Abstract
Background
Clinical decision support system (CDSS) alerts may help retain people living with HIV (PLWH) in care. A system of CDSS alerts utilizing the CHORUS™ portal was developed to identify PLWH at risk of being lost to care. To evaluate feasibility for a larger scale study, a before and after implementation research pilot study was implemented in the OPERA Cohort at three clinic sites in a southeastern US city.
Methods
Periods without intervention (before) or with CDSS alerts (after) were followed by 3 months of follow up. The study population consisted of PLWH with ≥ 1 electronic health record entry in the 2 years prior to, or during, the before or after period (Fig 1). To support clinicians through a discrete implementation strategy, alerts warning of suboptimal patient attendance were generated daily for the eligible PLWH at each site; providers or other clinic staff could respond to the alerts (Fig 2). Alerts, responses, and visits (i.e., meeting with provider or HIV lab measurement) were characterized. The proportion of PLWH with ≥ 1 visit in the before and after periods were compared at each site by Pearson’s Chi-square.
Figure 1. Pilot study timeline
Figure 2. CDSS alert criteria and response options
Results
A total of 12,230 PLWH were eligible (sites A: 11,271; B: 733; C: 1,344 PLWH), with > 75% in both the before and after periods. The ratio of alerts to responses was 11.9 at site A (2,245 alerts to 189 responses in 309 days; Fig 3A), and comparatively lower at sites B (756 alerts to 334 responses in 352 days, ratio=2.2; Fig 3B) and C (1,305 alerts to 896 responses in 246 days, ratio=1.5; Fig 3C). Responses to alerts were sporadic at sites A and B and consistent at site C. After the intervention, the proportion of PLWH with ≥ 1 visit stayed the same at site A (46% in both periods; p=0.47), decreased at site B (91% to 80%; p< 0.01), and increased at site C (72% to 81%; p< 0.01).
Figure 3. Alerts and responses over time in (A) Site A, (B) Site B, and (C) Site C
Conclusion
This pilot study was ecological by design: measures of retention in care were compared over two calendar periods, without accounting for changes in study populations, clinic characteristics, and policies in place over time (which could have impacted clinic attendance). Though engagement with the CDSS was suboptimal at some sites, this implementation pilot study has demonstrated the ability to implement a CDSS aimed at identifying at-risk PLWH, while highlighting areas for improvement in future larger scale studies.
Disclosures
Joel Wesley Thompson, MHS, PA-C, AAHIVS, DFAAPA, MHS, PA-C, AAHIVS, DFAAPA, Gilead (Shareholder, Speaker’s Bureau)Janssen (Speaker’s Bureau)Theratechnologies (Speaker’s Bureau)ViiV (Speaker’s Bureau) Tammeka Evans, MoP, ViiV Healthcare (Employee)
Randomized pilot study and qualitative evaluation of a clinical decision support system for brain tumour diagnosis based on SV 1H MRS: Evaluation as an additional information procedure for novice radiologists
