Engaging Multidisciplinary Clinical Users in the Design of an Artificial Intelligence-Powered Graphical User Interface for Intensive Care Unit Instability Decision Support.

BACKGROUND: Critical instability forecast and treatment can be optimized by artificial intelligence (AI)-enabled clinical decision support. It is important that the user-facing display of AI output facilitates clinical thinking and workflow for all disciplines involved in bedside care. OBJECTIVES: Our objective is to engage multidisciplinary users (physicians, nurse practitioners, physician assistants) in the development of a graphical user interface (GUI) to present an AI-derived risk score. METHODS: Intensive care unit (ICU) clinicians participated in focus groups seeking input on instability risk forecast presented in a prototype GUI. Two stratified rounds (three focus groups [only nurses, only providers, then combined]) were moderated by a focus group methodologist. After round 1, GUI design changes were made and presented in round 2. Focus groups were recorded, transcribed, and deidentified transcripts independently coded by three researchers. Codes were coalesced into emerging themes. RESULTS: Twenty-three ICU clinicians participated (11 nurses, 12 medical providers [3 mid-level and 9 physicians]). Six themes emerged: (1) analytics transparency, (2) graphical interpretability, (3) impact on practice, (4) value of trend synthesis of dynamic patient data, (5) decisional weight (weighing AI output during decision-making), and (6) display location (usability, concerns for patient/family GUI view). Nurses emphasized having GUI objective information to support communication and optimal GUI location. While providers emphasized need for recommendation interpretability and concern for impairing trainee critical thinking. All disciplines valued synthesized views of vital signs, interventions, and risk trends but were skeptical of placing decisional weight on AI output until proven trustworthy. CONCLUSION: Gaining input from all clinical users is important to consider when designing AI-derived GUIs. Results highlight that health care intelligent decisional support systems technologies need to be transparent on how they work, easy to read and interpret, cause little disruption to current workflow, as well as decisional support components need to be used as an adjunct to human decision-making.

Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction.

Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting electrocardiogram (ECG) are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but, currently, there are no accurate tools to identify them during initial triage. Here we report, to our knowledge, the first observational cohort study to develop machine learning models for the ECG diagnosis of OMI. Using 7,313 consecutive patients from multiple clinical sites, we derived and externally validated an intelligent model that outperformed practicing clinicians and other widely used commercial interpretation systems, substantially boosting both precision and sensitivity. Our derived OMI risk score provided enhanced rule-in and rule-out accuracy relevant to routine care, and, when combined with the clinical judgment of trained emergency personnel, it helped correctly reclassify one in three patients with chest pain. ECG features driving our models were validated by clinical experts, providing plausible mechanistic links to myocardial injury.

Developmental care pathway for hospitalised infants with CHD: on behalf of the Cardiac Newborn Neuroprotective Network, a Special Interest Group of the Cardiac Neurodevelopmental Outcome Collaborative.

Infants and children born with CHD are at significant risk for neurodevelopmental delays and abnormalities. Individualised developmental care is widely recognised as best practice to support early neurodevelopment for medically fragile infants born premature or requiring surgical intervention after birth. However, wide variability in clinical practice is consistently demonstrated in units caring for infants with CHD. The Cardiac Newborn Neuroprotective Network, a Special Interest Group of the Cardiac Neurodevelopmental Outcome Collaborative, formed a working group of experts to create an evidence-based developmental care pathway to guide clinical practice in hospital settings caring for infants with CHD. The clinical pathway, "Developmental Care Pathway for Hospitalized Infants with Congenital Heart Disease," includes recommendations for standardised developmental assessment, parent mental health screening, and the implementation of a daily developmental care bundle, which incorporates individualised assessments and interventions tailored to meet the needs of this unique infant population and their families. Hospitals caring for infants with CHD are encouraged to adopt this developmental care pathway and track metrics and outcomes using a quality improvement framework.

Machine Learning for the ECG Diagnosis and Risk Stratification of Occlusion Myocardial Infarction at First Medical Contact.

Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting ECG are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but we currently have no accurate tools to identify them during initial triage. Herein, we report the first observational cohort study to develop machine learning models for the ECG diagnosis of OMI. Using 7,313 consecutive patients from multiple clinical sites, we derived and externally validated an intelligent model that outperformed practicing clinicians and other widely used commercial interpretation systems, significantly boosting both precision and sensitivity. Our derived OMI risk score provided superior rule-in and rule-out accuracy compared to routine care, and when combined with the clinical judgment of trained emergency personnel, this score helped correctly reclassify one in three patients with chest pain. ECG features driving our models were validated by clinical experts, providing plausible mechanistic links to myocardial injury.

Engaging clinicians early during the development of a graphical user display of an intelligent alerting system at the bedside.

BACKGROUND: Artificial Intelligence (AI) is increasingly used to support bedside clinical decisions, but information must be presented in usable ways within workflow. Graphical User Interfaces (GUI) are front-facing presentations for communicating AI outputs, but clinicians are not routinely invited to participate in their design, hindering AI solution potential. PURPOSE: To inform early user-engaged design of a GUI prototype aimed at predicting future Cardiorespiratory Insufficiency (CRI) by exploring clinician methods for identifying at-risk patients, previous experience with implementing new technologies into clinical workflow, and user perspectives on GUI screen changes. METHODS: We conducted a qualitative focus group study to elicit iterative design feedback from clinical end-users on an early GUI prototype display. Five online focus group sessions were held, each moderated by an expert focus group methodologist. Iterative design changes were made sequentially, and the updated GUI display was presented to the next group of participants. RESULTS: 23 clinicians were recruited (14 nurses, 4 nurse practitioners, 5 physicians; median participant age ∼35 years; 60% female; median clinical experience 8 years). Five themes emerged from thematic content analysis: trend evolution, context (risk evolution relative to vital signs and interventions), evaluation/interpretation/explanation (sub theme: continuity of evaluation), clinician intuition, and clinical operations. Based on these themes, GUI display changes were made. For example, color and scale adjustments, integration of clinical information, and threshold personalization. CONCLUSIONS: Early user-engaged design was useful in adjusting GUI presentation of AI output. Next steps involve clinical testing and further design modification of the AI output to optimally facilitate clinician surveillance and decisions. Clinicians should be involved early and often in clinical decision support design to optimize efficacy of AI tools.

Your neighborhood matters: A machine-learning approach to the geospatial and social determinants of health in 9-1-1 activated chest pain.

Healthcare disparities in the initial management of patients with acute coronary syndrome (ACS) exist. Yet, the complexity of interactions between demographic, social, economic, and geospatial determinants of health hinders incorporating such predictors in existing risk stratification models. We sought to explore a machine-learning-based approach to study the complex interactions between the geospatial and social determinants of health to explain disparities in ACS likelihood in an urban community. This study identified consecutive patients transported by Pittsburgh emergency medical service for a chief complaint of chest pain or ACS-equivalent symptoms. We extracted demographics, clinical data, and location coordinates from electronic health records. Median income was based on US census data by zip code. A random forest (RF) classifier and a regularized logistic regression model were used to identify the most important predictors of ACS likelihood. Our final sample included 2400 patients (age 59 ± 17 years, 47% Females, 41% Blacks, 15.8% adjudicated ACS). In our RF model (area under the receiver operating characteristic curve of 0.71 ± 0.03) age, prior revascularization, income, distance from hospital, and residential neighborhood were the most important predictors of ACS likelihood. In regularized regression (akaike information criterion = 1843, bayesian information criterion = 1912, χ2 = 193, df = 10, p < 0.001), residential neighborhood remained a significant and independent predictor of ACS likelihood. Findings from our study suggest that residential neighborhood constitutes an upstream factor to explain the observed healthcare disparity in ACS risk prediction, independent from known demographic, social, and economic determinants of health, which can inform future work on ACS prevention, in-hospital care, and patient discharge.

The role of machine learning applications in diagnosing and assessing critical and non-critical CHD: a scoping review.

Machine learning uses historical data to make predictions about new data. It has been frequently applied in healthcare to optimise diagnostic classification through discovery of hidden patterns in data that may not be obvious to clinicians. Congenital Heart Defect (CHD) machine learning research entails one of the most promising clinical applications, in which timely and accurate diagnosis is essential. The objective of this scoping review is to summarise the application and clinical utility of machine learning techniques used in paediatric cardiology research, specifically focusing on approaches aiming to optimise diagnosis and assessment of underlying CHD. Out of 50 full-text articles identified between 2015 and 2021, 40% focused on optimising the diagnosis and assessment of CHD. Deep learning and support vector machine were the most commonly used algorithms, accounting for an overall diagnostic accuracy > 0.80. Clinical applications primarily focused on the classification of auscultatory heart sounds, transthoracic echocardiograms, and cardiac MRIs. The range of these applications and directions of future research are discussed in this scoping review.

Performance and limitations of automated ECG interpretation statements in patients with suspected acute coronary syndrome.

BACKGROUND: The 12­lead ECG plays an important role in triaging patients with symptomatic coronary artery disease, making automated ECG interpretation statements of "Acute MI" or "Acute Ischemia" crucial, especially during prehospital transport when access to physician interpretation of the ECG is limited. However, it remains unknown how automated interpretation statements correspond to adjudicated clinical outcomes during hospitalization. We sought to evaluate the diagnostic performance of prehospital automated interpretation statements to four well-defined clinical outcomes of interest: confirmed ST- segment elevation myocardial infarction (STEMI); presence of actionable coronary culprit lesions, myocardial necrosis, or any acute coronary syndrome (ACS). METHODS: An observational cohort study that enrolled consecutive patients with non-traumatic chest pain transported via ambulance. Prehospital ECGs were obtained with the Philips MRX monitor from the medical command center and re-processed using manufacturer-specific diagnostic algorithms to denote the likelihood of >>>Acute MI<<< or >>>Acute Ischemia<<<. Two independent reviewers retrospectively adjudicated the study outcomes and disagreements were resolved by a third reviewer. RESULTS: Our study included 2400 patients (age 59 ± 16, 47% females, 41% Black), with 190 (8%) patients with documented automated diagnostic statements of acute MI or acute ischemia. The sensitivity/specificity of the automated algorithm for detecting confirmed STEMI (n = 143, 6%); presence of actionable coronary culprit lesions (n = 258, 11%), myocardial necrosis (n = 291, 12%), or any ACS (n = 378, 16%) were 62.9%/95.6%; 37.2%/95.6%; 38.5%/96.4%; and 30.7%/96.3%, respectively. CONCLUSION: Although being very specific, automated interpretation statements of acute MI/acute ischemia on prehospital ECGs are not satisfactorily sensitive to exclude symptomatic coronary disease. Patients without these automated interpretation statements should be considered further for significant underlying coronary disease based on the clinical context. TRIAL REGISTRATION: ClinicalTrials.gov # NCT04237688.

Novel ECG features and machine learning to optimize culprit lesion detection in patients with suspected acute coronary syndrome.

BACKGROUND: Novel temporal-spatial features of the 12­lead ECG can conceptually optimize culprit lesions' detection beyond that of classical ST amplitude measurements. We sought to develop a data-driven approach for ECG feature selection to build a clinically relevant algorithm for real-time detection of culprit lesion. METHODS: This was a prospective observational cohort study of chest pain patients transported by emergency medical services to three tertiary care hospitals in the US. We obtained raw 10-s, 12­lead ECGs (500 s/s, HeartStart MRx, Philips Healthcare) during prehospital transport and followed patients 30 days after the encounter to adjudicate clinical outcomes. A total of 557 global and lead-specific features of P-QRS-T waveform were harvested from the representative average beats. We used Recursive Feature Elimination and LASSO to identify 35/557, 29/557, and 51/557 most recurrent and important features for LAD, LCX, and RCA culprits, respectively. Using the union of these features, we built a random forest classifier with 10-fold cross-validation to predict the presence or absence of culprit lesions. We compared this model to the performance of a rule-based commercial proprietary software (Philips DXL ECG Algorithm). RESULTS: Our sample included 2400 patients (age 59 ± 16, 47% female, 41% Black, 10.7% culprit lesions). The area under the ROC curves of our random forest classifier was 0.85 ± 0.03 with sensitivity, specificity, and negative predictive value of 71.1%, 84.7%, and 96.1%. This outperformed the accuracy of the automated interpretation software of 37.2%, 95.6%, and 92.7%, respectively, and corresponded to a net reclassification improvement index of 23.6%. Metrics of ST80; Tpeak-Tend; spatial angle between QRS and T vectors; PCA ratio of STT waveform; T axis; and QRS waveform characteristics played a significant role in this incremental gain in performance. CONCLUSIONS: Novel computational features of the 12­lead ECG can be used to build clinically relevant machine learning-based classifiers to detect culprit lesions, which has important clinical implications.

Holding and Mobility of Pediatric Patients With Transthoracic Intracardiac Catheters.

BACKGROUND: Nursing care of pediatric patients after cardiac surgery consists of close hemodynamic monitoring, often through transthoracic intracardiac catheters, requiring patients to remain on bed rest and limiting holding and mobility. OBJECTIVES: The primary aim of this quality improvement project was to determine the feasibility of safely mobilizing pediatric patients with transthoracic intracardiac catheters out of bed. Once feasibility was established, the secondary aim was to increase the number of days such patients were out of bed. METHODS AND INTERVENTIONS: New standards and procedures were implemented in July 2015 for pediatric patients with transthoracic intracardiac catheters. After initiation of the new policies, complications were tracked prospectively. Nursing documentation of activity and positioning for all patients with transthoracic intracardiac catheters was extracted from electronic health records for 2 fiscal years before and 3 fiscal years after the new policies were implemented. The Cochran-Armitage test for trend was used to determine whether patterns of out-of-bed documentation changed over time. RESULTS: A total of 1358 patients (approximately 250 to 300 patients each fiscal year) had activity and positioning documented while transthoracic intracardiac catheters were in place. The Cochran-Armitage test for trend revealed that out-of-bed documentation significantly increased after the new policies and procedures were initiated (P < .001). No major complications were noted resulting from patient mobility with transthoracic intracardiac catheters. CONCLUSION: Pediatric patients with transthoracic intracardiac catheters can be safely held and mobilized out of bed.

Nursing Practice With Transthoracic Intracardiac Catheters in Children: International Benchmarking Study.

BACKGROUND: Transthoracic intracardiac catheters are central catheters placed in the operating room at the conclusion of cardiac surgery for infants and children. Complications associated with these catheters (eg, bleeding, migration, premature removal, infection, leakage, and lack of function) have been described. However, no researchers have addressed the nursing management of these catheters in the intensive care unit, including catheter dressing and securement, mobilization of patients, and flushing the catheters, or the impact of these interventions on patients' outcomes. OBJECTIVES: To internationally benchmark current nursing practice associated with care of infants and children with transthoracic intracardiac catheters. METHODS: In a cross-sectional, descriptive study of nursing practice in infants and children with transthoracic intracardiac catheters, a convenience sample of bedside and advanced practice nurses was recruited to complete an online survey to benchmark current practice. The survey included questions on criteria for catheter insertion and removal, dressing care, flushing practice, securement, and mobilization of patients. RESULTS: Transthoracic intracardiac catheters are used by most centers that provide care for infants and children after open heart surgery. A wide range of practices was reported. CONCLUSIONS: Standardizing the use and care of transthoracic intracardiac catheters can improve the safety and efficacy of their use in infants and children and promote safe and early postoperative mobilization of patients.

Quality Over Quantity: Standardization of Pediatric HeartWare Ventricular Assist Device Dressing Changes.

Pediatric patients are unique both in their diagnosis and clinical presentation before implantation of a ventricular assist device (VAD) and in their driveline site characteristics post-implant. There is limited evidence in scholarly literature that describes complications of pediatric VAD driveline sites or approaches by which to manage them. The Cardiac Center at The Children's Hospital of Philadelphia (CHOP) follows a standard of care for HeartWare VAD (HVAD) dressing changes in the inpatient setting with the goal of transitioning patients to weekly dressing changes by the time they are discharged to home. As a patient with an HVAD nears discharge, members of an interprofessional team collaborate with insurance providers and home care agencies to procure the appropriate supplies needed at home. Individualized plans of care are necessary for patients who are unable to transition to weekly dressings; however, customized products (such as silicone foam border dressings and antimicrobial agents) may be challenging to supply as single items from home care agencies. Between March 2014 and June 2017, 15 patients underwent HVAD implantation, and eight (53%) were discharged home. Ten patients (67%) were able to transition to weekly dressing changes. Individualized plans of care for driveline site management were required for six (40%) patients with persistent drainage. Three patients (20%) experienced a driveline site infection. This article describes how a quality improvement (QI) initiative using rapid-cycle improvement methodology was executed to standardize HVAD dressing changes in our pediatric population.

Reducing Ischemic Injury From Indwelling Peripheral Arterial Catheters in a Pediatric Cardiac ICU: A Quality Improvement Initiative.

OBJECTIVES: To reduce the number of ischemic arterial catheter injuries in children with congenital or acquired heart disease. DESIGN: This is a quality improvement study with pre- and postintervention groups. SETTING: University-affiliated pediatric cardiac center in a quaternary care freestanding children's hospital. PATIENTS: All patients with an indwelling peripheral arterial catheter placed in the Children's Hospital of Philadelphia Cardiac Center associated with an admission to the Cardiac Intensive Cardiac Unit from January 2015 to July 2017 are included. Patients with umbilical arterial catheters were excluded from the cohort. The rate of arterial catheter injury is reported per 1,000 catheter days. The rate of "concerning" arterial catheter assessments is reported as a percentage of catheters per month. INTERVENTION: Initial intervention replaced intermittent manual arterial catheter flushing with a continuous arterial catheter infusion system during the delivery of anesthesia. The second intervention implemented a daily arterial catheter safety assessment during cardiac ICU rounds with documentation of the assessment in the cardiac ICU daily attending progress note. MEASUREMENTS AND MAIN RESULTS: Our project included 1,945 arterial catheters encompassing 7,197 catheter days. During the preintervention period, on average, 3.1 patients per month experienced an arterial catheter-related injury compared with 1.9 patients per month following intervention, a reduction of 38.7% (3.1 vs 1.9; p = 0.01). The rate of injury per 1,000 arterial catheter days was reduced from 16.7 pre intervention to 7.52 post intervention, a 55% overall reduction (16.7 vs 7.52; p = 0.0001). The rate of concerning arterial catheter nursing assessment based on our definition was reduced by 18.0% following our intervention cycles (25.5% vs 20.9%; p = 0.001) CONCLUSIONS:: Implementation of a quality improvement initiative and changing local practices reduced arterial catheter-associated harm in children with congenital and acquired heart disease requiring care in a cardiac ICU.

Just-in-Time Training for High-Risk Low-Volume Therapies: An Approach to Ensure Patient Safety.

High-risk low-volume therapies are those therapies that are practiced infrequently and yet carry an increased risk to patients because of their complexity. Staff nurses are required to competently manage these therapies to treat patients' unique needs and optimize outcomes; however, maintaining competence is challenging. This article describes implementation of Just-in-Time Training, which requires validation of minimum competency of bedside nurses managing high-risk low-volume therapies through direct observation of a return-demonstration competency checklist.

Implementation of a screening, brief intervention, and referral to treatment program using the electronic medical record in a pediatric trauma center.

The purpose of this project was to develop and implement a consistent process for (1) screening adolescents by history for alcohol and substance abuse and (2) providing a motivational interview for change and appropriate referrals as needed. In the 18 months since we implemented the program, 534 patients were eligible for screening. Of these, 442 actually underwent screening and of these, 32 screened positive, thus receiving a brief intervention by social work and referral for further treatment. Use of the electronic medical record was key to the implementation and sustainability of this project.