Establishing Medical Intelligence - Leveraging FHIR to Improve Clinical Management: a retrospective cohort and clinical implementation study.

BACKGROUND: FHIR (Fast Healthcare Interoperability Resources) has been proposed to enable health data interoperability. So far, its applicability has been demonstrated for selected research projects with limited data. OBJECTIVE: Here, we designed and implemented a conceptual medical intelligence framework to leverage real-world care data for clinical decision-making. METHODS: A Python package for the utilization of multimodal FHIR data (FHIRPACK) was developed and pioneered in five real-world clinical use cases, i.e., myocardial infarction (MI), stroke, diabetes, sepsis, and prostate cancer (PC). Patients were identified based on ICD-10 codes, and outcomes were derived from laboratory tests, prescriptions, procedures, and diagnostic reports. Results were provided as browser-based dashboards. RESULTS: For 2022, 1,302,988 patient encounters were analyzed. MI: In 72.7% of cases (N=261) medication regimens fulfilled guideline recommendations. Stroke: Out of 1,277 patients, 165 patients received thrombolysis and 108 thrombectomy. Diabetes: In 443,866 serum glucose and 16,180 HbA1c measurements from 35,494 unique patients, the prevalence of dysglycemic findings was 39% (N=13,887). Among those with dysglycemia, diagnosis was coded in 44.2% (N=6,138) of the patients. Sepsis: In 1,803 patients, Staphylococcus epidermidis was the primarily isolated pathogen (N=773, 28.9%) and piperacillin/tazobactam was the primarily prescribed antibiotic (N=593, 37.2%). PC: Three out of 54 patients who received radical prostatectomy were identified as cases with PSA persistence or biochemical recurrence. CONCLUSIONS: Leveraging FHIR data through large-scale analytics can enhance healthcare quality and improve patient outcomes across five clinical specialties. We identified i) sepsis patients requiring less broad antibiotic therapy, ii) patients with myocardial infarction who could benefit from statin and antiplatelet therapy, iii) stroke patients with longer than recommended times to intervention, iv) patients with hyperglycemia who could benefit from specialist referral and v) PC patients with early increases in cancer markers.

Effectiveness of Endovascular Recanalization Treatment for M2 Segment Occlusion: Comparison Between Intracranial ICA, M1, and M2 Segment Thrombectomy.

RATIONALE AND OBJECTIVES: Mechanical thrombectomy is common practice in proximal anterior vessel occlusion. However, it remains unclear whether peripheral artery occlusions should be treated as well. This retrospective study aimed to prove the effectiveness of endovascular recanalization treatment for the M2 segment by comparison of intracranial internal carotid artery (ICA), M1 segment, and M2 segment thrombectomy. MATERIALS AND METHODS: All patients who received endovascular treatment for distal ICA, M1, or M2 segment occlusions between January 2010 and July 2017 at our center were re-analyzed with respect to reperfusion success, interventional and clinical parameters. Statistical analysis was performed by Mann Whitney test, Chi square test, and Spearman correlation analysis. RESULTS: A total of 261 patients (median age, 72 years), 100 with ICA, 137 with M1, and 24 with M2 segment occlusion, were included. Duration of endovascular treatment was significantly longer in ICA occlusions (median, 83 minutes, p < 0.001) compared to M1 (56 minutes) or M2 segment occlusions (49 minutes). Recanalization and reperfusion success and rate of endovascular complications did not differ between occlusion sites (AOL, p = 0.071; mTICI, p = 0.540; complications, p = 0.064). No significant difference in revascularization success was found between the different thrombectomy devices (direct thrombus aspiration, stent retrieving, or a sequential combined approach; p = 0.112). Successful M2 recanalization (mTICI 2b-3) correlated significantly with stronger posttherapeutic NIHSS reduction (r = 0.691, p < 0.001). CONCLUSION: We found endovascular treatment of M2 segment occlusions as safe and successful as endovascular therapy of the ICA or M1 segment, with stronger posttherapeutic NIHSS reduction after successful compared to insufficient M2 recanalization.

Automated ASPECT rating: comparison between the Frontier ASPECT Score software and the Brainomix software.

PURPOSE: Computer-aided diagnosis (CAD) appears promising in early ischemic change detection computed tomography (CT). This study aimed to compare the performance of two new CAD systems (Frontier ASPECTS Prototype and Brainomix) with two experienced readers in selected patients with suspected acute ischemic stroke. METHODS: Retrospectively, non-contrast brain CTs of 150 patients suspected for acute middle cerebral artery ischemia were analyzed with respect to ASPECTS first separately, than in consensus by two senior radiologists, and by use of Frontier and Brainomix. Besides the fully automatic Frontier and Brainomix readings (Frontier_1, Brainomix_1), readings adjusted for the affected brain side (known by CT angiography or clinical presentation, Frontier_2, Brainomix_2) were assessed. Statistical analysis was performed by intraclass correlation and Bland-Altman statistics. RESULTS: The score-based ASPECTS readings of Brainomix_1, Brainomix_2, both radiologists, and the expert consensus reading correlated highly (r = 0.714 to 0.841; always p < 0.001), whereas Frontier_1 and Frontier_2 correlated only lowly or moderately with both radiologists, the expert consensus reading, and Brainomix (r = 0.471 to 0.680; always p < 0.001). Bland-Altman analysis revealed lower mean ASPECT difference and standard deviation of difference for Brainomix_2 (mean difference = -0.2; SD = 1.15) compared to Frontier_2 (mean difference = 1.2; SD = 1.76). Correlation of region-based ASPECTS reading with the expert consensus reading was moderate for Brainomix_2 (r = 0.534), but only low for Frontier_2 (r = 0283; always p < 0.001). CONCLUSION: We found high agreement in ASPECTS rating between both radiologists, expert consensus reading, and Brainomix, but only low to moderate agreement to Frontier.