Dynamic Prediction of Patient Outcomes in the Intensive Care Unit: A Scoping Review of the State-of-the-Art.

INTRODUCTION: Intensive care units (ICUs) are high-pressure, complex, technology-intensive medical environments where patient physiological data are generated continuously. Due to the complexity of interpreting multiple signals at speed, there are substantial opportunities and significant potential benefits in providing ICU staff with additional decision support and predictive modeling tools that can support and aid decision-making in real-time.This scoping review aims to synthesize the state-of-the-art dynamic prediction models of patient outcomes developed for use in the ICU. We define "dynamic" models as those where predictions are regularly computed and updated over time in response to updated physiological signals. METHODS: Studies describing the development of predictive models for use in the ICU were searched, using PubMed. The studies were screened as per Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines, and the data regarding predicted outcomes, methods used to develop the predictive models, preprocessing the data and dealing with missing values, and performance measures were extracted and analyzed. RESULTS: A total of n = 36 studies were included for synthesis in our review. The included studies focused on the prediction of various outcomes, including mortality (n = 17), sepsis-related complications (n = 12), cardiovascular complications (n = 5), and other complications (respiratory, renal complications, and bleeding, n = 5). The most common classification methods include logistic regression, random forest, support vector machine, and neural networks. CONCLUSION: The included studies demonstrated that there is a strong interest in developing dynamic prediction models for various ICU patient outcomes. Most models reported focus on mortality. As such, the development of further models focusing on a range of other serious and well-defined complications-such as acute kidney injury-would be beneficial. Furthermore, studies should improve the reporting of key aspects of model development challenges.

Decision Support Tools in Adult Long-term Care Facilities: Scoping Review.

BACKGROUND: Digital innovations are yet to make real impacts in the care home sector despite the considerable potential of digital health approaches to help with continued staff shortages and to improve quality of care. To understand the current landscape of digital innovation in long-term care facilities such as nursing and care homes, it is important to find out which clinical decision support tools are currently used in long-term care facilities, what their purpose is, how they were developed, and what types of data they use. OBJECTIVE: The aim of this review was to analyze studies that evaluated clinical decision support tools in long-term care facilities based on the purpose and intended users of the tools, the evidence base used to develop the tools, how the tools are used and their effectiveness, and the types of data the tools use to contribute to the existing scientific evidence to inform a roadmap for digital innovation, specifically for clinical decision support tools, in long-term care facilities. METHODS: A review of the literature published between January 1, 2010, and July 21, 2021, was conducted, using key search terms in 3 scientific journal databases: PubMed, Cochrane Library, and the British Nursing Index. Only studies evaluating clinical decision support tools in long-term care facilities were included in the review. RESULTS: In total, 17 papers were included in the final review. The clinical decision support tools described in these papers were evaluated for medication management, pressure ulcer prevention, dementia management, falls prevention, hospitalization, malnutrition prevention, urinary tract infection, and COVID-19 infection. In general, the included studies show that decision support tools can show improvements in delivery of care and in health outcomes. CONCLUSIONS: Although the studies demonstrate the potential of positive impact of clinical decision support tools, there is variability in results, in part because of the diversity of types of decision support tools, users, and contexts as well as limited validation of the tools in use and in part because of the lack of clarity in defining the whole intervention.

Decision Support in Cardiac Surgery: Early Exploration of Requirements with Cardiac Anesthetists and Surgeons.

Successful implementation of clinical decision support tools is rare, the key barrier being the lack of user involvement during development. Following the idea, development, exploration, assessment, long-term follow-up (IDEAL) framework, this study aims to provide early insights into the current challenges, clinical processes, and priorities when developing new decision support tools in cardiac surgery. Using a qualitative approach, semi-structured interviews were conducted with cardiac anesthetists and surgeons from three Scottish cardiac centers. Thematic analysis identified adverse postoperative outcomes, ageing cardiac patient population and changing surgical procedures to be the main challenges in cardiac surgery. Existing risk prediction tools were largely not used due to a perceived lack of utility and validation. This study underscores the need to shift focus towards predicting postoperative complications, instead of mortality. It emphasizes the importance of early collaboration with clinical experts and stakeholders in developing decision support systems that are fit for purpose. By identifying the priorities of cardiac clinicians, the study lays the groundwork for developing clinically meaningful prediction models.

Predictive Data Analytics in Telecare and Telehealth: Systematic Scoping Review.

BACKGROUND: Telecare and telehealth are important care-at-home services used to support individuals to live more independently at home. Historically, these technologies have reactively responded to issues. However, there has been a recent drive to make better use of the data from these services to facilitate more proactive and predictive care. OBJECTIVE: This review seeks to explore the ways in which predictive data analytics techniques have been applied in telecare and telehealth in at-home settings. METHODS: The PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist was adhered to alongside Arksey and O'Malley's methodological framework. English language papers published in MEDLINE, Embase, and Social Science Premium Collection between 2012 and 2022 were considered and results were screened against inclusion or exclusion criteria. RESULTS: In total, 86 papers were included in this review. The types of analytics featuring in this review can be categorized as anomaly detection (n=21), diagnosis (n=32), prediction (n=22), and activity recognition (n=11). The most common health conditions represented were Parkinson disease (n=12) and cardiovascular conditions (n=11). The main findings include: a lack of use of routinely collected data; a dominance of diagnostic tools; and barriers and opportunities that exist, such as including patient-reported outcomes, for future predictive analytics in telecare and telehealth. CONCLUSIONS: All papers in this review were small-scale pilots and, as such, future research should seek to apply these predictive techniques into larger trials. Additionally, further integration of routinely collected care data and patient-reported outcomes into predictive models in telecare and telehealth offer significant opportunities to improve the analytics being performed and should be explored further. Data sets used must be of suitable size and diversity, ensuring that models are generalizable to a wider population and can be appropriately trained, validated, and tested.

Development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basis.

Objectives: To develop and validate a digital biomarker for predicting the onset of acute kidney injury (AKI) on an hourly basis up to 24 hours in advance in the intensive care unit after cardiac surgery. Methods: The study analyzed data from 6056 adult patients undergoing coronary artery bypass graft and/or valve surgery between April 1, 2012, and December 31, 2018 (development phase, training, and testing) and 3572 patients between January 1, 2019, and June 30, 2022 (validation phase). The study used 2 dynamic predictive modeling approaches, namely logistic regression and bootstrap aggregated regression trees machine (BARTm), to predict AKI. The mean area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive and negative predictive values across all lead times before the occurrence of AKI were reported. The clinical practicality was assessed using calibration. Results: Of all included patients, 8.45% and 16.66% had AKI in the development and validation phases, respectively. When applied to testing data, AKI was predicted with the mean AUC of 0.850 and 0.802 by BARTm and logistic regression, respectively. When applied to validation data, BARTm and LR resulted in a mean AUC of 0.844 and 0.786, respectively. Conclusions: This study demonstrated the successful prediction of AKI on an hourly basis up to 24 hours in advance. The digital biomarkers developed and validated in this study have the potential to assist clinicians in optimizing treatment and implementing preventive strategies for patients at risk of developing AKI after cardiac surgery in the intensive care unit.

Definition and Classification of Postoperative Complications After Cardiac Surgery: Pilot Delphi Study.

BACKGROUND: Postoperative complications following cardiac surgery are common and represent a serious burden to health services and society. However, there is a lack of consensus among experts on what events should be considered as a "complication" and how to assess their severity. OBJECTIVE: This study aimed to consult domain experts to pilot the development of a definition and classification system for complications following cardiac surgery with the goal to allow the progression of standardized clinical processes and systems in cardiac surgery. METHODS: We conducted a Delphi study, which is a well-established method to reach expert consensus on complex topics. We sent 2 rounds of surveys to domain experts, including cardiac surgeons and anesthetists, to define and classify postoperative complications following cardiac surgery. The responses to open-ended questions were analyzed using a thematic analysis framework. RESULTS: In total, 71 and 37 experts' opinions were included in the analysis in Round 1 and Round 2 of the study, respectively. Cardiac anesthetists and cardiac critical care specialists took part in the study. Cardiac surgeons did not participate. Experts agreed that a classification for postoperative complications for cardiac surgery is useful, and consensus was reached for the generic definition of a postoperative complication in cardiac surgery. Consensus was also reached on classification of complications according to the following 4 levels: "Mild," "Moderate," "Severe," and "Death." Consensus was also reached on definitions for "Mild" and "Severe" categories of complications. CONCLUSIONS: Domain experts agreed on the definition and classification of complications in cardiac surgery for "Mild" and "Severe" complications. The standardization of complication identification, recording, and reporting in cardiac surgery should help the development of quality benchmarks, clinical audit, care quality assessment, resource planning, risk management, communication, and research.