Assessing Biological Age: The Potential of ECG Evaluation Using Artificial Intelligence: JACC Family Series.

Biological age may be a more valuable predictor of morbidity and mortality than a person's chronological age. Mathematical models have been used for decades to predict biological age, but recent developments in artificial intelligence (AI) have led to new capabilities in age estimation. Using deep learning methods to train AI models on hundreds of thousands of electrocardiograms (ECGs) to predict age results in a good, but imperfect, age prediction. The error predicting age using ECG, or the difference between AI-ECG-derived age and chronological age (delta age), may be a surrogate measurement of biological age, as the delta age relates to survival, even after adjusting for chronological age and other covariates associated with total and cardiovascular mortality. The relative affordability, noninvasiveness, and ubiquity of ECGs, combined with ease of access and potential to be integrated with smartphone or wearable technology, presents a potential paradigm shift in assessment of biological age.

Prospective evaluation of smartwatch-enabled detection of left ventricular dysfunction.

Although artificial intelligence (AI) algorithms have been shown to be capable of identifying cardiac dysfunction, defined as ejection fraction (EF) ≤ 40%, from 12-lead electrocardiograms (ECGs), identification of cardiac dysfunction using the single-lead ECG of a smartwatch has yet to be tested. In the present study, a prospective study in which patients of Mayo Clinic were invited by email to download a Mayo Clinic iPhone application that sends watch ECGs to a secure data platform, we examined patient engagement with the study app and the diagnostic utility of the ECGs. We digitally enrolled 2,454 unique patients (mean age 53 ± 15 years, 56% female) from 46 US states and 11 countries, who sent 125,610 ECGs to the data platform between August 2021 and February 2022; 421 participants had at least one watch-classified sinus rhythm ECG within 30 d of an echocardiogram, of whom 16 (3.8%) had an EF ≤ 40%. The AI algorithm detected patients with low EF with an area under the curve of 0.885 (95% confidence interval 0.823-0.946) and 0.881 (0.815-0.947), using the mean prediction within a 30-d window or the closest ECG relative to the echocardiogram that determined the EF, respectively. These findings indicate that consumer watch ECGs, acquired in nonclinical environments, can be used to identify patients with cardiac dysfunction, a potentially life-threatening and often asymptomatic condition.

An Algorithm for Pairing Interventionalists and Surgeons for the TAVR Procedure.

The Transcatheter Aortic Valve Replacement (TAVR) procedure requires an initial consultation and a subsequent procedure by an interventionalist (IC) and surgeon. The IC-surgeon pair coordination is extremely challenging, especially at Mayo Clinic due to provider time commitments distributed across practice, research, and education activities. Current practice aims to establish the coordination manually, resulting in a scheduling process that is cumbersome and time consuming for the schedulers. We develop an algorithm for pairing ICs and surgeons that minimizes the lead time (days elapsed between the clinic consult and procedure). As compared to current practice, this algorithm is able to reduce average lead time by 59% and increase possible IC-surgeon pairs by 7%. The proposed algorithm is shown to be flexible enough to incorporate practice variations such as lead time upper bound and two procedure days for a single consult day. Algorithm alternatives are also presented for practices who may find the proposed algorithm infeasible for their practice.

Development and Implementation of a Team-Based, Primary Care Delivery Model: Challenges and Opportunities.

In this article, we describe the implementation of a team-based care model during the first 2 years (2016-2017) after Mayo Clinic designed and built a new primary care clinic in Rochester, Minnesota. The clinic was configured to accommodate a team-based care model that included complete colocation of clinical staff to foster collaboration, designation of a physician team manager to support a physician to advanced practice practitioner ratio of 1:2, expanded roles for registered nurses, and integration of clinical pharmacists, behavioral health specialists, and community specialists; this model was designed to accommodate the growth of nonvisit care. We describe the implementation of this team-based care model and the key metrics that were tracked to assess performance related to the quadruple aim of improving population health, improving patient experience, reducing cost, and supporting care team's work life.

Family Medicine Panel Size with Care Teams: Impact on Quality.

PURPOSE: The demand for comprehensive primary health care continues to expand. The development of team-based practice allows for improved capacity within a collective, collaborative environment. Our hypothesis was to determine the relationship between panel size and access, quality, patient satisfaction, and cost in a large family medicine group practice using a team-based care model. METHODS: Data were retrospectively collected from 36 family physicians and included total panel size of patients, percentage of time spent on patient care, cost of care, access metrics, diabetic quality metrics, patient satisfaction surveys, and patient care complexity scores. We used linear regression analysis to assess the relationship between adjusted physician panel size, panel complexity, and outcomes. RESULTS: The third available appointments (P < .01) and diabetic quality (P = .03) were negatively affected by increased panel size. Patient satisfaction, cost, and percentage fill rate were not affected by panel size. A physician-adjusted panel size larger than the current mean (2959 patients) was associated with a greater likelihood of poor-quality rankings (≤25th percentile) compared with those with a less than average panel size (odds ratio [OR], 7.61; 95% confidence interval [CI], 1.13-51.46). Increased panel size was associated with a longer time to the third available appointment (OR, 10.9; 95% CI, 1.36-87.26) compared with physicians with panel sizes smaller than the mean. CONCLUSIONS: We demonstrated a negative impact of larger panel size on diabetic quality results and available appointment access. Evaluation of a family medicine practice parameters while controlling for panel size and patient complexity may help determine the optimal panel size for a practice.

HIPAA costs and patient perceptions privacy safeguards Mayo Clinic.

BACKGROUND: A study was conducted to assess the costs of implementation of the Health Insurance Portability and Accountability Act (HIPAA) and to report patient awareness of Notices of Privacy Practices (NPP) content and HIPAA privacy protections. METHODS: All HIPAA start-up and implementation costs were collected prospectively. A random sample of 2,000 patients receiving services at the Mayo Clinic after HIPAA implementation (April 14, 2003) was surveyed about HIPAA knowledge, HIPAA content, and privacy concerns. RESULTS: Comprehensive measures of total HIPAA costs and costs related only to privacy practices were amortized over 7, 15, and 20 years. Patient knowledge of privacy protections and attitudes toward HIPAA were obtained from 1,309 (65.5%) respondents. The total HIPAA startup costs were $4,663,672. Fully amortized costs (annual plus start-up costs) were $1 per patient visit or $5 per patient per year. Costs for the privacy portion were $2,734,855. These costs were about $.90 per patient visit or about $4 per patient per year. Patients indicated high levels of awareness of HIPAA (71%), reading the NPP (79%), knowledge about HIPAA (80% with 6+ correct answers on a 10-item quiz), and improved feelings of privacy (44% versus 55% the same). DISCUSSION: Patients reported high levels of knowledge about HIPAA and confidence in privacy protections. HIPAA costs were modest per patient or per visit.