The predictive items are readily available, and the web-based prognostic calculator (https://libo220284.shinyapps.io/DynNomapp/) can be used as an adjunctive tool to support the management of patients.

Process Mining the Performance of a Real-Time Healthcare 4.0 Systems Using Conditional Survival Models

As the world moves into the exciting age of Healthcare 4.0, it is essential that patients and clinicians have confidence and reassurance that the real-time clinical decision support systems being used throughout their care guarantee robustness and optimal quality of care. However, current systems involving autonomic behaviour and those with no prior clinical feedback, have generally to date had little focus on demonstrating robustness in the use of data and final output, thus generating a lack of confidence. This paper wishes to address this challenge by introducing a new process mining approach based on a statistically robust methodology that relies on the utilisation of conditional survival models for the purpose of evaluating the performance of Healthcare 4.0 systems and the quality of the care provided. Its effectiveness is demonstrated by analysing the performance of a clinical decision support system operating in an intensive care setting with the goal to monitor ventilated patients in real-time and to notify clinicians if the patient is predicted at risk of receiving injurious mechanical ventilation. Additionally, we will also demonstrate how the same metrics can be used for evaluating the patient quality of care. The proposed methodology can be used to analyse the performance of any Healthcare 4.0 system and the quality of care provided to the patient.

Prioritization of healthcare systems during pandemics using Cronbach's measure based fuzzy WASPAS approach

Pandemics are well-known as epidemics that spread globally and cause many illnesses and mortality. Because of globalization, the accelerated occurrence and circulation of new microbes, the infection has emerged and the incidence and movement of new microbes have sped up. Using technological devices to minimize the visit durations, specifying days for handling chronic diseases, subsidy for the staff are the alternatives that can help prevent healthcare systems from collapsing during pandemics. The study aims to define the efficient usage of optimization tools during pandemics to prevent healthcare systems from collapsing. In this study, a new integrated framework with fuzzy information is developed, which attempts to prioritize these alternatives for policymakers. First, rating data are assigned respective fuzzy values using the standard singleton grades. Later, criteria weights are determined by extending Cronbach´s measure to fuzzy context. The measure not only understands data consistency comprehensively, but also takes into consideration the attitudinal characteristics of experts. By this approach, a rational weight vector is obtained for decision-making. Further, an improved Weighted Aggregated Sum Product Assessment (WASPAS) algorithm is put forward for ranking alternatives, which is flexibly considering criteria along with personalized ordering and holistic ordering alternatives. The usefulness of the developed framework is tested with the help of a real case study. Rank values of alternatives when unbiased weights are used is given by 0.741, 0.582, 0.640 with ordering asR 1 ≻ R 3 ≻ R 2 . The sensitivity/comparative analysis reveals the impact of the proposed model as useful in selecting the best alternative for the healthcare systems during pandemics.

The principles of whole-hospital predictive analytics monitoring for clinical medicine originated in the neonatal ICU

In 2011, a multicenter group spearheaded at the University of Virginia demonstrated reduced mortality from real-time continuous cardiorespiratory monitoring in the neonatal ICU using what we now call Artificial Intelligence, Big Data, and Machine Learning. The large, randomized heart rate characteristics trial made real, for the first time that we know of, the promise that early detection of illness would allow earlier and more effective intervention and improved patient outcomes. Currently, though, we hear as much of failures as we do of successes in the rapidly growing field of predictive analytics monitoring that has followed. This Perspective aims to describe the principles of how we developed heart rate characteristics monitoring for neonatal sepsis and then applied them throughout adult ICU and hospital medicine. It primarily reflects the work since the 1990s of the University of Virginia group: the theme is that sudden and catastrophic deteriorations can be preceded by subclinical but measurable physiological changes apparent in the continuous cardiorespiratory monitoring and electronic health record.

A High-Fidelity Model to Predict Length-of-Stay in the Neonatal Intensive Care Unit (NICU)

Having an interpretable dynamic length-of-stay (LOS) model can help hospital administrators and clinicians make better decisions and improve the quality of care. The widespread implementation of electronic medical record (EMR) systems has enabled hospitals to collect massive amounts of health data. However, how to integrate this deluge of data into healthcare operations remains unclear. We propose a framework grounded in established clinical knowledge to model patients' lengths-of-stay. In particular, we impose expert knowledge when grouping raw clinical data into medically meaningful variables, which summarize patients' health trajectories. We use dynamic predictive models to output patients' remaining lengths-of-stay (RLOS), future discharges, and census probability distributions based on their health trajectories up to the current stay. Evaluated with large-scale EMR data, the dynamic model significantly improves predictive power over the performance of any model in previous literature and remains medically interpretable.

Machine learning based early mortality prediction in the emergency department

BACKGROUND

It is a great challenge for emergency physicians to early detect the patient's deterioration and prevent unexpected death through a large amount of clinical data, which requires sufficient experience and keen insight.

OBJECTIVE

To evaluate the performance of machine learning models in quantifying the severity of emergency department (ED) patients and identifying high-risk patients.

METHODS

Using routinely-available demographics, vital signs and laboratory tests extracted from electronic health records (EHRs), a framework based on machine learning and feature engineering was proposed for mortality prediction. Patients who had one complete record of vital signs and laboratory tests in ED were included. The following patients were excluded: pediatric patients aged < 18 years, pregnant woman, and patients died or were discharged or hospitalized within 12 h after admission. Based on 76 original features extracted, 9 machine learning models were adopted to validate our proposed framework. Their optimal hyper-parameters were fine-tuned using the grid search method. The prediction results were evaluated on performance metrics (i.e., accuracy, area under the curve (AUC), recall and precision) with repeated 5-fold cross-validation (CV). The time window from patient admission to the prediction was analyzed at 12 h, 24 h, 48 h, and entire stay.

RESULTS

We studied a total of 1114 ED patients with 71.54% (797/1114) survival and 28.46% (317/1114) death in the hospital. The results revealed a more complete time window leads to better prediction performance. Using the entire stay records, the LightGBM model with refined feature engineering demonstrated high discrimination and achieved 93.6% (±0.008) accuracy, 97.6% (±0.003) AUC, 97.1% (±0.008) recall, and 94.2% (±0.006) precision, even if no diagnostic information was utilized.

CONCLUSIONS

This study quantifies the criticality of ED patients and appears to have significant potential as a clinical decision support tool in assisting physicians in their clinical routine. While the model requires validation before use elsewhere, the same methodology could be used to create a strong model for the new hospital.

A decision algorithm to promote outpatient antimicrobial stewardship for uncomplicated urinary tract infection

Antibiotic resistance is a major cause of treatment failure and leads to increased use of broad-spectrum agents, which begets further resistance. This vicious cycle is epitomized by uncomplicated urinary tract infection (UTI), which affects one in two women during their life and is associated with increasing antibiotic resistance and high rates of prescription for broad-spectrum second-line agents. To address this, we developed machine learning models to predict antibiotic susceptibility using electronic health record data and built a decision algorithm for recommending the narrowest possible antibiotic to which a specimen is susceptible. When applied to a test cohort of 3629 patients presenting between 2014 and 2016, the algorithm achieved a 67% reduction in the use of second-line antibiotics relative to clinicians. At the same time, it reduced inappropriate antibiotic therapy, defined as the choice of a treatment to which a specimen is resistant, by 18% relative to clinicians. For specimens where clinicians chose a second-line drug but the algorithm chose a first-line drug, 92% (1066 of 1157) of decisions ended up being susceptible to the first-line drug. When clinicians chose an inappropriate first-line drug, the algorithm chose an appropriate first-line drug 47% (183 of 392) of the time. Our machine learning decision algorithm provides antibiotic stewardship for a common infectious syndrome by maximizing reductions in broad-spectrum antibiotic use while maintaining optimal treatment outcomes. Further work is necessary to improve generalizability by training models in more diverse populations.

Outcomes prediction in longitudinal data: Study designs evaluation, use case in ICU acquired sepsis

Outcomes' prediction in Electronic Health Records (EHR) and specifically in Critical Care is increasingly attracting more exploration and research. In this study, we used clinical data from the Intensive Care Unit (ICU), focusing on ICU acquired sepsis. Looking at the current literature, several evaluation approaches are reported, inspired by epidemiological designs, in which some do not always reflect real-life application's conditions. This problem seems relevant generally to outcomes' prediction in longitudinal EHR data, or generally longitudinal data, while in this study we focused on ICU data. Unlike in most previous studies that investigated all sepsis admissions, we focused specifically on ICU-Acquired Sepsis. Due to the sparse nature of the longitudinal data, we employed the use of Temporal Abstraction and Time Interval-Related Patterns discovery, which are further used as classification features. Two experiments were designed using three different outcomes prediction study designs from the literature, implementing various levels of real-life conditions to evaluate the prediction models. The first experiment focused on predicting whether a patient would suffer from ICU-acquired sepsis and when during her admission, given a sliding observation time window, and the comparison of the three study designs behavior. The second experiment focused only on predicting whether the patient will suffer from ICU-acquired sepsis, based on data taken relatively to his admission start time. Our results show that using Temporal Discretization for Classification (TD4C) led to better performance than using the Equal-Width Discretization, Knowledge-Based, or SAX. Also, using two states abstraction was better than three or four. Using the default Binary TIRP representation method performed better than Mean Duration, Horizontal Support, and horizontally normalized horizontal support. Using XGBoost as a classifier performed better than Logistic Regression, Neural Net, or Random Forest. Additionally, it is demonstrated why the use of case-crossover-control is most appropriate for real life application conditions evaluation, unlike other incomplete designs that may even result in "better performance".

Precision health data: Requirements, challenges and existing techniques for data security and privacy

Precision health leverages information from various sources, including omics, lifestyle, environment, social media, medical records, and medical insurance claims to enable personalized care, prevent and predict illness, and precise treatments. It extensively uses sensing technologies (e.g., electronic health monitoring devices), computations (e.g., machine learning), and communication (e.g., interaction between the health data centers). As health data contain sensitive private information, including the identity of patient and carer and medical conditions of the patient, proper care is required at all times. Leakage of these private information affects the personal life, including bullying, high insurance premium, and loss of job due to the medical history. Thus, the security, privacy of and trust on the information are of utmost importance. Moreover, government legislation and ethics committees demand the security and privacy of healthcare data. Besides, the public, who is the data source, always expects the security, privacy, and trust of their data. Otherwise, they can avoid contributing their data to the precision health system. Consequently, as the public is the targeted beneficiary of the system, the effectiveness of precision health diminishes. Herein, in the light of precision health data security, privacy, ethical and regulatory requirements, finding the best methods and techniques for the utilization of the health data, and thus precision health is essential. In this regard, firstly, this paper explores the regulations, ethical guidelines around the world, and domain-specific needs. Then it presents the requirements and investigates the associated challenges. Secondly, this paper investigates secure and privacy-preserving machine learning methods suitable for the computation of precision health data along with their usage in relevant health projects. Finally, it illustrates the best available techniques for precision health data security and privacy with a conceptual system model that enables compliance, ethics clearance, consent management, medical innovations, and developments in the health domain.

Sampling methods and feature selection for mortality prediction with neural networks

Along with digitization, automatic data-driven decision support systems become increasingly popular. Mortality prediction is a vital part of that decision process. With more data available, sophisticated machine learning models like (Artificial) Neural Networks (NNs) can be applied and promise favorable performance. We evaluate the reproducibility of a published mortality prediction approach using NNs along with the possibility to generalize it to a bigger and more generic dataset. We describe an extensive preprocessing pipeline, as well as the evaluation of different sampling techniques and NN architectures. Through training on a loss function that optimizes both, precision and recall, in combination with a good set of hyperparameters and a set of new features, we use a NN to predict in-hospital mortality with accuracy, sensitivity, and area under the receiver operating characteristic score of greater than 0.8.

Data-driven ICU management: Using Big Data and algorithms to improve outcomes

The digitalization of the Intensive Care Unit (ICU) led to an increasing amount of clinical data being collected at the bedside. The term "Big Data" can be used to refer to the analysis of these datasets that collect enormous amount of data of different origin and format. Complexity and variety define the value of Big Data. In fact, the retrospective analysis of these datasets allows to generate new knowledge, with consequent potential improvements in the clinical practice. Despite the promising start of Big Data analysis in medical research, which has seen a rising number of peer-reviewed articles, very limited applications have been used in ICU clinical practice. A close future effort should be done to validate the knowledge extracted from clinical Big Data and implement it in the clinic. In this article, we provide an introduction to Big Data in the ICU, from data collection and data analysis, to the main successful examples of prognostic, predictive and classification models based on ICU data. In addition, we focus on the main challenges that these models face to reach the bedside and effectively improve ICU care.

Decompensation in Critical Care: Early Prediction of Acute Heart Failure Onset

BACKGROUND

Heart failure is a leading cause of mortality and morbidity worldwide. Acute heart failure, broadly defined as rapid onset of new or worsening signs and symptoms of heart failure, often requires hospitalization and admission to the intensive care unit (ICU). This acute condition is highly heterogeneous and less well-understood as compared to chronic heart failure. The ICU, through detailed and continuously monitored patient data, provides an opportunity to retrospectively analyze decompensation and heart failure to evaluate physiological states and patient outcomes.

OBJECTIVE

The goal of this study is to examine the prevalence of cardiovascular risk factors among those admitted to ICUs and to evaluate combinations of clinical features that are predictive of decompensation events, such as the onset of acute heart failure, using machine learning techniques. To accomplish this objective, we leveraged tele-ICU data from over 200 hospitals across the United States.

METHODS

We evaluated the feasibility of predicting decompensation soon after ICU admission for 26,534 patients admitted without a history of heart failure with specific heart failure risk factors (ie, coronary artery disease, hypertension, and myocardial infarction) and 96,350 patients admitted without risk factors using remotely monitored laboratory, vital signs, and discrete physiological measurements. Multivariate logistic regression and random forest models were applied to predict decompensation and highlight important features from combinations of model inputs from dissimilar data.

RESULTS

The most prevalent risk factor in our data set was hypertension, although most patients diagnosed with heart failure were admitted to the ICU without a risk factor. The highest heart failure prediction accuracy was 0.951, and the highest area under the receiver operating characteristic curve was 0.9503 with random forest and combined vital signs, laboratory values, and discrete physiological measurements. Random forest feature importance also highlighted combinations of several discrete physiological features and laboratory measures as most indicative of decompensation. Timeline analysis of aggregate vital signs revealed a point of diminishing returns where additional vital signs data did not continue to improve results.

CONCLUSIONS

Heart failure risk factors are common in tele-ICU data, although most patients that are diagnosed with heart failure later in an ICU stay presented without risk factors making a prediction of decompensation critical. Decompensation was predicted with reasonable accuracy using tele-ICU data, and optimal data extraction for time series vital signs data was identified near a 200-minute window size. Overall, results suggest combinations of laboratory measurements and vital signs are viable for early and continuous prediction of patient decompensation.

Sparse multi-output Gaussian processes for online medical time series prediction

BACKGROUND

For real-time monitoring of hospital patients, high-quality inference of patients' health status using all information available from clinical covariates and lab test results is essential to enable successful medical interventions and improve patient outcomes. Developing a computational framework that can learn from observational large-scale electronic health records (EHRs) and make accurate real-time predictions is a critical step. In this work, we develop and explore a Bayesian nonparametric model based on multi-output Gaussian process (GP) regression for hospital patient monitoring.

METHODS

We propose MedGP, a statistical framework that incorporates 24 clinical covariates and supports a rich reference data set from which relationships between observed covariates may be inferred and exploited for high-quality inference of patient state over time. To do this, we develop a highly structured sparse GP kernel to enable tractable computation over tens of thousands of time points while estimating correlations among clinical covariates, patients, and periodicity in patient observations. MedGP has a number of benefits over current methods, including (i) not requiring an alignment of the time series data, (ii) quantifying confidence regions in the predictions, (iii) exploiting a vast and rich database of patients, and (iv) inferring interpretable relationships among clinical covariates.

RESULTS

We evaluate and compare results from MedGP on the task of online prediction for three patient subgroups from two medical data sets across 8,043 patients. We find MedGP improves online prediction over baseline and state-of-the-art methods for nearly all covariates across different disease subgroups and hospitals.

CONCLUSIONS

The MedGP framework is robust and efficient in estimating the temporal dependencies from sparse and irregularly sampled medical time series data for online prediction. The publicly available code is at https://github.com/bee-hive/MedGP .

Artificial Intelligence in Anesthesiology: Current Techniques, Clinical Applications, and Limitations

Artificial intelligence has been advancing in fields including anesthesiology. This scoping review of the intersection of artificial intelligence and anesthesia research identified and summarized six themes of applications of artificial intelligence in anesthesiology: (1) depth of anesthesia monitoring, (2) control of anesthesia, (3) event and risk prediction, (4) ultrasound guidance, (5) pain management, and (6) operating room logistics. Based on papers identified in the review, several topics within artificial intelligence were described and summarized: (1) machine learning (including supervised, unsupervised, and reinforcement learning), (2) techniques in artificial intelligence (e.g., classical machine learning, neural networks and deep learning, Bayesian methods), and (3) major applied fields in artificial intelligence.The implications of artificial intelligence for the practicing anesthesiologist are discussed as are its limitations and the role of clinicians in further developing artificial intelligence for use in clinical care. Artificial intelligence has the potential to impact the practice of anesthesiology in aspects ranging from perioperative support to critical care delivery to outpatient pain management.

Linking Big Data and Prediction Strategies: Tools, Pitfalls, and Lessons Learned

OBJECTIVES

Modern critical care amasses unprecedented amounts of clinical data-so called "big data"-on a minute-by-minute basis. Innovative processing of these data has the potential to revolutionize clinical prognostics and decision support in the care of the critically ill but also forces clinicians to depend on new and complex tools of which they may have limited understanding and over which they have little control. This concise review aims to provide bedside clinicians with ways to think about common methods being used to extract information from clinical big datasets and to judge the quality and utility of that information.

DATA SOURCES

We searched the free-access search engines PubMed and Google Scholar using the MeSH terms "big data", "prediction", and "intensive care" with iterations of a range of additional potentially associated factors, along with published bibliographies, to find papers suggesting illustration of key points in the structuring and analysis of clinical "big data," with special focus on outcomes prediction and major clinical concerns in critical care.

STUDY SELECTION

Three reviewers independently screened preliminary citation lists.

DATA EXTRACTION

Summary data were tabulated for review.

DATA SYNTHESIS

To date, most relevant big data research has focused on development of and attempts to validate patient outcome scoring systems and has yet to fully make use of the potential for automation and novel uses of continuous data streams such as those available from clinical care monitoring devices.

CONCLUSIONS

Realizing the potential for big data to improve critical care patient outcomes will require unprecedented team building across disparate competencies. It will also require clinicians to develop statistical awareness and thinking as yet another critical judgment skill they bring to their patients' bedsides and to the array of evidence presented to them about their patients over the course of care.

Utilized or Underutilized: A Qualitative Analysis of Building Coherence During Early Implementation of a Tele-Intensive Care Unit

Background: Generating, reading, or interpreting data is a component of Telemedicine-Intensive Care Unit (Tele-ICU) utilization that has not been explored in the literature. Introduction: Using the idea of "coherence," a construct of Normalization Process Theory, we describe how intensive care unit (ICU) and Tele-ICU staff made sense of their shared work and how they made use of Tele-ICU together. Materials and Methods: We interviewed ICU and Tele-ICU staff involved in the implementation of Tele-ICU during site visits to a Tele-ICU hub and 3 ICUs, at preimplementation (43 interviews with 65 participants) and 6 months postimplementation (44 interviews with 67 participants). Data were analyzed using deductive coding techniques and lexical searches. Results: In the early implementation of Tele-ICU, ICU and Tele-ICU staff lacked consensus about how to share information and consequently how to make use of innovations in data tracking and interpretation offered by the Tele-ICU (e.g., acuity systems). Attempts to collaborate and create opportunities for utilization were supported by quality improvement (QI) initiatives. Discussion: Characterizing Tele-ICU utilization as an element of a QI process limited how ICU staff understood Tele-ICU as an innovation. It also did not promote an understanding of how the Tele-ICU used data and may therefore attenuate the larger promise of Tele-ICU as a potential tool for leveraging big data in critical care. Conclusions: Shared data practices lay the foundation for Tele-ICU program utilization but raise new questions about how the promise of big data can be operationalized for bedside ICU staff.

Development of data dictionary for neonatal intensive care unit: advancement towards a better critical care unit

Background

Critical care units (CCUs) with extensive use of various monitoring devices generate massive data. To utilize the valuable information of these devices; data are collected and stored using systems like clinical information system and laboratory information management system. These systems are proprietary, allow limited access to their database and, have the vendor-specific clinical implementation. In this study, we focus on developing an open-source web-based meta-data repository for CCU representing stay of the patient with relevant details.

Methods

After developing the web-based open-source repository named data dictionary (DD), we analyzed prospective data from 2 sites for 4 months for data quality dimensions (completeness, timeliness, validity, accuracy, and consistency), morbidity, and clinical outcomes. We used a regression model to highlight the significance of practice variations linked with various quality indicators.

Results

DD with 1555 fields (89.6% categorical and 11.4% text fields) is presented to cover the clinical workflow of a CCU. The overall quality of 1795 patient days data with respect to standard quality dimensions is 87%. The data exhibit 88% completeness, 97% accuracy, 91% timeliness, and 94% validity in terms of representing CCU processes. The data scores only 67% in terms of consistency. Furthermore, quality indicators and practice variations are strongly correlated (P < 0.05).

Conclusion

This study documents DD for standardized data collection in CCU. DD provides robust data and insights for audit purposes and pathways for CCU to target practice improvements leading to specific quality improvements.

Incorporating repeated measurements into prediction models in the critical care setting: a framework, systematic review and meta-analysis

BACKGROUND

The incorporation of repeated measurements into multivariable prediction research may greatly enhance predictive performance. However, the methodological possibilities vary widely and a structured overview of the possible and utilized approaches lacks. Therefore, we [1] propose a structured framework for these approaches, [2] determine what methods are currently used to incorporate repeated measurements in prediction research in the critical care setting and, where possible, [3] assess the added discriminative value of incorporating repeated measurements.

METHODS

The proposed framework consists of three domains: the observation window (static or dynamic), the processing of the raw data (raw data modelling, feature extraction and reduction) and the type of modelling. A systematic review was performed to identify studies which incorporate repeated measurements to predict (e.g. mortality) in the critical care setting. The within-study difference in c-statistics between models with versus without repeated measurements were obtained and pooled in a meta-analysis.

RESULTS

From the 2618 studies found, 29 studies incorporated multiple repeated measurements. The annual number of studies with repeated measurements increased from 2.8/year (2000-2005) to 16.0/year (2016-2018). The majority of studies that incorporated repeated measurements for prediction research used a dynamic observation window, and extracted features directly from the data. Differences in c statistics ranged from - 0.048 to 0.217 in favour of models that utilize repeated measurements.

CONCLUSIONS

Repeated measurements are increasingly common to predict events in the critical care domain, but their incorporation is lagging. A framework of possible approaches could aid researchers to optimize future prediction models.

[Construction of multi-parameter emergency database and preliminary application research]

The analysis of big data in medical field cannot be isolated from the high quality clinical database, and the construction of first aid database in our country is still in the early stage of exploration. This paper introduces the idea and key technology of the construction of multi-parameter first aid database. By combining emergency business flow with information flow, an emergency data integration model was designed with reference to the architecture of the Medical Information Mart for Intensive Care III (MIMIC-III), created by Computational Physiology Laboratory of Massachusetts Institute of Technology (MIT), and a high-quality first-aid database was built. The database currently covers 22 941 medical records for 19 814 different patients from May 2015 to October 2017, including relatively complete information on physiology, biochemistry, treatment, examination, nursing, etc. And based on the database, the first First-Aid Big Data Datathon event, which 13 teams from all over the country participated in, was launched. The First-Aid database provides a reference for the construction and application of clinical database in China. And it could provide powerful data support for scientific research, clinical decision making and the improvement of medical quality, which will further promote secondary analysis of clinical data in our country.

Temporal Variability in the Sampling of Vital Sign Data Limits the Accuracy of Patient State Estimation

OBJECTIVES

Physiologic signals are typically measured continuously in the critical care unit, but only recorded at intermittent time intervals in the patient health record. Low frequency data collection may not accurately reflect the variability and complexity of these signals or the patient's clinical state. We aimed to characterize how increasing the temporal window size of observation from seconds to hours modifies the measured variability and complexity of basic vital signs.

DESIGN

Retrospective analysis of signal data acquired between April 1, 2013, and September 30, 2015.

SETTING

Critical care unit at The Hospital for Sick Children, Toronto.

PATIENTS

Seven hundred forty-seven patients less than or equal to 18 years old (63,814,869 data values), within seven diagnostic/surgical groups.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Measures of variability (SD and the absolute differences) and signal complexity (multiscale sample entropy and detrended fluctuation analysis [expressed as the scaling component α]) were calculated for systolic blood pressure, heart rate, and oxygen saturation. The variability of all vital signs increases as the window size increases from seconds to hours at the patient and diagnostic/surgical group level. Significant differences in the magnitude of variability for all time scales within and between groups was demonstrated (p < 0.0001). Variability correlated negatively with patient age for heart rate and oxygen saturation, but positively with systolic blood pressure. Changes in variability and complexity of heart rate and systolic blood pressure from time of admission to discharge were found.

CONCLUSIONS

In critically ill children, the temporal variability of physiologic signals supports higher frequency data capture, and this variability should be accounted for in models of patient state estimation.

Artificial Intelligence: Applications in orthognathic surgery

Artificial Intelligence (AI) applications have already invaded our everyday life, and the last 10 years have seen the emergence of very promising applications in the field of medicine. However, the literature dealing with the potential applications of IA in Orthognathic Surgery is remarkably poor to date. Yet, it is very likely that due to its amazing power in image recognition AI will find tremendous applications in dento-facial deformities recognition in a near future. In this article, we point out the state-of-the-art AI applications in medicine and its potential applications in the field of orthognathic surgery. AI is a very powerful tool and it is the responsibility of the entire medical profession to achieve a positive symbiosis between clinical sense and AI.

Physiology and technology for the ICU in vivo

This paper discusses the physiological and technological concepts that might form the future of critical care medicine. Initially, we discuss the need for a personalized approach and introduce the concept of personalized physiological medicine (PPM), including (1) assessment of frailty and physiological reserve, (2) continuous assessment of organ function, (3) assessment of the microcirculation and parenchymal cells, and (4) integration of organ and cell function for continuous therapeutic feedback control. To understand the cellular basis of organ failure, we discuss the processes that lead to cell death, including necrosis, necroptosis, autophagy, mitophagy, and cellular senescence. In vivo technology is used to monitor these processes. To this end, we discuss new materials for developing in vivo biosensors and drug delivery systems. Such in vivo biosensors will define the diagnostic platform of the future ICU in vivo interacting with theragnostic drugs. In addition to pharmacological therapeutic options, placement and control of artificial organs to support or replace failing organs will be central in the ICU in vivo of the future. Remote monitoring and control of these biosensors and artificial organs will be made using adaptive physiological mathematical modeling of the critically ill patient. The current state of these developments is discussed.

High in-hospital blood pressure variability and severe disability or death in primary intracerebral hemorrhage patients

OBJECTIVE

To quantify in-hospital systolic blood pressure variability among patients with intracerebral hemorrhage, determine the association between high systolic blood pressure variability (HSBPV) and 90-day severe disability or death, and examine the association between pre-hospital factors and HSBPV.

METHODS

Adult, radiologically confirmed, intracerebral hemorrhage patients enrolled in a multi-site cohort were included. Using a semi-automated algorithm, systolic blood pressure values recorded from routine non-invasive systolic blood pressure monitoring in critical and acute care settings were extracted for the duration of hospitalization. Inter and intra-patient systolic blood pressure variability was quantified using generalized estimating equation methods. Modified Poisson and logistic regression models were fit to determine the association between HSBPV and 90-day severe disability or death and between pre-hospital characteristics and HSBPV, respectively.

RESULTS

A total of 566 patients managed at four certified stroke centers were included. Over 120,000 systolic blood pressure readings were analyzed, and a standard deviation (SD) of 13.0 was parameterized as a cut-off point to categorize HSBPV. Patients with HSBPV had a greater risk of 90-day severe disability or death (relative risk: 1.20, 95% confidence interval: 1.04-1.39), after controlling for age, pre-morbid functional status, and other disease severity measures. Greater likelihood of in-hospital HSBPV was independently observed in elderly, female patients, and in patients with high admission systolic blood pressure.

CONCLUSION

Quantification of HSBPV is feasible utilizing routinely collected systolic blood pressure readings, and a singular cut-off parameter for systolic blood pressure variability demonstrated association with 90-day severe disability or death. Elderly, female, and patients with high admission systolic blood pressure may be more likely to demonstrate HSBPV during hospitalization.

Big data and machine learning in critical care: Opportunities for collaborative research

The introduction of clinical information systems (CIS) in Intensive Care Units (ICUs) offers the possibility of storing a huge amount of machine-ready clinical data that can be used to improve patient outcomes and the allocation of resources, as well as suggest topics for randomized clinical trials. Clinicians, however, usually lack the necessary training for the analysis of large databases. In addition, there are issues referred to patient privacy and consent, and data quality. Multidisciplinary collaboration among clinicians, data engineers, machine-learning experts, statisticians, epidemiologists and other information scientists may overcome these problems. A multidisciplinary event (Critical Care Datathon) was held in Madrid (Spain) from 1 to 3 December 2017. Under the auspices of the Spanish Critical Care Society (SEMICYUC), the event was organized by the Massachusetts Institute of Technology (MIT) Critical Data Group (Cambridge, MA, USA), the Innovation Unit and Critical Care Department of San Carlos Clinic Hospital, and the Life Supporting Technologies group of Madrid Polytechnic University. After presentations referred to big data in the critical care environment, clinicians, data scientists and other health data science enthusiasts and lawyers worked in collaboration using an anonymized database (MIMIC III). Eight groups were formed to answer different clinical research questions elaborated prior to the meeting. The event produced analyses for the questions posed and outlined several future clinical research opportunities. Foundations were laid to enable future use of ICU databases in Spain, and a timeline was established for future meetings, as an example of how big data analysis tools have tremendous potential in our field.

A Systematic Review on Healthcare Analytics: Application and Theoretical Perspective of Data Mining

The growing healthcare industry is generating a large volume of useful data on patient demographics, treatment plans, payment, and insurance coverage—attracting the attention of clinicians and scientists alike. In recent years, a number of peer-reviewed articles have addressed different dimensions of data mining application in healthcare. However, the lack of a comprehensive and systematic narrative motivated us to construct a literature review on this topic. In this paper, we present a review of the literature on healthcare analytics using data mining and big data. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we conducted a database search between 2005 and 2016. Critical elements of the selected studies—healthcare sub-areas, data mining techniques, types of analytics, data, and data sources—were extracted to provide a systematic view of development in this field and possible future directions. We found that the existing literature mostly examines analytics in clinical and administrative decision-making. Use of human-generated data is predominant considering the wide adoption of Electronic Medical Record in clinical care. However, analytics based on website and social media data has been increasing in recent years. Lack of prescriptive analytics in practice and integration of domain expert knowledge in the decision-making process emphasizes the necessity of future research.

Big Data and Data Science in Critical Care

The digitalization of the health-care system has resulted in a deluge of clinical big data and has prompted the rapid growth of data science in medicine. Data science, which is the field of study dedicated to the principled extraction of knowledge from complex data, is particularly relevant in the critical care setting. The availability of large amounts of data in the ICU, the need for better evidence-based care, and the complexity of critical illness makes the use of data science techniques and data-driven research particularly appealing to intensivists. Despite the increasing number of studies and publications in the field, thus far there have been few examples of data science projects that have resulted in successful implementations of data-driven systems in the ICU. However, given the expected growth in the field, intensivists should be familiar with the opportunities and challenges of big data and data science. The present article reviews the definitions, types of algorithms, applications, challenges, and future of big data and data science in critical care.

The Dependence of Machine Learning on Electronic Medical Record Quality

There is growing interest in applying machine learning methods to Electronic Medical Records (EMR). Across different institutions, however, EMR quality can vary widely. This work investigated the impact of this disparity on the performance of three advanced machine learning algorithms: logistic regression, multilayer perceptron, and recurrent neural network. The EMR disparity was emulated using different permutations of the EMR collected at Children's Hospital Los Angeles (CHLA) Pediatric Intensive Care Unit (PICU) and Cardiothoracic Intensive Care Unit (CTICU). The algorithms were trained using patients from the PICU to predict in-ICU mortality for patients on a held out set of PICU and CTICU patients. The disparate patient populations between the PICU and CTICU provide an estimate of generalization errors across different ICUs. We quantified and evaluated the generalization of these algorithms on varying EMR size, input types, and fidelity of data.

Distributions and Behavior of Vital Signs in Critically Ill Children by Admission Diagnosis

OBJECTIVES

Define the distributions of heart rate and intraarterial blood pressure in children at admission to an ICU based on admission diagnosis and examine trends in these physiologic signs over 72 hours from admission (or to discharge if earlier).

DESIGN

A retrospective analysis of continuously acquired signals.

SETTING

A quaternary and primary referral children's hospital with a general PICU and cardiac critical care unit.

PATIENTS

One thousand two hundred eighty-nine patients less than 18 years old were analyzed. Data from individual patient admissions were divided into 19 groups by primary admission diagnosis or surgical procedure.

INTERVENTIONS

None.

MEASUREMENT AND MAIN RESULTS

Distributions at admission are dependent on patient age and admission diagnosis (p < 10(-6)). Heart rate decreases over time, whereas arterial blood pressure is relatively stable, with differences seen in the directions and magnitude of these trends when analyzed by diagnosis group (p < 10(-6)). Multiple linear regression analysis shows that patient age, diagnosis group, and physiologic vital sign value at admission explain 50-63% of the variation observed for that physiologic signal at 72 hours (or at discharge if earlier) with admission value having the greatest influence. Furthermore, the variance of either heart rate or arterial blood pressure for the individual patient is smaller than the variance measured at the level of the group of patients with the same diagnosis.

CONCLUSIONS

This is the first study reporting distributions of continuously measured physiologic variables and trends in their behavior according to admission diagnosis in critically ill children. Differences detected between and within diagnostic groups may aid in earlier recognition of outliers as well as allowing refinement of patient monitoring strategies.