Longitudinal Care Management Research Articles

Enhancing Clinical Communication through AI-Powered Recording and Analysis: A Multi-Center Study of Scribr AI Implementation

This article examines the implementation and effectiveness of Scribr AI, an artificial intelligence-powered system designed to enhance doctor-patient communication through automated recording, transcription, and multilingual support in clinical settings. The article evaluates the platform's impact on clinical documentation, patient comprehension, and longitudinal care management across multiple healthcare facilities. Through a comprehensive article analysis of system usage, patient engagement, and healthcare provider feedback, the article demonstrates significant improvements in communication accuracy, patient understanding, and clinical workflow efficiency. The findings indicate that AI-enabled recording and translation systems can effectively bridge language barriers, enhance patient recall of medical instructions, and support precision medicine through detailed documentation of health histories. Additionally, the study reveals notable benefits for chronic care patients through improved tracking and accessibility of historical health data. These results suggest that AI-powered communication tools can play a crucial role in modernizing healthcare delivery while addressing persistent challenges in doctor-patient communication and medical documentation. The findings have important implications for healthcare institutions seeking to improve patient engagement, reduce communication barriers, and enhance the quality of clinical documentation.

Novel Approaches and Actionable Insights to Improve Outcomes

This issue of NEJM Catalyst Innovations in Care Delivery includes articles, case studies, and research reports on improved access to organ transplantation, a health equity index, global collaboration on patient-reported outcomes, clinical decision-making tools, integration of teaching and research into community practices, longitudinal care management, and patient quality and safety.

Longitudinal Care Management for Diabetes and Hypertension

Addressing common sources of chronic disease leads to improved patient health, as well as presenting a scalable target for the improvement of value-based care outcomes. Improving patients’ self-management skills and quality of life is the key goal of chronic disease management. Mitigating high-costs and slowing disease progression create mutual success for both patients and health care systems. By training nurses to deliver a refined model of longitudinal care management, Corewell Health West was able to achieve improved chronic disease control and create additional capacity among primary care providers. The initial focus of the longitudinal care program was diabetes and hypertension management. Corewell Health created a Multidisciplinary Approach to Disease Over Time (MADOT) framework to guide care management for patients with multiple chronic conditions or who are facing long recovery journeys. The framework emphasizes timely and actionable patient identification, regular contact between patients and health care staff that prioritizes patient goals and assesses their “readiness to change,” and specialized skills development for health care staff. The framework has shown success among patients with uncontrolled diabetes (A1c ≥8.0). Of the targeted interventions carried out for more than 1,000 patients since January 2022, 608 patients fully completed the program; these patients demonstrated an average 2.24-percentage point reduction in hemoglobin A1c. Of those 608 patients, 364 had a pre-intervention hemoglobin A1c level ≥9.0 and achieved an average 3.02-percentage point reduction in hemoglobin A1c. Similarly, patients who graduated from the program saw greater improvement in systolic blood pressure than patients who disenrolled or declined interventions.

Pediatric Population Management Classification for Children with Medical Complexity.

Improving the overall care of children with medical complexity (CMC) is often beset by challenges in proactively identifying the population most in need of clinical management and quality improvement. The objective of the current study was to create a system to better capture longitudinal risk for sustained and elevated utilization across time using real-time electronic health record (EHR) data. A new Pediatric Population Management Classification (PPMC), drawn from visit diagnoses and continuity problem lists within the EHR of a tristate health system, was compared with an existing complex chronic conditions (CCC) system for agreement (with weighted κ) on identifying CCMC, as well as persistence of elevated charges and utilization from 2016 to 2019. Agreement of assignment PPMC was lower among primary care provider (PCP) populations than among other children traversing the health system for specialty or hospital services only (weighted κ 62% for PCP vs. 82% for non-PCP). The PPMC classification scheme, displaying greater precision in identifying CMC with persistently high utilization and charges for those who receive primary care within a large integrated health network, may offer a more pragmatic approach to selecting children with CMC for longitudinal care management.

Longitudinal Risk Management for Patients with Increased Risk for Breast Cancer

IntroductionThis study aims to characterize longitudinal care management and evaluate the relationship between various patient factors and the likelihood of choosing risk-reducing behaviors in women with increased risk of developing breast cancer. MethodsA retrospective study was conducted to evaluate all adult female patients who had at least one clinic visit with a surgical provider for discussion of breast cancer risk assessment between January, 2017 to July, 2020 at an academic center. Patients with prior history of breast cancer were excluded. Patient details and strategies pursued at clinic visits were recorded. A time-to-event analysis was performed, and hazard ratios were determined to characterize associations between patient characteristics and time to pursuing risk-reducing care management. ResultsThere were 283 participants with at least one follow-up visit and 48 (17.0%) ultimately changed their initial strategy to either chemoprevention or prophylactic mastectomy. Patients with gene mutations were 6 times more likely to engage in risk-reducing management compared to those without (hazard ratio (HR) 5.99, P < 0.001). Those with histories of high-risk proliferative changes (HR 7.62, P < 0.001) and hysterectomy (HR 2.99, P = 0.019) were also more likely to engage in risk-reducing management. Age, race, and increased predicted risk of developing breast cancer (estimated by various calculators) were not associated with increased likelihood of engaging in risk-reducing strategies. ConclusionKnown gene mutations, history of high-risk proliferative changes, and prior hysterectomy were factors associated with women who were more likely to engage in risk-reducing strategies. These findings, when paired with patient reported outcome measures, may help guide shared decision-making.

Exploring and Overcoming the Challenges Primary Care Practices Face with Care Management of High-Risk Patients in CPC+: a Mixed-Methods Study.

Longitudinal care management (LCM) for high-risk patients is a cornerstone of primary care models aiming to improve quality and reduce costs. Describe the extent to which LCM was implemented in the second year of Comprehensive Primary Care Plus (CPC+), and barriers to and facilitators of implementation. Mixed-methods. Quantitative: 2715 practices participating in CPC+ in 2018. Qualitative: Interviews with practitioners and staff in 23 representative CPC+ practices. Across all CPC+ practices, we report median percentages of empaneled patients placed in the highest-risk tiers and, of those, the median percentage receiving LCM. Across 23 CPC+ practices, we report qualitative findings on LCM implementation. While practices reported benefits of LCM, a small proportion of patients received LCM. Practices placed 2.4% (median) of patients in the highest-risk tier; of these, 30% (median) received LCM. Practices placed 10% (median) of patients in the second-highest-risk tier; of these, 7% (median) received LCM. Interviews revealed LCM uptake across tiers was low because of insufficient care manager staffing. Other challenges included lack of practitioner buy-in to using risk stratification to identify high-risk patients, patients' reluctance to engage in LCM or change behaviors, and limited health information technology functionality for developing, maintaining, and accessing high-risk patients' care plans. Facilitators included embedding care managers within practices and electronic health record functionalities that support LCM. Despite substantial financial and other supports, and practices' perceived benefits of LCM, insufficient care manager staffing and other barriers have limited its potential in CPC+ to date. To expand LCM's reach, practices need additional care managers, training to overcome barriers to patient engagement, better identification of patients who might benefit from LCM, improved information technology tools for risk stratification and care plans, and more practitioner buy-in to risk stratification.

Evaluating the Feasibility of a Software Prototype Supporting the Management of Multimorbid Seniors: Mixed Methods Study in General Practices.

BackgroundLongitudinal, patient-centered care represents a challenge for general practices. Decision support and reminder systems can offer targeted support.ObjectiveThe objective of this study was to follow a user-oriented, stepwise approach to develop an add-on for German electronic health record (EHR) systems, which aims to support longitudinal care management of multimorbid seniors, using a flag system displaying patient-centered information relevant for comprehensive health care management. This study evaluated the prototype’s feasibility from both a technical and users’ perspective.MethodsThe study was conducted with 18 general practitioners (GPs) and practice assistants (PAs) from 9 general practices using a mixed methods approach. In all practices, 1 GP and 1 PA tested the software each for 4 multimorbid seniors selected from the practice patient data. Technical feasibility was evaluated by documenting all technical problems. To evaluate the feasibility from the users’ perspective, participants’ responses during the software test were documented. In addition, they completed a self-administered questionnaire, including the validated System Usability Scale (SUS). Data were merged by transforming qualitative data into quantitative data. Analyses were performed using univariate statistics in IBM SPSS statistics.ResultsFrom a technical perspective, the new software was easy to install and worked without problems. Difficulties during the installation occurred in practices lacking a 64-bit system or a current version of Microsoft .NET. As EHRs used in German practices do not provide an interface to extract the data needed, additional software was required. Incomplete flags for some laboratory data occurred, although this function was implemented in our software as shown in previous tests. From the users’ perspective, the new add-on provided a better overview of relevant patient information, reminded more comprehensively about upcoming examinations, and better supported guideline-based care when compared with their individual practice strategies. A total of 14 out of 18 participants (78%) were interested in using the software long-term. Furthermore, 8 of 9 GPs were willing to pay 5 to 25 Euros (mean 14.75, SD 5.93) monthly for its use. The usability was rated as 75% (43%-95%).ConclusionsThe new EHR add-on was well accepted and achieved a good usability rating measured by the validated SUS. In perspective, the legally consolidated, standardized interface to German EHRs will facilitate the technical integration. In view of the high feasibility, we plan to study the software’s effectiveness in everyday primary care.Trial RegistrationGerman Clinical Trials Register DRKS00008777; https://www.drks.de/drks_web/navigate.do? navigationId=trial.HTML&TRIAL_ID=DRKS00008777

Abstract 147: Impact of Risk Factor Modification in Improving Quality of Life and Arrhythmia Symptoms in Patients With Atrial Fibrillation

Objective: The desired goal of atrial fibrillation (AF) management is maintenance of sinus rhythm in order to improve quality of life (QoL) and arrhythmia symptoms (AS). Although obesity and obstructive sleep apnea (OSA) are known risk factors for development of AF, these remain inadequately treated. We report the impact of prospectively modifying these risk factors on QoL and AS in AF patients (pts). Methods: AF pts with obesity (body mass index (BMI) ≥30kg/m 2 ) and/or the need for OSA management (high-risk as per Berlin Questionnaire or untreated OSA) were voluntarily enrolled in a nurse-led risk factor modification (RFM) program at their arrhythmia clinic visit. RFM entailed patient education, lifestyle modification counseling, coordination of care with appropriate specialists, and longitudinal care management. Progress with weight loss (WL) and OSA treatment was monitored via monthly follow-up calls and/or downloads from continuous positive airway pressure (CPAP) units for up to 12 months. QoL and AS were determined with the SF-36 and AF Severity Scale (AFSS) respectively, and were assessed at baseline, 6 months, and 12 months. Student t-test and chi-square tests were used to compare continuous and dichotomous variables. Results: From 11/1/16 to 10/31/17, 252 pts (age 63±11 years; male=179; paroxysmal AF=126) were enrolled as follows: 189 for obesity and 93 for OSA. The mean WL was 2.7±3.8% from baseline and 78% (n=126 of 162 pts with available data) of enrolled obese patients achieved WL. Among 93 pts at risk for OSA, 70 completed sleep studies and 50 were identified with OSA. Majority of these patients (76%; n=38 of 50) started CPAP therapy and have remained full (57%; n=17 of 30 pts with available CPAP data) and partial (13%; n=4 of 30) users. Table shows that SF-36 and AFSS scores improved for most measures of QoL and AS from baseline to 6 months. Conclusion: Participation in a risk factor modification program targeting obesity and obstructive sleep apnea can improve quality of life and arrhythmia symptoms in patients with atrial fibrillation. The impact of this strategy on long-term maintenance of sinus rhythm remains to be determined.

The Strategies to Reduce Injuries and Develop Confidence in Elders Intervention: Falls Risk Factor Assessment and Management, Patient Engagement, and Nurse Co-management.

In response to the epidemic of falls and serious falls-related injuries in older persons, in 2014, the Patient Centered Outcomes Research Institute (PCORI) and the National Institute on Aging funded a pragmatic trial, Strategies to Reduce Injuries and Develop confidence in Elders (STRIDE) to compare the effects of a multifactorial intervention with those of an enhanced usual care intervention. The STRIDE multifactorial intervention consists of five major components that registered nurses deliver in the role of falls care managers, co-managing fall risk in partnership with patients and their primary care providers (PCPs). The components include a standardized assessment of eight modifiable risk factors (medications; postural hypotension; feet and footwear; vision; vitamin D; osteoporosis; home safety; strength, gait, and balance impairment) and the use of protocols and algorithms to generate recommended management of risk factors; explanation of assessment results to the patient (and caregiver when appropriate) using basic motivational interviewing techniques to elicit patient priorities, preferences, and readiness to participate in treatments; co-creation of individualized falls care plans that patients' PCPs review, modify, and approve; implementation of the falls care plan; and ongoing monitoring of response, regularly scheduled re-assessments of fall risk, and revisions of the falls care plan. Custom-designed falls care management software facilitates risk factor assessment, the identification of recommended interventions, clinic note generation, and longitudinal care management. The trial testing the effectiveness of the STRIDE intervention is in progress, with results expected in late 2019.

Collaborative care from the emergency department for injured patients with prescription drug misuse: An open feasibility study

Collaborative Care is a comprehensive longitudinal care management strategy. The purpose of this pilot effectiveness-implementation hybrid study was to determine the feasibility of a Collaborative Care intervention initiated from the Emergency Department and proceeding longitudinally for six months for injured patients with prescription drug misuse (PDM). Adult patients presenting to an urban ED with an injury were screened for eligibility from 2/2015–8/2015. Eligible participants with a positive screen for PDM were enrolled in the ‘ED-LINC’ intervention which included the following elements: 1) active care coordination and linkage, 2) medication safety and utilization of opioid guidelines 3) longitudinal care management and 4) utilization of Electronic Medical Record (EMR) innovations such as the statewide Emergency Department Information Exchange (EDIE) and statewide prescription monitoring program information for assessment and follow-up. Baseline characteristics of the sample were assessed and regression models were used to evaluate longitudinal trajectories of risk for PDM. A total of 36 participants (56% of patients approached) had PDM and 30 participants were enrolled. Of those enrolled, 37% had prescription stimulant misuse, 20% with prescription sedative misuse and 97% had prescription opioid misuse. Follow-up rates at all time points were ≥83%. Baseline levels of comorbidity were high; 57% endorsed recent heroin use and 70% endorsed symptoms consistent with major depression. Over 50% had five or more statewide ED visits and 53% had used three or more different ED‘s in the past year. On average, participants received a total of 85 minutes of ED-LINC over six months with 90% of participants receiving all four intervention elements. All patients had care coordinated with new or existing primary care providers (PCP's) and 23% were linked to a new PCP. A majority of patients (≥80%) reported receiving high quality, desired intervention services. There was no significant change in PDM over time. Collaborative Care initiated from the ED is feasible and acceptable to patients with trauma and PDM. Future directions could include effectiveness-implementation hybrid trials to study implementation barriers and strategies as well as patient-level outcomes of this intervention for this complex patient population.

Improvement in interprofessional student learning and patient outcomes

Abstract Background Traditional health professions training programs are seeking ways to provide experiential clinical interprofessional teamwork needed for providing population care management consistent with the Patient-Centered Medical Home (PCMH) model. Purpose Interprofessional faculty developed a longitudinal care management program for patients with uncontrolled diabetes, designed to provide interprofessional teamwork learning opportunities and improved patient care delivery. Methods Health professional learners participated in a longitudinal ambulatory outpatient diabetes care management program. In a quasi-experimental design, control and participating learners completed pre and post self-assessments of both teamwork skills and attitude. Control and participating patients completed a patient perception survey. Discussion Teamwork skills, as self-assessed by participating learners, significantly improved. Patient satisfaction scores significantly improved for participating patients; select patients demonstrated better diabetes control, smoking cessation, and lifestyle changes. Conclusions Linking learning and care delivery in an interprofessional longitudinal ambulatory care management program positively impacted patient satisfaction and learner teamwork skills.

Innovative Information Technology–Powered Population Health Care Management Improves Outcomes and Reduces Hospital Readmissions and Emergency Department Visits

Patients with chronic conditions are often the most frequent users of health care. Moreover, adapting to developments in one's illness, understanding how to self-manage a chronic illness, and sharing information between primary care and specialty providers, can be a full-time job for someone with a chronic illness. In response to these challenges, Christiana Care Health System (Wilmington, Delaware) developed Care Link, an information technology (IT)-enhanced care management support to enable populations of patients to achieve better clinical outcomes at lower cost. In 2012 Christiana Care received a grant to design a generalizable, scalable, and replicable IT-driven care model that would integrate disparate clinical and registry data generated from routine care to support longitudinal care management for patients with ischemic heart disease. The single-disease care management program was expanded beginning in mid-2015 to serve risk-based models for many diseases and chronic conditions. More than 8,600 patients in several surgical and medical populations, including joint replacement, cervical spine surgery, and congestive heart failure, have been supported by Care Link. For example, preoperative assessment of patients with elective joint replacement to predict post-acute care needs led to an increase in the volume of patients discharged to home with self-care or with home health care by 30%-from 61% to 80%. Care Link IT functions can be replicated to address the unique longitudinal care needs of any population. Care Link's next steps are to continue to increase the number of patients served throughout the region and to expand the scope of care management programming.

Is the Care Transitions Measure Associated with Readmission Risk? Analysis from a Single Academic Center.

It is widely hypothesized that improvement in transitions of care will reduce unplanned hospital readmissions. However, the association between the Care Transitions Measure, the national quality metric for transitions of care and readmission risk, has not been established. We aimed to determine the association between the Care Transition Measure and readmission. This was a single-center, prospective cohort study. Convenience sample of 2,963 patients enrolled in the "Bridging the Divides" program, a longitudinal care management program for patients with coronary revascularization, from 2013 to 2014. Of these, 1594 (54%) patients completed a post-discharge Care Transition Measure questionnaire. Care Transition Measure scores were collected by trained research staff blinded to study hypothesis, by telephone, within 30days of discharge. Higher Care Transition Measure scores reflect a higher quality transition of care. 30-day readmission was measured. Of the1594 patients that completed the Care Transition Measure survey, 1216 (76%) received percutaneous coronary intervention and 378 (24%) received coronary artery bypass grafting. Mean Care Transition Measure scores were significantly lower among patients who had a prior admission (77.2 vs. 82.1, p < 0.001) and those with ≥ 5 comorbidities (77 vs. 82.6 vs. 81.6, p < 0.001). Mean scores were significantly lower among patients who were readmitted within the percutaneous coronary intervention subgroup (73 vs. 80.9, p < 0.001) and the total study population (74.6 vs. 81.1, p < 0.001) compared to those who were not readmitted. This was not the case in the coronary artery bypass grafting subgroup (78.5 vs. 81.7, p = 0.29). After multivariable adjustment, every ten-point increase in the Care Transition Measure score was associated with a 14% reduction in readmission risk (adjusted odds ratio 0.86, 95% CI 0.78-0.95). The Care Transition Measure is strongly associated with readmissions, which strengthens its validity. However, its association with patient variables linked with readmission and its inconsistent association with readmission across clinical groups raises concerns that scores may be influenced by patient characteristics.