Artificial neural networks and risk stratification in emergency departments

Role of Artificial Intelligence in Improving Syncope Management

Syncope is common in the general population and is a common presenting symptom in acute care settings. Substantial costs are attributed to care of patients with syncope. Current challenges include differentiating syncope from its mimickers, identifying serious underlying conditions that caused the syncope, and wide variations in current management. While validated risk tools exist especially for short-term prognosis, there is inconsistent application, and the current approach does not meet the patient needs/expectations. Artificial intelligence (AI) techniques such as machine learning methods including natural language processing can potentially address the current challenges in syncope management. Preliminary evidence from published studies indicates that it is possible to accurately differentiate syncope from its mimickers and predict short-term prognosis/ hospitalization. More recently AI analysis of ECG has shown promise in detection of serious structural and functional cardiac abnormalities which has the potential to improve syncope care. Future AI studies have the potential to address current issues in syncope management. AI can automatically prognosticate risk in real time by accessing traditional and non-traditional data. However, steps to mitigate known problems such generalizability, patient privacy, data protection, and liability will be needed. In the past AI has had limited impact due to underdeveloped analytical methods, lack of computing power, poor access to powerful computing systems, and availability of reliable high-quality data. All impediments except data have been solved. AI will live up to its promise to transform syncope care if the health care system can satisfy AI requirement of large scale, robust, accurate, and reliable data.

Artificial Intelligence in Enhancing Syncope Management - An Update

This review looks into the use of Artificial Intelligence (AI) in the management of syncope, a condition characterized by a brief loss of consciousness caused by cerebral hypoperfusion. With rising prevalence, high costs, and difficulty in diagnosis and risk stratification, syncope poses significant healthcare challenges. AI has the potential to improve symptom differentiation, risk assessment, and patient management. Machine learning, specifically Artificial Neural Networks, has shown promise in accurate risk stratification. AI-powered clinical decision support tools can improve patient evaluation and resource utilization. While AI holds great promise for syncope management, challenges such as data quality, class imbalance, and defining risk categories remain. Ethical concerns about patient privacy, as well as the need for human empathy, complicate AI integration. Collaboration among data scientists, clinicians, and ethics experts is critical for the successful implementation of AI, which has the potential to improve patient outcomes and healthcare efficiency in syncope management.

A Hybrid Model for 30-Day Syncope Prognosis Prediction in the Emergency Department

Syncope is a challenging problem in the emergency department (ED) as the available risk prediction tools have suboptimal predictive performances. Predictive models based on machine learning (ML) are promising tools whose application in the context of syncope remains underexplored. The aim of the present study was to develop and compare the performance of ML-based models in predicting the risk of clinically significant outcomes in patients presenting to the ED for syncope. We enrolled 266 consecutive patients (age 73, IQR 58-83; 52% males) admitted for syncope at three tertiary centers. We collected demographic and clinical information as well as the occurrence of clinically significant outcomes at a 30-day telephone follow-up. We implemented an XGBoost model based on the best-performing candidate predictors. Subsequently, we integrated the XGboost predictors with knowledge-based rules. The obtained hybrid model outperformed the XGboost model (AUC = 0.81 vs. 0.73, p < 0.001) with acceptable calibration. In conclusion, we developed an ML-based model characterized by a commendable capability to predict adverse events within 30 days post-syncope evaluation in the ED. This model relies solely on clinical data routinely collected during a patient's initial syncope evaluation, thus obviating the need for laboratory tests or syncope experienced clinical judgment.

Application of artificial neural networks in reproductive medicine

With the emergence of the age of information, the data on reproductive medicine has improved immensely. Nonetheless, healthcare workers who wish to utilise the relevance and implied value of the various data available to aid clinical decision-making encounter the difficulty of statistically analysing such large data. The application of artificial intelligence becoming widespread in recent years has emerged as a turning point in this regard. Artificial neural networks (ANNs) exhibit beneficial characteristics of comprehensive analysis and autonomous learning, owing to which these are being applied to disease diagnosis, embryo quality assessment, and prediction of pregnancy outcomes. The present report aims to summarise the application of ANNs in the field of reproduction and analyse its further application potential.

Multimodal deep learning for COVID-19 prognosis prediction in the emergency department: a bi-centric study

Predicting clinical deterioration in COVID-19 patients remains a challenging task in the Emergency Department (ED). To address this aim, we developed an artificial neural network using textual (e.g. patient history) and tabular (e.g. laboratory values) data from ED electronic medical reports. The predicted outcomes were 30-day mortality and ICU admission. We included consecutive patients from Humanitas Research Hospital and San Raffaele Hospital in the Milan area between February 20 and May 5, 2020. We included 1296 COVID-19 patients. Textual predictors consisted of patient history, physical exam, and radiological reports. Tabular predictors included age, creatinine, C-reactive protein, hemoglobin, and platelet count. TensorFlow tabular-textual model performance indices were compared to those of models implementing only tabular data. For 30-day mortality, the combined model yielded slightly better performances than the tabular fastai and XGBoost models, with AUC 0.87 ± 0.02, F1 score 0.62 ± 0.10 and an MCC 0.52 ± 0.04 (p < 0.32). As for ICU admission, the combined model MCC was superior (p < 0.024) to the tabular models. Our results suggest that a combined textual and tabular model can effectively predict COVID-19 prognosis which may assist ED physicians in their decision-making process.

Can Artificial Intelligence Enhance Syncope Management?: A JACC: Advances Multidisciplinary Collaborative Statement

Syncope, a form of transient loss of consciousness, remains a complex medical condition for which adverse cardiovascular outcomes, including death, are of major concern but rarely occur. Current risk stratification algorithms have not completely delineated which patients benefit from hospitalization and specific interventions. Patients are often admitted unnecessarily and at high cost. Artificial intelligence (AI) and machine learning may help define the transient loss of consciousness event, diagnose the cause, assess short- and long-term risks, predict recurrence, and determine need for hospitalization and therapeutic intervention; however, several challenges remain, including medicolegal and ethical concerns. This collaborative statement, from a multidisciplinary group of clinicians, investigators, and scientists, focuses on the potential role of AI in syncope management with a goal to inspire creation of AI-derived clinical decision support tools that may improve patient outcomes, streamline diagnostics, and reduce health-care costs.

Characteristics of Artificial Intelligence Clinical Trials in the Field of Healthcare: A Cross-Sectional Study on ClinicalTrials.gov

Artificial intelligence (AI) has driven innovative transformation in healthcare service patterns, despite a lack of understanding of its performance in clinical practice. We conducted a cross-sectional analysis of AI-related trials in healthcare based on ClinicalTrials.gov, intending to investigate the trial characteristics and AI's development status. Additionally, the Neo4j graph database and visualization technology were employed to construct an AI technology application graph, achieving a visual representation and analysis of research hotspots in healthcare AI. A total of 1725 eligible trials that were registered in ClinicalTrials.gov up to 31 March 2022 were included in this study. The number of trial registrations has dramatically grown each year since 2016. However, the AI-related trials had some design drawbacks and problems with poor-quality result reporting. The proportion of trials with prospective and randomized designs was insufficient, and most studies did not report results upon completion. Currently, most healthcare AI application studies are based on data-driven learning algorithms, covering various disease areas and healthcare scenarios. As few studies have publicly reported results on ClinicalTrials.gov, there is not enough evidence to support an assessment of AI's actual performance. The widespread implementation of AI technology in healthcare still faces many challenges and requires more high-quality prospective clinical validation.

Influence of artificial intelligence on the work design of emergency department clinicians a systematic literature review

Objective

This systematic literature review aims to demonstrate how Artificial Intelligence (AI) is currently used in emergency departments (ED) and how it alters the work design of ED clinicians. AI is still new and unknown to many healthcare professionals in emergency care, leading to unfamiliarity with its capabilities.

Method

Various criteria were used to establish the suitability of the articles to answer the research question. This study was based on 34 selected peer-reviewed papers on the use of Artificial Intelligence (AI) in the Emergency Department (ED), published in the last five years. Drawing on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, all articles were scanned, read full-text, and analyzed afterward.

Results

The majority of the AI applications consisted of AI-based tools to aid with clinical decisions and to relieve overcrowded EDs of their burden. AI support was mostly offered during triage, the moment that sets the patient trajectory. There is ample evidence that AI-based applications could improve the clinical decision-making process.

Conclusion

The use of AI in EDs is still in its nascent stages. Many studies focus on the question of whether AI has clinical utility, such as decision support, improving resource allocation, reducing diagnostic errors, and promoting proactivity. Some studies suggest that AI-based tools essentially have the ability to outperform human skills. However, it is evident from the literature that current technology does not have the aims or power to do so. Nevertheless, AI-based tools can impact clinician work design in the ED by providing support with clinical decisions, which could ultimately help alleviate a portion of the increasing clinical burden.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-022-08070-7.

Daily estimates of individual discharge likelihood with deep learning natural language processing in general medicine: a prospective and external validation study

Machine learning, in particular deep learning, may be able to assist in the prediction of the length of stay and timing of discharge for individual patients. Artificial neural networks applied to medical text have previously shown promise in this area. In this study, a previously derived artificial neural network was applied to prospective and external validation datasets. In the prediction of discharge within the next 2 days, when the algorithm was applied to prospective and external datasets, the area under the receiver operator curve for this task were 0.78 and 0.74, respectively. The performance in the prediction of discharge within the next 7 days was more limited (area under the receiver operator curve 0.68 and 0.67). This study has shown that in prospective and external validation datasets the previously derived deep learning algorithms have demonstrated moderate performance in the prediction of which patients will be discharged within the next 2 days. Future studies may seek to further refine or evaluate the effect of the implementation of such algorithms.

Risk stratification of syncope: Current syncope guidelines and beyond

Syncope is an alarming event carrying the possibility of serious outcomes, including sudden cardiac death (SCD). Therefore, immediate risk stratification should be applied whenever syncope occurs, especially in the Emergency Department, where most dramatic presentations occur. It has long been known that short- and long-term syncope prognosis is affected not only by its mechanism but also by presence of concomitant conditions, especially cardiovascular disease. Over the last two decades, several syncope prediction tools have been developed to refine patient stratification and triage patients who need expert in-hospital care from those who may receive nonurgent expert care in the community. However, despite promising results, prognostic tools for syncope remain challenging and often poorly effective. Current European Society of Cardiology syncope guidelines recommend an initial syncope workup based on detailed patient's history, physical examination supine and standing blood pressure, resting ECG, and laboratory tests, including cardiac biomarkers, where appropriate. Subsequent risk stratification based on screening of features aims to identify three groups: high-, intermediate- and low-risk. The first should immediately be hospitalized and appropriately investigated; intermediate group, with recurrent or medium-risk events, requires systematic evaluation by syncope experts; low-risk group, sporadic reflex syncope, merits education about its benign nature, and discharge. Thus, initial syncope risk stratification is crucial as it determines how and by whom syncope patients are managed. This review summarizes the crucial elements of syncope risk stratification, pros and cons of proposed risk evaluation scores, major challenges in initial syncope management, and how risk stratification impacts management of high-risk/recurrent syncope.

Neural networks and hospital length of stay: an application to support healthcare management with national benchmarks and thresholds

Background

The problem of correct inpatient scheduling is extremely significant for healthcare management. Extended length of stay can have negative effects on the supply of healthcare treatments, reducing patient accessibility and creating missed opportunities to increase hospital revenues by means of other treatments and additional hospitalizations.

Methods

Adopting available national reference values and focusing on a Department of Internal and Emergency Medicine located in the North-West of Italy, this work assesses prediction models of hospitalizations with length of stay longer than the selected benchmarks and thresholds. The prediction models investigated in this case study are based on Artificial Neural Networks and examine risk factors for prolonged hospitalizations in 2018. With respect current alternative approaches (e.g., logistic models), Artificial Neural Networks give the opportunity to identify whether the model will maximize specificity or sensitivity.

Results

Our sample includes administrative data extracted from the hospital database, collecting information on more than 16,000 hospitalizations between January 2018 and December 2019. Considering the overall department in 2018, 40% of the hospitalizations lasted more than the national average, and almost 3.74% were outliers (i.e., they lasted more than the threshold). According to our results, the adoption of the prediction models in 2019 could reduce the average length of stay by up to 2 days, guaranteeing more than 2000 additional hospitalizations in a year.

Conclusions

The proposed models might represent an effective tool for administrators and medical professionals to predict the outcome of hospital admission and design interventions to improve hospital efficiency and effectiveness.

Mixed-data deep learning in repeated predictions of general medicine length of stay: a derivation study

The accurate prediction of likely discharges and estimates of length of stay (LOS) aid in effective hospital administration and help to prevent access block. Machine learning (ML) may be able to help with these tasks. For consecutive patients admitted under General Medicine at the Royal Adelaide Hospital over an 8-month period, daily ward round notes and relevant discrete data fields were collected from the electronic medical record. These data were then split into training and testing sets (7-month/1-month train/test split) prior to use in ML analyses aiming to predict discharge within the next 2 days, discharge within the next 7 days and an estimated date of discharge (EDD). Artificial neural networks and logistic regression were effective at predicting discharge within 48 h of a given ward round note. These models achieved an area under the receiver operator curve (AUC) of 0.80 and 0.78, respectively. Prediction of discharge within 7 days of a given note was less accurate, with artificial neural network returning an AUC of 0.68 and logistic regression an AUC of 0.61. The generation of an exact EDD remains inaccurate. This study has shown that repeated estimates of LOS using daily ward round notes and mixed-data inputs are effective in the prediction of general medicine discharges in the next 48 h. Further research may seek to prospectively and externally validate models for prediction of upcoming discharge, as well as combination human-ML approaches for generating EDDs.

Machine Learning and Syncope Management in the ED: The Future Is Coming

In recent years, machine learning (ML) has been promisingly applied in many fields of clinical medicine, both for diagnosis and prognosis prediction. Aims of this narrative review were to summarize the basic concepts of ML applied to clinical medicine and explore its main applications in the emergency department (ED) setting, with a particular focus on syncope management. Through an extensive literature search in PubMed and Embase, we found increasing evidence suggesting that the use of ML algorithms can improve ED triage, diagnosis, and risk stratification of many diseases. However, the lacks of external validation and reliable diagnostic standards currently limit their implementation in clinical practice. Syncope represents a challenging problem for the emergency physician both because its diagnosis is not supported by specific tests and the available prognostic tools proved to be inefficient. ML algorithms have the potential to overcome these limitations and, in the future, they could support the clinician in managing syncope patients more efficiently. However, at present only few studies have addressed this issue, albeit with encouraging results.

Short vs long-course antibiotic therapy in pyelonephritis: a comparison of systematic reviews and guidelines for the SIMI choosing wisely campaign

BACKGROUND

The Italian Society of Internal Medicine (SIMI) Choosing Wisely Campaign has recently proposed, among its five items, to reduce the prescription of long-term intravenous antibiotics if not indicated. The aim of our study was to assess the available evidences on optimal duration of antibiotic treatment in pyelonephritis through a systematic review of secondary studies.

MATERIALS AND METHODS

We searched for all guidelines on pyelonephritis and systematic reviews assessing the optimal duration of antibiotic therapy in this type of infection. We compared the recommendations of the three most cited and recent guidelines on the topic of interest. We extracted data of non-duplicated RCT from the selected systematic reviews and performed meta-analyses for clinical and microbiological failure. A trial sequential analysis (TSA) was also achieved to identify the need for further evidence.

RESULTS

We identified 4 systematic reviews, including data from 10 non-duplicated RCTs (1536 patients). The meta-analysis showed a higher rate of clinical cure for short-course antibiotic treatment (RR for clinical failure 0.70, 95% CI [0.53-0.94]). No significant difference in the rate of microbiological failure (RR 1.06, 95% CI [0.75-1.49]) was observed. In terms of clinical cure, the TSA suggests that current evidence is sufficient to consider short course at least as effective as long-course treatment. Selected guidelines recommend considering shorter courses, but do not cite most of the published RCTs.

CONCLUSIONS

Short-course antibiotic treatment is at least as effective as longer courses for both microbiological and clinical success in the treatment of acute uncomplicated pyelonephritis.

Analysis of Hemorrhagic Fever With Renal Syndrome Using Wavelet Tools in Mainland China, 2004-2019

Introduction : Hemorrhagic fever with renal syndrome (HFRS) is a life-threatening public health problem in China, accounting for ~90% of HFRS cases reported globally. Accurate analysis and prediction of the HFRS epidemic could help to establish effective preventive measures.

Materials and Methods : In this study, the geographical information system (GIS) explored the spatiotemporal features of HFRS, the wavelet power spectrum (WPS) unfolded the cyclical fluctuation of HFRS, and the wavelet neural network (WNN) model predicted the trends of HFRS outbreaks in mainland China.

Results : A total of 209,209 HFRS cases were reported in mainland China from 2004 to 2019, with the annual incidence ranged from 0 to 13.05 per 100,0000 persons at the province level. The WPS proved that the periodicity of HFRS could be half a year, 1 year, and roughly 7-year at different time intervals. The WNN structure of 12-6-1 was set up as the fittest forecasting model for the HFRS epidemic.

Conclusions : This study provided several potential support tools for the control and risk-management of HFRS in China.

Phased genome sequence of an interspecific hybrid flowering cherry, 'Somei-Yoshino' (Cerasus × yedoensis)

We report the phased genome sequence of an interspecific hybrid, the flowering cherry ‘Somei-Yoshino’ (Cerasus × yedoensis). The sequence data were obtained by single-molecule real-time sequencing technology, split into two subsets based on genome information of the two probable ancestors, and assembled to obtain two haplotype phased genome sequences of the interspecific hybrid. The resultant genome assembly consisting of the two haplotype sequences spanned 690.1 Mb with 4,552 contigs and an N50 length of 1.0 Mb. We predicted 95,076 high-confidence genes, including 94.9% of the core eukaryotic genes. Based on a high-density genetic map, we established a pair of eight pseudomolecule sequences, with highly conserved structures between the two haplotype sequences with 2.4 million sequence variants. A whole genome resequencing analysis of flowering cherries suggested that ‘Somei-Yoshino’ might be derived from a cross between C. spachiana and either C. speciosa or its relatives. A time-course transcriptome analysis of floral buds and flowers suggested comprehensive changes in gene expression in floral bud development towards flowering. These genome and transcriptome data are expected to provide insights into the evolution and cultivation of flowering cherry and the molecular mechanism underlying flowering.