Hands on the Medical Informatics Initiative Core Data Set - Lessons Learned from Converting the MIMIC-IV

A Standardized Clinical Data Harmonization Pipeline for Scalable AI Application Deployment (FHIR-DHP): Validation and Usability Study

BACKGROUND

Increasing digitalization in the medical domain gives rise to large amounts of health care data, which has the potential to expand clinical knowledge and transform patient care if leveraged through artificial intelligence (AI). Yet, big data and AI oftentimes cannot unlock their full potential at scale, owing to nonstandardized data formats, lack of technical and semantic data interoperability, and limited cooperation between stakeholders in the health care system. Despite the existence of standardized data formats for the medical domain, such as Fast Healthcare Interoperability Resources (FHIR), their prevalence and usability for AI remain limited.

OBJECTIVE

In this paper, we developed a data harmonization pipeline (DHP) for clinical data sets relying on the common FHIR data standard.

METHODS

We validated the performance and usability of our FHIR-DHP with data from the Medical Information Mart for Intensive Care IV database.

RESULTS

We present the FHIR-DHP workflow in respect of the transformation of "raw" hospital records into a harmonized, AI-friendly data representation. The pipeline consists of the following 5 key preprocessing steps: querying of data from hospital database, FHIR mapping, syntactic validation, transfer of harmonized data into the patient-model database, and export of data in an AI-friendly format for further medical applications. A detailed example of FHIR-DHP execution was presented for clinical diagnoses records.

CONCLUSIONS

Our approach enables the scalable and needs-driven data modeling of large and heterogenous clinical data sets. The FHIR-DHP is a pivotal step toward increasing cooperation, interoperability, and quality of patient care in the clinical routine and for medical research.

Association of geriatric nutritional risk index with all-cause hospital mortality among elderly patients in intensive care unit

Background

Malnutrition is associated with poor outcomes for geriatric patients in intensive care unit (ICU). It is important to identify patients at risk of malnutrition and provide individual nutrition support. The assessment of malnutrition risk is not easy for these patients due to their cognitive impairment. Geriatric nutrition risk index (GNRI) is a simple and objective scoring tool to evaluate the risk of malnutrition in elderly patients. In this study, we aimed to see whether GNRI score was appropriate to predict clinical outcomes among geriatric patients in the setting of ICU.

Materials and methods

Elderly patients with age ≥ 65 years were extracted from Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Categories based on GNRI were classified as major risk (GNRI <82), moderate risk (GNRI 82 to <92), low risk (GNRI 92 to ≤98), and no risk (GNRI >98). The primary outcome was all-cause hospital mortality. Multivariable Cox proportional hazards regression models and restricted cubic spline were used to investigate associations of GNRI with hospital mortality, respectively. A two-piecewise linear regression model was applied to examine the inflection point of GNRI on hospital mortality. To reduce selection bias, propensity score matching (PSM) was used in a 1:1 ratio.

Results

A total of 3,696 geriatric patients were finally included with median age 75 (69, 81) years. The prevalence of major risk was 28.6%. In the fully adjusted model, GNRI categories featured a negative trend with hospital mortality (p for trend = 0.037). Restricted cubic spline analysis demonstrated an L-shaped relationship between GNRI and hospital mortality before and after matching. The inflection point was 78.7. At the left side of inflection point, GNRI levels were significantly negatively associated with hospital mortality (HR = 0.96, 95% CI: 0.94-0.98; p < 0.001) and featured no significant relations at the right side. Multiple linear regression also showed that GNRI was negatively associated with length of stay in hospital.

Conclusion

The major risk of malnutrition defined by GNRI was able to predict poor prognosis for geriatric patients admitted to ICU.