Dataset Information

A Data-Driven Algorithm to Recommend Initial Clinical Workup for Outpatient Specialty Referral: Algorithm Development and Validation Using Electronic Health Record Data and Expert Surveys.

ABSTRACT:

Background

Millions of people have limited access to specialty care. The problem is exacerbated by ineffective specialty visits due to incomplete prereferral workup, leading to delays in diagnosis and treatment. Existing processes to guide prereferral diagnostic workup are labor-intensive (ie, building a consensus guideline between primary care doctors and specialists) and require the availability of the specialists (ie, electronic consultation).

Objective

Using pediatric endocrinology as an example, we develop a recommender algorithm to anticipate patients' initial workup needs at the time of specialty referral and compare it to a reference benchmark using the most common workup orders. We also evaluate the clinical appropriateness of the algorithm recommendations.

Methods

Electronic health record data were extracted from 3424 pediatric patients with new outpatient endocrinology referrals at an academic institution from 2015 to 2020. Using item co-occurrence statistics, we predicted the initial workup orders that would be entered by specialists and assessed the recommender's performance in a holdout data set based on what the specialists actually ordered. We surveyed endocrinologists to assess the clinical appropriateness of the predicted orders and to understand the initial workup process.

Results

Specialists (n=12) indicated that <50% of new patient referrals arrive with complete initial workup for common referral reasons. The algorithm achieved an area under the receiver operating characteristic curve of 0.95 (95% CI 0.95-0.96). Compared to a reference benchmark using the most common orders, precision and recall improved from 37% to 48% (P<.001) and from 27% to 39% (P<.001) for the top 4 recommendations, respectively. The top 4 recommendations generated for common referral conditions (abnormal thyroid studies, obesity, amenorrhea) were considered clinically appropriate the majority of the time by specialists surveyed and practice guidelines reviewed.

Conclusions

An item association-based recommender algorithm can predict appropriate specialists' workup orders with high discriminatory accuracy. This could support future clinical decision support tools to increase effectiveness and access to specialty referrals. Our study demonstrates important first steps toward a data-driven paradigm for outpatient specialty consultation with a tier of automated recommendations that proactively enable initial workup that would otherwise be delayed by awaiting an in-person visit.

SUBMITTER: Ip W

PROVIDER: S-EPMC8931647 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundWith increasing use of real world data in observational health care research, data quality assessment of these data is equally gaining in importance. Electronic health record (EHR) or claims datasets can differ significantly in the spectrum of care covered by the data.ObjectiveIn our study, we link provider specialty with diagnoses (encoded in International Classification of Diseases) with a motivation to characterize data completeness.MethodsWe develop a set of measures that determine diagnostic span of a specialty (how many distinct diagnosis codes are generated by a specialty) and specialty span of a diagnosis (how many specialties diagnose a given condition). We also analyze ranked lists for both measures. As use case, we apply these measures to outpatient Medicare claims data from 2016 (3.5 billion diagnosis-specialty pairs). We analyze 82 distinct specialties present in Medicare claims (using Medicare list of specialties derived from level III Healthcare Provider Taxonomy Codes).ResultsA typical specialty diagnoses on average 4,046 distinct diagnosis codes. It can range from 33 codes for medical toxicology to 25,475 codes for internal medicine. Specialties with large visit volume tend to have large diagnostic span. Median specialty span of a diagnosis code is 8 specialties with a range from 1 to 82 specialties. In total, 13.5% of all observed diagnoses are generated exclusively by a single specialty. Quantitative cumulative rankings reveal that some diagnosis codes can be dominated by few specialties. Using such diagnoses in cohort or outcome definitions may thus be vulnerable to incomplete specialty coverage of a given dataset.ConclusionWe propose specialty fingerprinting as a method to assess data completeness component of data quality. Datasets covering a full spectrum of care can be used to generate reference benchmark data that can quantify relative importance of a specialty in constructing diagnostic history elements of computable phenotype definitions.

Project description:BACKGROUND:Creation of a new electronic health record (EHR)-based registry often can be a "one-off" complex endeavor: first developing new EHR data collection and clinical decision support tools, followed by developing registry-specific data extractions from the EHR for analysis. Each development phase typically has its own long development and testing time, leading to a prolonged overall cycle time for delivering one functioning registry with companion reporting into production. The next registry request then starts from scratch. Such an approach will not scale to meet the emerging demand for specialty registries to support population health and value-based care. OBJECTIVE:To determine if the creation of EHR-based specialty registries could be markedly accelerated by employing (a) a finite core set of EHR data collection principles and methods, (b) concurrent engineering of data extraction and data warehouse design using a common dimensional data model for all registries, and (c) agile development methods commonly employed in new product development. METHODS:We adopted as guiding principles to (a) capture data as a byproduct of care of the patient, (b) reinforce optimal EHR use by clinicians, (c) employ a finite but robust set of EHR data capture tool types, and (d) leverage our existing technology toolkit. Registries were defined by a shared condition (recorded on the Problem List) or a shared exposure to a procedure (recorded on the Surgical History) or to a medication (recorded on the Medication List). Any EHR fields needed - either to determine registry membership or to calculate a registry-associated clinical quality measure (CQM) - were included in the enterprise data warehouse (EDW) shared dimensional data model. Extract-transform-load (ETL) code was written to pull data at defined "grains" from the EHR into the EDW model. All calculated CQM values were stored in a single Fact table in the EDW crossing all registries. Registry-specific dashboards were created in the EHR to display both (a) real-time patient lists of registry patients and (b) EDW-generated CQM data. Agile project management methods were employed, including co-development, lightweight requirements documentation with User Stories and acceptance criteria, and time-boxed iterative development of EHR features in 2-week "sprints" for rapid-cycle feedback and refinement. RESULTS:Using this approach, in calendar year 2015 we developed a total of 43 specialty chronic disease registries, with 111 new EHR data collection and clinical decision support tools, 163 new clinical quality measures, and 30 clinic-specific dashboards reporting on both real-time patient care gaps and summarized and vetted CQM measure performance trends. CONCLUSIONS:This study suggests concurrent design of EHR data collection tools and reporting can quickly yield useful EHR structured data for chronic disease registries, and bodes well for efforts to migrate away from manual abstraction. This work also supports the view that in new EHR-based registry development, as in new product development, adopting agile principles and practices can help deliver valued, high-quality features early and often.

Project description:Multiple payment reform efforts are under way to improve the value of care delivered to Medicare beneficiaries, yet few directly address the interface between primary and specialty care.To describe regional variation in outpatient visits for individual specialties and the association between specialty physician-specific payments and patient-reported satisfaction with care and health status.Retrospective cross-sectional study.A 20 % random sample of Medicare fee-for-service beneficiaries in 2012.Regions were grouped into quartiles of specialist index, defined as the observed/expected regional likelihood of having an outpatient visit to a specialist, for ten common specialties, adjusting for age, sex, and race. Outcomes were per capita specialty-specific physician payments and Medicare Current Beneficiary Survey responses.The proportion of beneficiaries seeing a specialist varied the most for endocrinology and gastroenterology (3.7- and 3.9-fold difference between the highest and lowest quartiles, respectively) and least for orthopedics and urology (1.5- and 1.7-fold difference, respectively). Multiple analyses suggested that this variation was not explained by prevalence of disease. Average specialty-specific payments were strongly associated with the likelihood of visiting a specialist. Differences in per capita payments from lowest (Q1) to highest quartiles (Q4) were greatest for cardiology ($89, $135, $172, $251) and dermatology ($46, $64, $82, $124). Satisfaction with overall care (median [interquartile range] across specialties: Q1, 93.3 % [92.6-93.7 %]; Q4, 93.1 % [92.9-93.2 %]) and self-reported health status (Q1, 37.1 % [36.9-37.7 %]; Q4, 38.2 % [37.2-38.4 %]) was similar across quartiles. Satisfaction with access to specialty care was consistently lower in the lowest quartile of specialty index (Q1, 89.7 % [89.2-91.1 %]; Q4, 94.5 % [94.4-94.8 %]).Substantial regional variability in outpatient specialist visits is associated with greater payments with limited benefits in terms of patient-reported satisfaction with care or reported health status. Reducing outpatient physician visits may represent an important opportunity to improve the efficiency of care.

Project description:BackgroundA major problem in treating acute kidney injury (AKI) is that clinical criteria for recognition are markers of established kidney damage or impaired function; treatment before such damage manifests is desirable. Clinicians could intervene during what may be a crucial stage for preventing permanent kidney injury if patients with incipient AKI and those at high risk of developing AKI could be identified.ObjectiveIn this study, we evaluate a machine learning algorithm for early detection and prediction of AKI.DesignWe used a machine learning technique, boosted ensembles of decision trees, to train an AKI prediction tool on retrospective data taken from more than 300 000 inpatient encounters.SettingData were collected from inpatient wards at Stanford Medical Center and intensive care unit patients at Beth Israel Deaconess Medical Center.PatientsPatients older than the age of 18 whose hospital stays lasted between 5 and 1000 hours and who had at least one documented measurement of heart rate, respiratory rate, temperature, serum creatinine (SCr), and Glasgow Coma Scale (GCS).MeasurementsWe tested the algorithm's ability to detect AKI at onset and to predict AKI 12, 24, 48, and 72 hours before onset.MethodsWe tested AKI detection and prediction using the National Health Service (NHS) England AKI Algorithm as a gold standard. We additionally tested the algorithm's ability to detect AKI as defined by the Kidney Disease: Improving Global Outcomes (KDIGO) guidelines. We compared the algorithm's 3-fold cross-validation performance to the Sequential Organ Failure Assessment (SOFA) score for AKI identification in terms of area under the receiver operating characteristic (AUROC).ResultsThe algorithm demonstrated high AUROC for detecting and predicting NHS-defined AKI at all tested time points. The algorithm achieves AUROC of 0.872 (95% confidence interval [CI], 0.867-0.878) for AKI detection at time of onset. For prediction 12 hours before onset, the algorithm achieves an AUROC of 0.800 (95% CI, 0.792-0.809). For 24-hour predictions, the algorithm achieves AUROC of 0.795 (95% CI, 0.785-0.804). For 48-hour and 72-hour predictions, the algorithm achieves AUROC values of 0.761 (95% CI, 0.753-0.768) and 0.728 (95% CI, 0.719-0.737), respectively.LimitationsBecause of the retrospective nature of this study, we cannot draw any conclusions about the impact the algorithm's predictions will have on patient outcomes in a clinical setting.ConclusionsThe results of these experiments suggest that a machine learning-based AKI prediction tool may offer important prognostic capabilities for determining which patients are likely to suffer AKI, potentially allowing clinicians to intervene before kidney damage manifests.

Project description:BackgroundPeripheral artery disease (PAD) affects 8 to 10 million Americans, who face significantly elevated risks of both mortality and major limb events such as amputation. Unfortunately, PAD is relatively underdiagnosed, undertreated, and underresearched, leading to wide variations in treatment patterns and outcomes. Efforts to improve PAD care and outcomes have been hampered by persistent difficulties identifying patients with PAD for clinical and investigatory purposes.ObjectiveThe aim of this study is to develop and validate a model-based algorithm to detect patients with peripheral artery disease (PAD) using data from an electronic health record (EHR) system.MethodsAn initial query of the EHR in a large health system identified all patients with PAD-related diagnosis codes for any encounter during the study period. Clinical adjudication of PAD diagnosis was performed by chart review on a random subgroup. A binary logistic regression to predict PAD was built and validated using a least absolute shrinkage and selection operator (LASSO) approach in the adjudicated patients. The algorithm was then applied to the nonsampled records to further evaluate its performance.ResultsThe initial EHR data query using 406 diagnostic codes yielded 15,406 patients. Overall, 2500 patients were randomly selected for ground truth PAD status adjudication. In the end, 108 code flags remained after removing rarely- and never-used codes. We entered these code flags plus administrative encounter, imaging, procedure, and specialist flags into a LASSO model. The area under the curve for this model was 0.862.ConclusionsThe algorithm we constructed has two main advantages over other approaches to the identification of patients with PAD. First, it was derived from a broad population of patients with many different PAD manifestations and treatment pathways across a large health system. Second, our model does not rely on clinical notes and can be applied in situations in which only administrative billing data (eg, large administrative data sets) are available. A combination of diagnosis codes and administrative flags can accurately identify patients with PAD in large cohorts.