Prediction and early detection of delirium in the intensive care unit by using heart rate variability and machine learning

The role of heart rate variability in predicting delirium: A systematic review and meta-analysis

Brain and heart interact through multiple ways. Heart rate variability, a non-invasive measurement is studied extensively as a predicting model for various health conditions including subarachnoid hemorrhage, cancer, and diabetes. There is limited evidence to predict delirium, an acute fluctuating disorder of brain dysfunction, as it poses a significant challenge in the intensive care unit (ICU) and post-operative setting. In this systematic review of 9 articles, heart rate variability indices were used to investigate the occurrence of post-operative and ICU delirium. This systematic review and meta-analysis reveal evidence of a strong predilection between postoperative and intensive care unit delirium and alterations in the heart rate variability, measured by mean differences for standard deviation of NN-intervals. Other heart rate variability indices [root mean squares of successive differences, low-frequency (LF), high-frequency (HF), and LF:HF ratio] showed lack of or very weak association. A non-invasive tool of brain and heart interaction may refine diagnostic predictions for acute brain dysfunctions like delirium in such population and would be an important step in delirium research.

Novel opportunities for clinical pharmacy research: development of a machine learning model to identify medication related causes of delirium in different patient groups

The advent of artificial intelligence (AI) technologies has taken the world of science by storm in 2023. The opportunities of this easy to access technology for clinical pharmacy research are yet to be fully understood. The development of a custom-made large language model (LLM) (DELSTAR) trained on a wide range of internationally recognised scientific publication databases, pharmacovigilance sites and international product characteristics to help identify and summarise medication related information on delirium, as a proof-of-concept model, identified new facilitators and barriers for robust clinical pharmacy practice research. This technology holds great promise for the development of much more comprehensive prescribing guidelines, practice support applications for clinical pharmacy, increased patient and prescribing safety and resultant implications for healthcare costs. The challenge will be to ensure its methodologically robust use and the detailed and transparent verification of its information accuracy.

Heart rate response and recovery during exercise predict future delirium risk-A prospective cohort study in middle- to older-aged adults

BACKGROUND

Delirium is a neurocognitive disorder characterized by an abrupt decline in attention, awareness, and cognition after surgical/illness-induced stressors on the brain. There is now an increasing focus on how cardiovascular health interacts with neurocognitive disorders given their overlapping risk factors and links to subsequent dementia and mortality. One common indicator for cardiovascular health is the heart rate response/recovery (HRR) to exercise, but how this relates to future delirium is unknown.

METHODS

Electrocardiogram data were examined in 38,740 middle- to older-aged UK Biobank participants (mean age = 58.1 years, range: 40-72 years; 47.3% males) who completed a standardized submaximal exercise stress test (15-s baseline, 6-min exercise, and 1-min recovery) and required hospitalization during follow-up. An HRR index was derived as the product of the heart rate (HR) responses during exercise (peak/resting HRs) and recovery (peak/recovery HRs) and categorized into low/average/high groups as the bottom quartile/middle 2 quartiles/top quartile, respectively. Associations between 3 HRR groups and new-onset delirium were investigated using Cox proportional hazards models and a 2-year landmark analysis to minimize reverse causation. Sociodemographic factors, lifestyle factors/physical activity, cardiovascular risk, comorbidities, cognition, and maximal workload achieved were included as covariates.

RESULTS

During a median follow-up period of 11 years, 348 participants (9/1000) newly developed delirium. Compared with the high HRR group (16/1000), the risk for delirium was almost doubled in those with low HRR (hazard ratio = 1.90, 95% confidence interval (95%CI): 1.30-2.79, p = 0.001) and average HRR (hazard ratio = 1.54, 95%CI: 1.07-2.22, p = 0.020)). Low HRR was equivalent to being 6 years older, a current smoker, or ≥3 additional cardiovascular disease risks. Results were robust in sensitivity analysis, but the risk appeared larger in those with better cognition and when only postoperative delirium was considered (n = 147; hazard ratio = 2.66, 95%CI: 1.46-4.85, p = 0.001).

CONCLUSION

HRR during submaximal exercise is associated with future risk for delirium. Given that HRR is potentially modifiable, it may prove useful for neurological risk stratification alongside traditional cardiovascular risk factors.

Potential of electronic devices for detection of health problems in older adults at home: A systematic review and meta-analysis

OBJECTIVE

The aim of this review was to evaluate the overall diagnostic performance of e-devices for detection of health problems in older adults at home.

METHODS

A systematic review was conducted following the PRISMA-DTA guidelines.

RESULTS

31 studies were included with 24 studies included in meta-analysis. The included studies were divided into four categories according to the signals detected: physical activity (PA), vital signs (VS), electrocardiography (ECG) and other. The meta-analysis showed the pooled estimates of sensitivity and specificity were 0.94 and 0.98 respectively in the 'VS' group. The pooled sensitivity and specificity were 0.97 and 0.98 respectively in the 'ECG' group.

CONCLUSIONS

All kinds of e-devices perform well in diagnosing the common health problems. While ECG-based health problems detection system is more reliable than VS-based ones. For sole signal detection system has limitation in diagnosing specific health problems, more researches should focus on developing new systems combined of multiple signals.

Prediction of intrapartum fever using continuously monitored vital signs and heart rate variability

Objectives

Neonatal early onset sepsis (EOS), bacterial infection during the first seven days of life, is difficult to diagnose because presenting signs are non-specific, but early diagnosis before birth can direct life-saving treatment for mother and baby. Specifically, maternal fever during labor from placental infection is the strongest predictor of EOS. Alterations in maternal heart rate variability (HRV) may precede development of intrapartum fever, enabling incipient EOS detection. The objective of this work was to build a predictive model for intrapartum fever.

Methods

Continuously measured temperature, heart rate, and beat-to-beat RR intervals were obtained from wireless sensors on women (n = 141) in labor; traditional manual vital signs were taken every 3-6 hours. Validated measures of HRV were calculated in moving 5-minute windows of RR intervals: standard deviation of normal-to-normal intervals (SDNN) and root mean square of successive differences (RMSSD) between normal heartbeats.

Results

Fever (>38.0 °C) was detected by manual or continuous measurements in 48 women. Compared to afebrile mothers, average SDNN and RMSSD in febrile mothers decreased significantly (p < 0.001) at 2 and 3 hours before fever onset, respectively. This observed HRV divergence and raw recorded vitals were applied to a logistic regression model at various time horizons, up to 4-5 hours before fever onset. Model performance increased with decreasing time horizons, and a model built using continuous vital signs as input variables consistently outperformed a model built from episodic vital signs.

Conclusions

HRV-based predictive models could identify mothers at risk for fever and infants at risk for EOS, guiding maternal antibiotic prophylaxis and neonatal monitoring.

The development of a web-based app employing machine learning for delirium prevention in long-term care facilities in South Korea

Background

Long-term care facilities (LCFs) in South Korea have limited knowledge of and capability to care for patients with delirium. They also often lack an electronic medical record system. These barriers hinder systematic approaches to delirium monitoring and intervention. Therefore, this study aims to develop a web-based app for delirium prevention in LCFs and analyse its feasibility and usability.

Methods

The app was developed based on the validity of the AI prediction model algorithm. A total of 173 participants were selected from LCFs to participate in a study to determine the predictive risk factors for delerium.

The app was developed in five phases: (1) the identification of risk factors and preventive intervention strategies from a review of evidence-based literature, (2) the iterative design of the app and components of delirium prevention, (3) the development of a delirium prediction algorithm and cloud platform, (4) a pilot test and validation conducted with 33 patients living in a LCF, and (5) an evaluation of the usability and feasibility of the app, completed by nurses (Main users).

Results

A web-based app was developed to predict high risk of delirium and apply preventive interventions accordingly. Moreover, its validity, usability, and feasibility were confirmed after app development. By employing machine learning, the app can predict the degree of delirium risk and issue a warning alarm. Therefore, it can be used to support clinical decision-making, help initiate the assessment of delirium, and assist in applying preventive interventions.

Conclusions

This web-based app is evidence-based and can be easily mobilised to support care for patients with delirium in LCFs. This app can improve the recognition of delirium and predict the degree of delirium risk, thereby helping develop initiatives for delirium prevention and providing interventions. Moreover, this app can be extended to predict various risk factors of LCF and apply preventive interventions. Its use can ultimately improve patient safety and quality of care.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-01966-8.

Heart Rate Variability Can Detect Blunt Traumatic Brain Injury Within the First Hour

INTRODUCTION

In patients with multi-organ system trauma, the diagnosis of coinciding traumatic brain injury can be difficult due to injuries from the hemorrhagic shock that confound clinical and radiographic signs of traumatic brain injury. In this study, a novel technique using heart rate variability was developed in a porcine model to detect traumatic brain injury early in the setting of hemorrhagic shock without the need for radiographic imaging or clinical exam.

METHODS

A porcine model of hemorrhagic shock was used with an arm of swine receiving hemorrhagic shock alone and hemorrhagic shock with traumatic brain injury. High-resolution heart rate frequencies were collected at different time intervals using waveforms based on voltage delivered from the heart rate monitor. Waveforms were analyzed to assess statistically significant differences between heart rate variability parameters in those with hemorrhagic shock and traumatic brain injury versus those with only hemorrhagic shock. Stochastic analysis was used to assess the validity of results and create a model by machine learning to better assess the presence of traumatic brain injury.

RESULTS

Significant differences were found in several heart rate variability parameters between the two groups. Additionally, significant differences in heart rate variability parameters were found in swine within 1 hour of inducing hemorrhage in those with traumatic brain injury versus those without. These results were confirmed with stochastic analysis and machine learning was used to generate a model which determined the presence of traumatic brain injury in the setting of hemorrhage shock with 91.6% accuracy.

CONCLUSIONS

 Heart rate variability represents a promising diagnostic tool to aid in the diagnosis of traumatic brain injury within 1 hour of injury.

Redefining critical illness

Research and practice in critical care medicine have long been defined by syndromes, which, despite being clinically recognizable entities, are, in fact, loose amalgams of heterogeneous states that may respond differently to therapy. Mounting translational evidence-supported by research on respiratory failure due to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection-suggests that the current syndrome-based framework of critical illness should be reconsidered. Here we discuss recent findings from basic science and clinical research in critical care and explore how these might inform a new conceptual model of critical illness. De-emphasizing syndromes, we focus on the underlying biological changes that underpin critical illness states and that may be amenable to treatment. We hypothesize that such an approach will accelerate critical care research, leading to a richer understanding of the pathobiology of critical illness and of the key determinants of patient outcomes. This, in turn, will support the design of more effective clinical trials and inform a more precise and more effective practice at the bedside.

Early heart rate variability evaluation enables to predict ICU patients' outcome

Heart rate variability (HRV) is a mean to evaluate cardiac effects of autonomic nervous system activity, and a relation between HRV and outcome has been proposed in various types of patients. We attempted to evaluate the best determinants of such variation in survival prediction using a physiological data-warehousing program. Plethysmogram tracings (PPG) were recorded at 75 Hz from the standard monitoring system, for a 2 h period, during the 24 h following ICU admission. Physiological data recording was associated with metadata collection. HRV was derived from PPG in either the temporal and non-linear domains. 540 consecutive patients were recorded. A lower LF/HF, SD2/SD1 ratios and Shannon entropy values on admission were associated with a higher ICU mortality. SpO2/FiO2 ratio and HRV parameters (LF/HF and Shannon entropy) were independent correlated with mortality in the multivariate analysis. Machine-learning using neural network (kNN) enabled to determine a simple decision tree combining the three best determinants (SDNN, Shannon Entropy, SD2/SD1 ratio) of a composite outcome index. HRV measured on admission enables to predict outcome in the ICU or at Day-28, independently of the admission diagnosis, treatment and mechanical ventilation requirement.

Trial registration: ClinicalTrials.gov identifier NCT02893462.

Predicting Delayed Neurocognitive Recovery After Non-cardiac Surgery Using Resting-State Brain Network Patterns Combined With Machine Learning

Delayed neurocognitive recovery (DNR) is a common subtype of postoperative neurocognitive disorders. An objective approach for identifying subjects at high risk of DNR is yet lacking. The present study aimed to predict DNR using the machine learning method based on multiple cognitive-related brain network features. A total of 74 elderly patients (≥ 60-years-old) undergoing non-cardiac surgery were subjected to resting-state functional magnetic resonance imaging (rs-fMRI) before the surgery. Seed-based whole-brain functional connectivity (FC) was analyzed with 18 regions of interest (ROIs) located in the default mode network (DMN), limbic network, salience network (SN), and central executive network (CEN). Multiple machine learning models (support vector machine, decision tree, and random forest) were constructed to recognize the DNR based on FC network features. The experiment has three parts, including performance comparison, feature screening, and parameter adjustment. Then, the model with the best predictive efficacy for DNR was identified. Finally, independent testing was conducted to validate the established predictive model. Compared to the non-DNR group, the DNR group exhibited aberrant whole-brain FC in seven ROIs, including the right posterior cingulate cortex, right medial prefrontal cortex, and left lateral parietal cortex in the DMN, the right insula in the SN, the left anterior prefrontal cortex in the CEN, and the left ventral hippocampus and left amygdala in the limbic network. The machine learning experimental results identified a random forest model combined with FC features of DMN and CEN as the best prediction model. The area under the curve was 0.958 (accuracy = 0.935, precision = 0.899, recall = 0.900, F1 = 0.890) on the test set. Thus, the current study indicated that the random forest machine learning model based on rs-FC features of DMN and CEN predicts the DNR following non-cardiac surgery, which could be beneficial to the early prevention of DNR. Clinical Trial Registration: The study was registered at the Chinese Clinical Trial Registry (Identification number: ChiCTR-DCD-15006096).

Machine Learning to Identify Psychomotor Behaviors of Delirium for Patients in Long-Term Care Facility

This study aimed to develop accurate and explainable machine learning models for three psychomotor behaviors of delirium for hospitalized adult patients. A prospective pilot study was conducted with 33 participants admitted to a long-term care facility between August 10 and 25, 2020. During the pilot study, we collected 560 cases that included 33 clinical variables and the survey items from the short confusion assessment method (S-CAM), and developed a mobile-based application. Multiple machine learning algorithms, including four rule-mining algorithms (C4.5, CBA, MCAR, and LEM2) and four other statistical learning algorithms (LR, ANNs, SVMs with three kernel functions, and random forest), were validated by paired Wilcoxon signed-rank tests on both macro-averaged F1 and weighted average F1-measures during the 10-times stratified 2-fold cross-validation. The LEM2 algorithm achieved the best prediction performance (macro-averaged F1-measure of 49.35%; weighted average F1-measure of 96.55%), correctly identifying adult patients at delirium risk. In the pairwise comparison between predictive powers observed from independent models, the LEM2 model showed a medium or large effect size between 0.4925 and 0.8766 when compared with LR, ANN, SVM with RBF, and MCAR models. We have confirmed that acute consciousness in S-CAM assessment is closely associated with different predictors for screening three psychomotor behaviors of delirium: 1) education level, dementia type or its level, sleep disorder, dehydration, and infection in mixed-type delirium; 2) gender, education level, dementia type, dehydration, bedsores, and foley catheter in hyperactive delirium; and 3) pain, sleep disorder, and haloperidol use in hypoactive delirium.

Preoperative heart rate variability analysis is as a potential simple and easy measure for predicting perioperative delirium in esophageal surgery

Background

Delirium is one of the most common but severe perioperative complications. Autonomic activity evaluated by heart rate variability (HRV) has been recently reported as a useful tool for prediction and for early detection of delirium in acute care medicine, especially in postoperative intensive care unit (ICU) patients. We hypothesized that HRV, by 3-lead electrocardiogram (ECG), one day prior to surgery might correlate with the presence of postoperative delirium.

Materials and methods

This study was cohort prospective pilot study. We measured preoperative HRV and postoperative delirium in patients who underwent surgery for elective esophageal cancer. ECG of the participants was performed for 10 min 6–12 h preceding surgery. Postoperatively, patients were admitted to the ICU or critical care unit and stayed for at least 3 days. Delirium was diagnosed by psychiatrist rounds twice a day.

Results

Delirium was assessed for 3 days after surgery and 30 patients performed the study. Seven patients developed delirium during their ICU stay, while the remaining twenty-three did not. After HRV analysis, the preoperative high frequency power in delirium patients was significantly lower than that in non-delirium patient. Other parameters of HRV, including lower frequency power, total power and the ratio showed no statistically significant difference between the groups.

Conclusion

The results of current study demonstrated that preoperative measurement of HRV may be a useful predictor of delirium. Further investigation could pave the way to a non-invasive, minimally stressful method of predicting postoperative delirium.

•

Delirium is one of the most common and severe postoperative complications.

•

Delirium prediction can provide better treatment for patients.

•

Heart rate variability analysis might predict delirium in esophageal cancer surgery.

Heart rate variability and delirium in acute non-cardioembolic stroke: a prospective, cross-sectional, cohort study

Objectives

Delirium is an acute fluctuating disorder of attention and awareness. It is associated with autonomic dysfunction and increased mortality. The primary endpoint of our study was to measure autonomic activity in acute stroke patients, by means of heart rate variability analysis, in order to identify autonomic modifications that can predispose to delirium.

Methods

Patients were consecutively enrolled from the stroke unit. Inclusion criteria were age ≥ 18 years and diagnosis of stroke with onset within the previous 72 h confirmed by neuroimaging. Exclusion criteria were atrial fibrillation, congestive heart failure, and conditions requiring intensive care unit. Patients were evaluated by means of Richmond Agitation Sedation Scale (RASS) and Confusion Assessment Method-Intensive Care Unit (CAM-ICU) at baseline, after 72 h, or when symptoms suggesting delirium occurred. For each patient, ECG was recorded at baseline assessment and HRV analysis was conducted on five consecutive minutes of artifact-free ECG traces.

Results

Fifty-six ECGs were available for analysis. During the study period, 11 patients developed delirium. Patients with and without delirium did not differ for sex, age, severity of stroke, and comorbidities. The delirium group had greater standard deviation of the heart rate (DLR − :9.16 ± 8.28; DLR + : 14.36 ± 5.55; p = 0.026) and lower power spectral density of the HF component (DLR − : 38.23 ± 19.23 n.u.; DLR + : 25.75 ± 8.77 n.u.; p = 0.031).

Conclusions

Acute non-cardioembolic stroke patients with increased variability of heart rate and decreased vagal control are at risk for delirium.

Developing a machine learning model to identify delirium risk in geriatric internal medicine inpatients

PURPOSE

To develop a machine learning model that predicts delirium risk in geriatric internal medicine inpatients.

METHODS

A prospective cohort study of internal medicine wards in a tertiary care hospital in China. Blinded observers assessed delirium using the Confusion Assessment Method (CAM). The data set was randomly divided into a training set (70%) and a test set (30%). The model was trained on the training set using the decision tree and the five-fold cross-validation, and then the model performance was evaluated on the test set. Under-sampling was used to address the class imbalance. The discriminatory power of the model was measured by the area under the receiver operating characteristic curve (AUC) and F1 score. The data set comprised 740 patients from March 2016 to January 2017.

RESULTS

The training set included 518 patients; the median (IQR) age was 84 (79-87) years; 364 (70.3%) were men; 71 (13.7%) with delirium. The test set included 222 patients; the median (IQR) age was 84.5 (79-87) years; 163 (73.4%) were men; 30 (13.5%) with delirium. In total, the data set included 740 hospital admissions with a median (IQR) age of 84 (79-87) years, 527 (71.2%) were men, and 101 (13.6%) with delirium. From 32 potential predictors, we included five variables in the predictive model: depression, cognitive impairment, types of drugs, nutritional status, and activity of daily life (ADL). The mean AUC on the training set was 0.967, the AUC and F1 score on the test set was 0.950 and 0.810, respectively. The model achieved 93.3% sensitivity, 94.3% specificity, 71.8% positive predictive value, 98.9% negative predictive value, and 94.1% accuracy on the test set.

CONCLUSION

This machine learning model may allow more precise targeting of delirium prevention and could support clinical decision making in geriatric internal medicine wards.

Predicting brain function status changes in critically ill patients via Machine learning

OBJECTIVE

In intensive care units (ICUs), a patient's brain function status can shift from a state of acute brain dysfunction (ABD) to one that is ABD-free and vice versa, which is challenging to forecast and, in turn, hampers the allocation of hospital resources. We aim to develop a machine learning model to predict next-day brain function status changes.

MATERIALS AND METHODS

Using multicenter prospective adult cohorts involving medical and surgical ICU patients from 2 civilian and 3 Veteran Affairs hospitals, we trained and externally validated a light gradient boosting machine to predict brain function status changes. We compared the performances of the boosting model against state-of-the-art models-an ABD predictive model and its variants. We applied Shapley additive explanations to identify influential factors to develop a compact model.

RESULTS

There were 1026 critically ill patients without evidence of prior major dementia, or structural brain diseases, from whom 12 295 daily transitions (ABD: 5847 days; ABD-free: 6448 days) were observed. The boosting model achieved an area under the receiver-operating characteristic curve (AUROC) of 0.824 (95% confidence interval [CI], 0.821-0.827), compared with the state-of-the-art models of 0.697 (95% CI, 0.693-0.701) with P < .001. Using 13 identified top influential factors, the compact model achieved 99.4% of the boosting model on AUROC. The boosting and the compact models demonstrated high generalizability in external validation by achieving an AUROC of 0.812 (95% CI, 0.812-0.813).

CONCLUSION

The inputs of the compact model are based on several simple questions that clinicians can quickly answer in practice, which demonstrates the model has direct prospective deployment potential into clinical practice, aiding in critical hospital resource allocation.

A Machine Learning Approach for Investigating Delirium as a Multifactorial Syndrome

Delirium is a psycho-organic syndrome common in hospitalized patients, especially the elderly, and is associated with poor clinical outcomes. This study aims to identify the predictors that are mostly associated with the risk of delirium episodes using a machine learning technique (MLT). A random forest (RF) algorithm was used to evaluate the association between the subject’s characteristics and the 4AT (the 4 A’s test) score screening tool for delirium. RF algorithm was implemented using information based on demographic characteristics, comorbidities, drugs and procedures. Of the 78 patients enrolled in the study, 49 (63%) were at risk for delirium, 32 (41%) had at least one episode of delirium during the hospitalization (38% in orthopedics and 31% both in internal medicine and in the geriatric ward). The model explained 75.8% of the variability of the 4AT score with a root mean squared error of 3.29. Higher age, the presence of dementia, physical restraint, diabetes and a lower degree are the variables associated with an increase of the 4AT score. Random forest is a valid method for investigating the patients’ characteristics associated with delirium onset also in small case-series. The use of this model may allow for early detection of delirium onset to plan the proper adjustment in healthcare assistance.

Development and validation of a postoperative delirium prediction model for pediatric patients: A prospective, observational, single-center study

Postoperative delirium is a serious complication that relates to poor outcomes. A risk prediction model could help the staff screen for children at high risk for postoperative delirium. Our study aimed to establish a postoperative delirium prediction model for pediatric patients and to verify the sensitivity and specificity of this model.Data were collected from a total of 1134 children (0-16yr) after major elective surgery between February 2020 to June 2020. Demographic and clinical data were collected to explore the risk factors. Multivariate logistic regression analysis was used to develop the model, and we assessed the predictive ability of the model by using the area under the receiver operating characteristics curve (AUROC). Further data were collected from another 100 patients in October 2020 to validate the model.Prevalence of postoperative delirium in this sample was 11.1%. The model consisted of 5 predictors, namely, age, developmental delay, type of surgery, pain, and dexmedetomidine. The AUROC was 0.889 (P < .001, 95% confidence interval (CI):0.857-0.921), with sensitivity and specificity of 0.754 and 0.867, and the Youden of 0.621. The model verification results showed the sensitivity of 0.667, the specificity of 0.955.Children undergoing surgery are at risk for developing delirium during the postoperative period, young age, developmental delay, otorhinolaryngology surgery, pain, and exposure to dexmedetomidine were associated with increased odds of delirium. Our study established a postoperative delirium prediction model for pediatric patients, which may be a base for development of strategies to prevent and treat postoperative delirium in children.

A novel model to label delirium in an intensive care unit from clinician actions

BACKGROUND

In the intensive care unit (ICU), delirium is a common, acute, confusional state associated with high risk for short- and long-term morbidity and mortality. Machine learning (ML) has promise to address research priorities and improve delirium outcomes. However, due to clinical and billing conventions, delirium is often inconsistently or incompletely labeled in electronic health record (EHR) datasets. Here, we identify clinical actions abstracted from clinical guidelines in electronic health records (EHR) data that indicate risk of delirium among intensive care unit (ICU) patients. We develop a novel prediction model to label patients with delirium based on a large data set and assess model performance.

METHODS

EHR data on 48,451 admissions from 2001 to 2012, available through Medical Information Mart for Intensive Care-III database (MIMIC-III), was used to identify features to develop our prediction models. Five binary ML classification models (Logistic Regression; Classification and Regression Trees; Random Forests; Naïve Bayes; and Support Vector Machines) were fit and ranked by Area Under the Curve (AUC) scores. We compared our best model with two models previously proposed in the literature for goodness of fit, precision, and through biological validation.

RESULTS

Our best performing model with threshold reclassification for predicting delirium was based on a multiple logistic regression using the 31 clinical actions (AUC 0.83). Our model out performed other proposed models by biological validation on clinically meaningful, delirium-associated outcomes.

CONCLUSIONS

Hurdles in identifying accurate labels in large-scale datasets limit clinical applications of ML in delirium. We developed a novel labeling model for delirium in the ICU using a large, public data set. By using guideline-directed clinical actions independent from risk factors, treatments, and outcomes as model predictors, our classifier could be used as a delirium label for future clinically targeted models.

Machine Learning to Develop and Internally Validate a Predictive Model for Post-operative Delirium in a Prospective, Observational Clinical Cohort Study of Older Surgical Patients

BACKGROUND

Our objective was to assess the performance of machine learning methods to predict post-operative delirium using a prospective clinical cohort.

METHODS

We analyzed data from an observational cohort study of 560 older adults (≥ 70 years) without dementia undergoing major elective non-cardiac surgery. Post-operative delirium was determined by the Confusion Assessment Method supplemented by a medical chart review (N = 134, 24%). Five machine learning algorithms and a standard stepwise logistic regression model were developed in a training sample (80% of participants) and evaluated in the remaining hold-out testing sample. We evaluated three overlapping feature sets, restricted to variables that are readily available or minimally burdensome to collect in clinical settings, including interview and medical record data. A large feature set included 71 potential predictors. A smaller set of 18 features was selected by an expert panel using a consensus process, and this smaller feature set was considered with and without a measure of pre-operative mental status.

RESULTS

The area under the receiver operating characteristic curve (AUC) was higher in the large feature set conditions (range of AUC, 0.62-0.71 across algorithms) versus the selected feature set conditions (AUC range, 0.53-0.57). The restricted feature set with mental status had intermediate AUC values (range, 0.53-0.68). In the full feature set condition, algorithms such as gradient boosting, cross-validated logistic regression, and neural network (AUC = 0.71, 95% CI 0.58-0.83) were comparable with a model developed using traditional stepwise logistic regression (AUC = 0.69, 95% CI 0.57-0.82). Calibration for all models and feature sets was poor.

CONCLUSIONS

We developed machine learning prediction models for post-operative delirium that performed better than chance and are comparable with traditional stepwise logistic regression. Delirium proved to be a phenotype that was difficult to predict with appreciable accuracy.

ICU Delirium-Prediction Models: A Systematic Review

Supplemental Digital Content is available in the text.

Objective:

Summarize performance and development of ICU delirium-prediction models published within the past 5 years.

Data Sources:

Systematic electronic searches were conducted in April 2019 using PubMed, Embase, Cochrane Central, Web of Science, and Cumulative Index to Nursing and Allied Health Literature to identify peer-reviewed studies.

Study Selection:

Eligible studies were published in English during the past 5 years that specifically addressed the development, validation, or recalibration of delirium-prediction models in adult ICU populations.

Data Extraction:

Screened citations were extracted independently by three investigators with a 42% overlap to verify consistency using the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies.

Data Synthesis:

Eighteen studies featuring 23 distinct prediction models were included. Model performance varied greatly, as assessed by area under the receiver operating characteristic curve (0.62–0.94), specificity (0.50–0.97), and sensitivity (0.45–0.96). Most models used data collected from a single time point or window to predict the occurrence of delirium at any point during hospital or ICU admission, and lacked mechanisms for providing pragmatic, actionable predictions to clinicians.

Conclusions:

Although most ICU delirium-prediction models have relatively good performance, they have limited applicability to clinical practice. Most models were static, making predictions based on data collected at a single time-point, failing to account for fluctuating conditions during ICU admission. Further research is needed to create clinically relevant dynamic delirium-prediction models that can adapt to changes in individual patient physiology over time and deliver actionable predictions to clinicians.

Transcutaneous Neuromodulation improved inflammation and sympathovagal ratio in patients with primary biliary ssscholangitis and inadequate response to Ursodeoxycholic acid: a pilot study

Background

At present, ursodeoxycholic acid (UDCA) is internationally recognized as a therapeutic drug in clinic. However, about 40% Primary Biliary Cholangitis (PBC) patients are poor responders to UDCA. It has been demonstrated that Transcutaneous Neuromodulation (TN) can be involved in gut motility, metabolism of bile acids, immune inflammation, and autonomic nerve. Therefore, this study aimed to explore the effect of TN combined with UDCA on PBC and related mechanisms.

Methods

According to inclusion and exclusion criteria, 10 healthy volunteers and 15 PBC patients were recruited to control group and TN group, respectively. PBC patients were alternately but blindly assigned to group A (TN combined with UDCA) and group B (sham-TN combined with UDCA), and a crossover design was used. The TN treatment was performed via the posterior tibial nerve and acupoint ST36 (Zusanli) 1 h twice/day for 2 weeks. T test and nonparametric test were used to analyze the data.

Results

1. TN combined with UDCA improved the liver function of PBC patients shown by a significant decrease of alkaline phosphatase and gamma-glutamyltransferase (γ-GT) (P < 0.05). 2. The treatment also decreased serum IL-6 levels (P < 0.05), but not the level of Tumor Necrosis Factor-α, IL-1β or IL-10. 3. TN combined with UDCA regulated autonomic function, enhanced vagal activity, and decreased the sympathovagal ratio assessed by the spectral analysis of heart rate variability (P < 0.05). 4. There was no change in 13 bile acids in serum or stool after TN or sham-TN.

Conclusions

TN cssombined with UDCA can significantly improve the liver function of PBC patients. It is possibly via the cholinergic anti-inflammatory pathway. TN might be a new non-drug therapy for PBC. Further studies are required.

Trial registration

The study protocol was registered in Chinese Clinical Trial Registry (number ChiCTR1800014633) on 25 January 2018.

Delirium prediction in the intensive care unit: a temporal approach

The incidence of delirium in intensive care units is high and associated with poor outcomes; therefore, its prediction is desirable to establish preventive treatments. This retrospective study proposes a novel approach for delirium prediction. We analyzed static and temporal data from 10,475 patients admitted to one of 15 intensive care units (ICUs) in Alberta, Canada between January 1, 2014 and June 30, 2016. We tested 168 different combinations of study design parameters and five different predictive models (logistic regression, support vector machines, random forests, adaptive boosting and neural networks). The area under the receiver operating characteristic curve (AUROC) ranged from 0.754 (CI 95% ± 0.018) to 0.852 (± 0.033), with sensitivity and specificity respectively ranging from 0.739 (CI 95% ± 0.047) to 0.840 (CI 95% ± 0.064), and 0.770 (CI 95% ± 0.030) to 0.865 (CI 95% ± 0.038). These results are similar to previous studies; however, our approach allows for continuous updates and short-term prediction horizons which might provide major advantages.

Toward precision health: applying artificial intelligence analytics to digital health biometric datasets

The rapid development of digital health devices has enabled patients to engage in their care to an unprecedented degree and holds the possibility of significantly improving the diagnosis, treatment and monitoring of many medical conditions. Combined with the emergence of artificial intelligence algorithms, biometric datasets produced from these digital health devices present new opportunities to create precision-based, personalized approaches for healthcare delivery. For effective implementation of such innovations to patient care, clinicians will require an understanding of the types of datasets produced from digital health technologies; the types of analytic methods including feature selection, convolution neural networking, and deep learning that can be used to analyze digital data; and how the interpretation of these findings are best translated to patient care. In this perspective, we aim to provide the groundwork for clinicians to be able to apply artificial intelligence to this transformation of healthcare.

A New Methodology Based on EMD and Nonlinear Measurements for Sudden Cardiac Death Detection

Heart diseases are among the most common death causes in the population. Particularly, sudden cardiac death (SCD) is the cause of 10% of the deaths around the world. For this reason, it is necessary to develop new methodologies that can predict this event in the earliest possible stage. This work presents a novel methodology to predict when a person can develop an SCD episode before it occurs. It is based on the adroit combination of the empirical mode decomposition, nonlinear measurements, such as the Higuchi fractal and permutation entropy, and a neural network. The obtained results show that the proposed methodology is capable of detecting an SCD episode 25 min before it appears with a 94% accuracy. The main benefits of the proposal are: (1) an improved detection time of 25% compared with previously published works, (2) moderate computational complexity since only two features are used, and (3) it uses the raw ECG without any preprocessing stage, unlike recent previous works.

Comparison of multiple cardiac signal acquisition technologies for heart rate variability analysis

Heart rate variability analysis is a recognized non-invasive tool that is used to assess autonomic nervous system regulation in various clinical settings and medical conditions. A wide variety of HRV analysis methods have been proposed, but they all require a certain number of cardiac beats intervals. There are many ways to record cardiac activity: electrocardiography, phonocardiography, plethysmocardiography, seismocardiography. However, the feasibility of performing HRV analysis with these technologies and particularly their ability to detect autonomic nervous system changes still has to be studied. In this study, we developed a technology allowing the simultaneous monitoring of electrocardiography, phonocardiography, seismocardiography, photoplethysmocardiography and piezoplethysmocardiography and investigated whether these sensors could be used for HRV analysis. We therefore tested the evolution of several HRV parameters computed from several sensors before, during and after a postural change. The main findings of our study is that even if most sensors were suitable for mean HR computation, some of them demonstrated limited agreement for several HRV analyses methods. We also demonstrated that piezoplethysmocardiography showed better agreement with ECG than other sensors for most HRV indexes.

The Effects of Transcranial Direct Current Stimulation on the Cognitive and Behavioral Changes After Electrode Implantation Surgery in Rats

Postoperative delirium can lead to increased morbidity and mortality, and may even be a potentially life-threatening clinical syndrome. However, the neural mechanism underlying this condition has not been fully understood and there is little knowledge regarding potential preventive strategies. To date, investigation of transcranial direct current stimulation (tDCS) for the relief of symptoms caused by neuropsychiatric disorders and the enhancement of cognitive performance has led to promising results. In this study, we demonstrated that tDCS has a possible effect on the fast recovery from delirium in rats after microelectrode implant surgery, as demonstrated by postoperative behavior and neurophysiology compared with sham stimulation. This is the first study to describe the possible effects of tDCS for the fast recovery from delirium based on the study of both electroencephalography and behavioral changes. Postoperative rats showed decreased attention, which is the core symptom of delirium. However, anodal tDCS over the right frontal area immediately after surgery exhibited positive effects on acute attentional deficit. It was found that relative power of theta was lower in the tDCS group than in the sham group after surgery, suggesting that the decrease might be the underlying reason for the positive effects of tDCS. Connectivity analysis revealed that tDCS could modulate effective connectivity and synchronization of brain activity among different brain areas, including the frontal cortex, parietal cortex, and thalamus. It was concluded that anodal tDCS on the right frontal regions may have the potential to help patients recover quickly from delirium.

Applying machine learning to continuously monitored physiological data

The use of machine learning (ML) in healthcare has enormous potential for improving disease detection, clinical decision support, and workflow efficiencies. In this commentary, we review published and potential applications for the use of ML for monitoring within the hospital environment. We present use cases as well as several questions regarding the application of ML to the analysis of the vast amount of complex data that clinicians must interpret in the realm of continuous physiological monitoring. ML, especially employed in bidirectional conjunction with electronic health record data, has the potential to extract much more useful information out of this currently under-analyzed data source from a population level. As a data driven entity, ML is dependent on copious, high quality input data so that error can be introduced by low quality data sources. At present, while ML is being studied in hybrid formulations along with static expert systems for monitoring applications, it is not yet actively incorporated in the formal artificial learning sense of an algorithm constantly learning and updating its rules without external intervention. Finally, innovations in monitoring, including those supported by ML, will pose regulatory and medico-legal challenges, as well as questions regarding precisely how to incorporate these features into clinical care and medical education. Rigorous evaluation of ML techniques compared to traditional methods or other AI methods will be required to validate the algorithms developed with consideration of database limitations and potential learning errors. Demonstration of value on processes and outcomes will be necessary to support the use of ML as a feature in monitoring system development: Future research is needed to evaluate all AI based programs before clinical implementation in non-research settings.

Deep phenotyping in zebrafish reveals genetic and diet-induced adiposity changes that may inform disease risk

The regional distribution of adipose tissues is implicated in a wide range of diseases. For example, proportional increases in visceral adipose tissue increase the risk for insulin resistance, diabetes, and CVD. Zebrafish offer a tractable model system by which to obtain unbiased and quantitative phenotypic information on regional adiposity, and deep phenotyping can explore complex disease-related adiposity traits. To facilitate deep phenotyping of zebrafish adiposity traits, we used pairwise correlations between 67 adiposity traits to generate stage-specific adiposity profiles that describe changing adiposity patterns and relationships during growth. Linear discriminant analysis classified individual fish according to an adiposity profile with 87.5% accuracy. Deep phenotyping of eight previously uncharacterized zebrafish mutants identified neuropilin 2b as a novel gene that alters adipose distribution. When we applied deep phenotyping to identify changes in adiposity during diet manipulations, zebrafish that underwent food restriction and refeeding had widespread adiposity changes when compared with continuously fed, equivalently sized control animals. In particular, internal adipose tissues (e.g., visceral adipose) exhibited a reduced capacity to replenish lipid following food restriction. Together, these results in zebrafish establish a new deep phenotyping technique as an unbiased and quantitative method to help uncover new relationships between genotype, diet, and adiposity.