Integrating Clinical Classifications Software Refined (CCSR), Process Indicators, and Geographic Information System (GIS) Mapping to Inform Population Health Management: Development of an Interactive Dashboard (Preprint)
Bibliographic record
Abstract
Background: Population health management requires tools that transform complex clinical data into actionable insights to guide care coordination, community outreach, and system-level planning. Objective: The objective of this study is to develop and apply a population health intelligence dashboard that integrates inpatient utilization, process indicators, and health status data for patients with diabetes mellitus, using a clinically meaningful classification system and geospatial visualization. Methods: We used data from the SingHealth Diabetes Registry (SDR; 2019-2024) to build an interactive dashboard using R Shiny (Posit Software). A semiautomated mapping algorithm was developed to map ICD-10-AM (International Classification of Diseases, 10th Revision, Australian Modification) principal diagnosis codes into CCSR (Clinical Classifications Software Refined) categories. We built an interactive dashboard in R Shiny incorporating 3 analytic domains: inpatient utilization (by admission count, length of stay, and prolonged stays), diabetes care process indicators, and health status indicators (eg, comorbidities, laboratory results, and diabetes-related complications). Geographic information system mapping enabled spatial visualization by patients' residential locations. Results: Diabetes mellitus with complication (END003) was the leading cause of admission (7.0%-8.1% annually), followed by pneumonia (RSP002, 3.7%-5.1%), fluid and electrolyte disorders (END011, 3.4%-4.1%), and skin infections (SKN001, 2.8%-3.1%). In 2024, top ICD-10-AM diagnoses under END003 included E1122-type 2 diabetes mellitus with established diabetic nephropathy, E1173-type 2 diabetes mellitus with foot ulcer due to multiple causes, and E1172-type 2 diabetes mellitus with features of insulin resistance. For END011, the most frequent diagnosis codes were E877-fluid overload, R18-ascites, E875-hyperkalemia, and hypo-osmolality and hyponatremia. In total, SingHealth Diabetes Registry patients accounted for 687,062 inpatient bed days in 2024. Circulatory conditions (eg, cerebral infarction and heart failure) contributed 124,417 (17.7%) bed days, while injuries (eg, hip fractures and surgical complications) accounted for 86,541 (12.6%) bed days. CCSR-based analyses revealed distinct patterns when comparing conditions driving admission frequency versus prolonged length of stay. GIS mapping identified residential clusters with high inpatient utilization, unmet care processes, and poor cardiometabolic control, supporting region-specific intervention planning. Conclusions: The dashboard demonstrates a novel, interactive approach to visualizing inpatient utilization, care gaps, and health status, enabling targeted, place-based interventions. It represents a scalable framework for operationalizing population health intelligence across other chronic disease areas and health care systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".