Using informatics to improve healthcare quality.

PURPOSE: The purpose of this paper is to provide insights into contemporary challenges associated with applying informatics and big data to healthcare quality improvement. DESIGN/METHODOLOGY/APPROACH: This paper is a narrative literature review. FINDINGS: Informatics serve as a bridge between big data and its applications, which include artificial intelligence, predictive analytics and point-of-care clinical decision making. Healthcare investment returns, measured by overall population health, healthcare operation efficiency and quality, are currently considered to be suboptimal. The challenges posed by informatics/big data span a wide spectrum from individual patients to government/regulatory agencies and healthcare providers. PRACTICAL IMPLICATIONS: The paper utilizes informatics and big data to improve population health and healthcare quality improvement. ORIGINALITY/VALUE: Informatics and big data utilization have the potential to improve population health and service quality. This paper discusses the challenges posed by these methods as the author strives to achieve the aims.

Prevalence and long-term prognosis of patients with complete bundle branch block (right or left bundle branch) with normal left ventricular ejection fraction referred for stress echocardiography.

BACKGROUND: The prognostic value of stress echocardiography (SE) in patients with complete bundle branch blocks (BBB) with normal left ventricular ejection fraction (LVEF) has not been well described. We sought to determine the prognostic value of SE in patients with BBB and normal LVEF. METHODS: We analyzed 7214 patients (58 ± 14 years; 57% female) with a mean follow-up time of 9 ± 4 years. Dobutamine SE was performed in 51% of patients and exercise SE was performed in 49%. All-cause mortality data were obtained from the Social Security Death Index. RESULTS: There were 222 (3%) patients with right bundle branch block (RBBB) and 50 (0.7%) patients with left bundle branch block (LBBB). Patients with LBBB were 3 times more likely to have an abnormal stress test after adjusting for age, gender, mode of stress test, and coronary artery disease risk factors (OR = 3.3; 95% CI: 1.86-5.92; P < 0.001). The mortality rates were 4.5%/year for patients with LBBB, 2.5%/year for patients with RBBB, and 1.9%/year for patients without BBB (P < 0.001). Among patients with a normal SE, those with LBBB had similar mortality to those without LBBB (HR = 0.9; 95% CI: 0.4-2.2; P = 0.8). Patients with LBBB and abnormal SE had more than 2 times greater risk of all-cause mortality (HR = 2.4; 95% CI: 1.4-4.2; P = 0.002). CONCLUSION: A normal stress echocardiogram in LBBB is associated with benign prognosis while those with LBBB and abnormal SE have the worst outcomes.

The Need to Prioritize Model-Updating Processes in Clinical Artificial Intelligence (AI) Models: Protocol for a Scoping Review.

BACKGROUND: With an increase in the number of artificial intelligence (AI) and machine learning (ML) algorithms available for clinical settings, appropriate model updating and implementation of updates are imperative to ensure applicability, reproducibility, and patient safety. OBJECTIVE: The objective of this scoping review was to evaluate and assess the model-updating practices of AI and ML clinical models that are used in direct patient-provider clinical decision-making. METHODS: We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist and the PRISMA-P protocol guidance in addition to a modified CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) checklist to conduct this scoping review. A comprehensive medical literature search of databases, including Embase, MEDLINE, PsycINFO, Cochrane, Scopus, and Web of Science, was conducted to identify AI and ML algorithms that would impact clinical decision-making at the level of direct patient care. Our primary end point is the rate at which model updating is recommended by published algorithms; we will also conduct an assessment of study quality and risk of bias in all publications reviewed. In addition, we will evaluate the rate at which published algorithms include ethnic and gender demographic distribution information in their training data as a secondary end point. RESULTS: Our initial literature search yielded approximately 13,693 articles, with approximately 7810 articles to consider for full reviews among our team of 7 reviewers. We plan to complete the review process and disseminate the results by spring of 2023. CONCLUSIONS: Although AI and ML applications in health care have the potential to improve patient care by reducing errors between measurement and model output, currently there exists more hype than hope because of the lack of proper external validation of these models. We expect to find that the AI and ML model-updating methods are proxies for model applicability and generalizability on implementation. Our findings will add to the field by determining the degree to which published models meet the criteria for clinical validity, real-life implementation, and best practices to optimize model development, and in so doing, reduce the overpromise and underachievement of the contemporary model development process. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/37685.

Using a Machine Learning Algorithm to Predict Online Patient Portal Utilization: A Patient Engagement Study.

Objective: There is a low rate of online patient portal utilization in the U.S. This study aimed to utilize a machine learning approach to predict access to online medical records through a patient portal. Methods: This is a cross-sectional predictive machine learning algorithm-based study of Health Information National Trends datasets (Cycles 1 and 2; 2017-2018 samples). Survey respondents were U.S. adults (≥18 years old). The primary outcome was a binary variable indicating that the patient had or had not accessed online medical records in the previous 12 months. We analyzed a subset of independent variables using k-means clustering with replicate samples. A cross-validated random forest-based algorithm was utilized to select features for a Cycle 1 split training sample. A logistic regression and an evolved decision tree were trained on the rest of the Cycle 1 training sample. The Cycle 1 test sample and Cycle 2 data were used to benchmark algorithm performance. Results: Lack of access to online systems was less of a barrier to online medical records in 2018 (14%) compared to 2017 (26%). Patients accessed medical records to refill medicines and message primary care providers more frequently in 2018 (45%) than in 2017 (25%). Discussion: Privacy concerns, portal knowledge, and conversations between primary care providers and patients predict portal access. Conclusion: Methods described here may be employed to personalize methods of patient engagement during new patient registration.

Beyond Getting Rid of Stupid Stuff in the Electronic Health Record (Beyond-GROSS): Protocol for a User-Centered, Mixed-Method Intervention to Improve the Electronic Health Record System.

BACKGROUND: Up to 60% of health care providers experience one or more symptoms of burnout. Perceived clinician burden resulting in burnout arises from factors such as electronic health record (EHR) usability or lack thereof, perceived loss of autonomy, and documentation burden leading to less clinical time with patients. Burnout can have detrimental effects on health care quality and contributes to increased medical errors, decreased patient satisfaction, substance use, workforce attrition, and suicide. OBJECTIVE: This project aims to improve the user-centered design of the EHR by obtaining direct input from clinicians about deficiencies. Fixing identified deficiencies via user-centered design has the potential to improve usability, thereby increasing satisfaction by reducing EHR-induced burnout. METHODS: Quantitative and qualitative data will be obtained from clinician EHR users. The input will be received through a form built in a REDCap database via a link embedded in the home page of the EHR. The REDCap data will be analyzed in 2 main dimensions, based on nature of the input, what section of the EHR is affected, and what is required to fix the issue(s). Identified issues will be escalated to relevant stakeholders responsible for rectifying the problems identified. Data analysis, project evaluation, and lessons learned from the evaluation will be incorporated in a Plan-Do-Study-Act (PDSA) manner every 4-6 weeks. RESULTS: The pilot phase of the study began in October 2020 in the Gastroenterology Division at Mount Sinai Hospital, New York City, NY, which includes 39 physicians and 15 nurses. The pilot is expected to run over a 4-6-month period. The results of the REDCap data analysis will be reported within 1 month of completing the pilot phase. We will analyze the nature of requests received and the impact of rectified issues on the clinician EHR user. We expect that the results will reveal which sections of the EHR have the highest deficiencies while also highlighting issues about workflow difficulties. Perceived impact of the project on provider engagement, patient safety, and workflow efficiency will also be captured by evaluation survey and other qualitative methods where possible. CONCLUSIONS: The project aims to improve user-centered design of the EHR by soliciting direct input from clinician EHR users. The ultimate goal is to improve efficiency, reduce EHR inefficiencies with the possibility of improving staff engagement, and lessen EHR-induced clinician burnout. Our project implementation includes using informatics expertise to achieve the desired state of a learning health system as recommended by the National Academy of Medicine as we facilitate feedback loops and rapid cycles of improvement. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/25148.

Impact of Digital Divide on the Adoption of Online Patient Portals for Self-Motivated Patients.

OBJECTIVE: Our study aimed to determine the effect of the digital divide in the adoption of online patient portals by motivated patients who wish to improve their health outcomes through the use of the Internet and information technology to assess determinants of low adoption rates of online portals and to explore social media use as a correlation to patient portal use. METHODS: We utilized data from the Health Information National Trends Survey (HINTS) 2017 and 2018. We performed a cross-sectional study analyzing the outcome variable of patient portal use with several predictor variables, namely, age, marital status, gender, mental health, education, Medicaid, income, number of people in household, trust, social media, chronic disease, and health app use. Basic descriptive statistics and logistic regression were performed using SPSS version 25. RESULTS: Our study found that low adoption rates go beyond the digital divide. A correlation exists between social media use and patient portal use, and the impact of previously identified factors on patients with self-motivation for health improvement. CONCLUSION: Self-motivation is an important factor in patient portal use and access. Behavioral and motivational interventions geared towards the adoption of health information technology tools, such as online portals, can assist with improving the public health significance of these tools.

A quality improvement intervention to enhance performance and perceived confidence of new internal medicine residents.

Background: Orientation for new medical residents is challenging due to the diversity of prior experiences and cultural backgrounds and is compounded by a lack of orientation curricula that adequately addresses the needs of the medical residents to allow them to perform their duties in an efficient manner from the start. The beginning of residency training is associated with reduced quality of healthcare widely referred to as the 'July effect'. Objective: To assess the impact of a peer-led orientation for new interns on (a) self-reported confidence level, (b) improvement in performance of first-year residents in appropriate clinical documentation and efficient discharge procedures and protocols. Design/methods: In June 2016, a hybrid of interactive teaching and simulation exercises was used to teach documentation of critical information, such as discharge medication reconciliation and discharge summary. A handout of an intern guide/manual was also provided. The previous year's data served as comparison/control data. Comparison data were obtained for both groups from hospital's utilisation review department. Results: Twenty-one of 23 expected new interns (91%) participated in the intervention. There was a significant decrease in non-compliance for clinical documentation in the intervention group compared to the control group. The self-reported confidence level in the intervention group increased 34%. Conclusions: Such peer-to-peer orientation has the potential to effectively improve appropriate documentation and discharge process by new residents and may help to reduce the 'July effect'.

Effect of body mass index on outcome in patients with suspected coronary artery disease referred for stress echocardiography.

In patients with hypertension, heart failure, or coronary artery disease (CAD), obese patients have been shown to have a lower cardiac event rate compared with normal weight counterparts. This phenomenon has been termed the "obesity paradox." We sought to determine whether the obesity paradox exists in a cohort of patients referred for stress echocardiography. We evaluated 4,103 patients with suspected CAD (58 ± 13 years; 42% men) undergoing stress echocardiography (52% exercise and 47% dobutamine). Patients were divided into 3 groups on the basis of body mass index (BMI): 18.5 to 24.9, 25 to 29.9, and >30 kg/m(2). During the follow-up of 8.2 ± 3.6 years, there were 683 deaths (17%). Myocardial ischemia was present in 21% of the population. Myocardial ischemia was more prevalent in patients with a BMI of 18.5 to 24.9 kg/m(2) (26%) than those with a BMI of 25 to 29.9 kg/m(2) (21%) and >30 kg/m(2) (18%). Patients with a BMI of >30 kg/m(2) had the lowest death rate (1.2%/year) compared with those with a BMI of 25 to 29.9 kg/m(2) (1.75%/year) and 18.5 to 24.9 kg/m(2) (2.9%/year; p <0.001). After adjusting for significant clinical variables including exercise capacity, patients with higher BMI (>30 kg/m(2) and 25 to 29.9 kg/m(2)) had less risk of mortality compared with those with a BMI of 18.5 to 24.9 kg/m(2) (hazard ratio 0.58, 95% confidence interval 0.47 to 0.72, p <0.0001 and hazard ratio 0.69, 95% confidence interval 0.57 to 0.82, p <0.0001, respectively). In conclusion, higher survival rate in patients with higher BMI as previously described in patients with hypertension, heart failure, and CAD extends to patients with suspected CAD referred for stress echocardiography, independent of exercise capacity.

Lymphatic malformations of the airway.

OBJECTIVES/HYPOTHESIS: To characterize the anatomic distribution of lymphatic malformations of the upper airway. STUDY DESIGN: Case series with chart review. SETTING: Tertiary care referral center specializing in the diagnosis and treatment of vascular anomalies. METHODS: A 7-year (2004-2011) retrospective chart review of patients with lymphatic malformations was performed at a tertiary care referral center. Patients with airway lymphatic malformations were identified. The anatomic distribution of lymphatic malformations within the airway was reviewed. RESULTS: A total of 141 patients with lymphatic malformations of the upper aerodigestive tract (UADT) were studied. Of these, 15 (11%) had laryngeal (supraglottic) involvement. In all of these patients, the disease was above the true vocal folds. Seventy-four (52%) patients had involvement of 1 anatomic zone (most common was the oral cavity), and 67 (48%) had involvement of multiple zones. With regard to each zone, 105 (75%) patients had involvement of the oral cavity, 50 (36%) the oropharynx, 8 (6%) the hypopharynx, 42 (30%) the parapharynx, and 12 (9%) had retropharygeal disease (some patients had multiple zones involved). No patients were identified with glottic, subglottic, or tracheal involvement. CONCLUSIONS: Based on our large series, airway involvement in head and neck lymphatic malformations may occur at multiple sites above the glottis. A high percentage of these patients have involvement of the oral cavity (75%) and oropharynx (35%). None involve the glottis, subglottis, or trachea.