HIM 500 Module 7 Final Project Milestone Three Example

Final Project Milestone Three: Adopt, Defer or Pilot, Technology Recommendations for Bramble Bay

[Student Name]

Southern New Hampshire University

HIM 500: Healthcare Informatics

Final Project Milestone Three

[Instructor Name]

[Date]

The organization, setting and figures below are a composite written as a model document. No real employer, client, colleague or patient is described.

Final Project Milestone Three: Adopt, Defer or Pilot, Technology Recommendations for Bramble Bay

Milestones One and Two built an evaluation process and a legal review for three technologies Bramble Bay Medical Center is considering. This milestone completes the process for each: it states the need, summarizes the findings of each step, scores the options on the agreed weighted criteria and makes a recommendation with conditions, measures and costs.

Defining the Three Needs

Each proposal was tied to a measurable need. For national exchange, the need is that 71% of transfer patients currently arrive without electronic outside records. For decision support, the need is safer prescribing where the Module Six review found inappropriate overrides, especially renal dosing and high-severity interactions. For ambient documentation, the need is documentation burden: hospital data show that outpatient physicians spend an average of 1.6 hours a day in the record outside scheduled clinic time. National studies suggest this is common. Sinsky et al. (2016) found that for every hour physicians spent with patients in ambulatory practice, they spent nearly two more on the record and desk work, and in the event log study by Arndt et al. (2017), record work took up close to half of a primary care physician's long clinic day.

Findings by Evaluation Step

National exchange performed well on every step: it uses established standards, reduces information blocking risk and is supported by evidence that exchange improves care, although Holmgren and Adler-Milstein (2017) found integration of outside data into workflow to be the weakest link nationally, so the hospital must plan for it. The legal review requires segmentation of substance use disorder records before joining. The predictive decision support package had weak local evidence: its deterioration model had not been validated in a population like Bramble Bay's, and the Module Six review showed that adding alerts before rationalization would likely deepen alert fatigue. Ambient documentation had promising but early evidence. Tierney et al. (2024) reported a large rollout across a health system in which thousands of physicians used ambient scribes and generally reported less documentation burden, and Duggan et al. (2025) found reductions in time spent on notes and after-hours work among clinicians who used an ambient scribe. The legal review, however, found open questions about recordings, retention and model training.

Weighted Scores

Table 1 shows the scores on the criteria and weights agreed in Milestone One, each rated from 1 to 5 by the steering committee.

Table 1. Weighted Scores for Three Proposals

Note. Scores assigned by the steering committee; composite data.

Recommendation 1: Adopt National Exchange

Within six months, Bramble Bay should become a participant in national trusted exchange through one of the qualified networks. Conditions are the segmentation of Part 2 records before go-live and a workflow that places outside medications, problems and results where clinicians reconcile them at admission. The target is outside records available for 80% of transfers and electronic medication reconciliation for 60% of transfer admissions within a year. Five-year cost is estimated at $210,000, mostly interface and staff time.

Recommendation 2: Defer the Predictive Package

The predictive decision support package should be deferred for twelve months. During that time, the hospital should complete the medication alert rationalization proposed in Module Six and obtain from the developer the required disclosures describing how every model was built, validated and monitored. After rationalization, each model can be evaluated individually, beginning with a silent trial in which predictions are recorded but not shown, so their accuracy in Bramble Bay's patients can be measured before any alert appears.

Recommendation 3: Pilot Ambient Documentation Under Conditions

Ambient documentation should proceed only as a 16-week pilot with 20 volunteer clinicians in primary care and hospital medicine, and only after the contract settles three conditions: recordings are deleted within 30 days of note signature, the vendor may not use Bramble Bay's recordings to train models without separate written approval and the vendor notifies the hospital of any breach within 48 hours. Patients will be told at check-in and may decline. The pilot will measure after-hours record time, note quality through a monthly audit by health information staff, clinician satisfaction and patient comfort. The health information audit matters because draft notes may contain errors a busy clinician signs without catching.

Why Not All Three at Once

Adopting everything the vendor offers would stretch the informatics team, which has capacity for about one major project per quarter, and would load new alerts and new note workflows onto clinicians at the same time. Sequencing exchange first, the ambient pilot second and predictive tools only after rationalization matches the hospital's capacity and follows the lesson of 2012, when rushed configuration created problems that are still being fixed.

Risks Across the Recommendations

Each recommendation carries risk that leadership should accept knowingly. Exchange could deliver outside records that clinicians do not trust or cannot find, so its success depends on the reconciliation workflow, not just the connection. Deferring the predictive package could mean missing benefits if the models turn out to work well, a risk reduced by the silent trial that will test them locally. The ambient pilot could produce notes with errors that slip into the legal record, which is why health information staff will audit a sample every month and why the pilot can be stopped if error rates exceed an agreed threshold. Finally, the vendor may offer discounts that expire before the evaluation is complete; the steering committee should accept that cost rather than bypass the process that the hospital adopted to avoid repeating 2012.

Conclusion

The evaluation process produced three different answers for three different technologies: adopt national exchange, defer predictive decision support and pilot ambient documentation under strict conditions. Each answer rests on a defined need, evidence, legal review, usability and cost, rather than on vendor timing. The final project will present these recommendations with an implementation roadmap to hospital leadership.

References

Arndt, B. G., Beasley, J. W., Watkinson, M. D., Temte, J. L., Tuan, W.-J., Sinsky, C. A., & Gilchrist, V. J. (2017). Tethered to the EHR: Primary care physician workload assessment using EHR event log data and time-motion observations. Annals of Family Medicine, 15(5), 419-426. https://doi.org/10.1370/afm.2121

Duggan, M. J., Gervase, J., Schoenbaum, A., Hanson, W., Howell, J. T., Sheinberg, M., & Johnson, K. B. (2025). Clinician experiences with ambient scribe technology to assist with documentation burden and efficiency. JAMA Network Open, 8(2), Article e2460637. https://doi.org/10.1001/jamanetworkopen.2024.60637

Holmgren, A. J., & Adler-Milstein, J. (2017). Health information exchange in US hospitals: The current landscape and a path to improved information sharing. Journal of Hospital Medicine, 12(3), 193-198. https://doi.org/10.12788/jhm.2704

Sinsky, C., Colligan, L., Li, L., Prgomet, M., Reynolds, S., Goeders, L., Westbrook, J., Tutty, M., & Blike, G. (2016). Allocation of physician time in ambulatory practice: A time and motion study in 4 specialties. Annals of Internal Medicine, 165(11), 753-760. https://doi.org/10.7326/M16-0961

Tierney, A. A., Gayre, G., Hoberman, B., Mattern, B., Ballesca, M., Kipnis, P., Liu, V., & Lee, K. (2024). Ambient artificial intelligence scribes to alleviate the burden of clinical documentation. NEJM Catalyst, 5(3). https://doi.org/10.1056/CAT.23.0404