Case Study: How This Chain Of Hospitals Uses AI-Powered Tools To Address Social Determinants In Healthcare

How This Chain Of Hospitals Uses AI-Powered Tools To Address Social Determinants In Healthcare

In the Indian healthcare sector today, it has become extremely important for service providers to study and analyse the social determinants and the non-medical factors of patients, such as age, work, livelihood, socioeconomic status and education, among others, that can heavily influence patients’ health status and its outcomes. 

In a bid to stay relevant in this data-ruled world, an Iowa-based chain of hospitals, clinics, and health care facilities called MercyOne PHSO are trying to identify the prominent social determinants of health affecting their population. With more than 3,10,000 patients under 20+ value-based agreements, MercyOne PHSO’s operations are spread across seven regional delivery networks with more than 870 service locations, including 181 participant organisations and 3,700 total providers. 

The Challenge

While healthcare has a lot of data, 80% of this data is unstructured, distributed across physicians’ hand-written notes, prescriptions, and such. Putting all of this information together is necessary to create a picture of the patient, but finding it, integrating it, and analysing it is a challenge.

Additionally, success in the value-based care environment cannot be achieved based solely on clinical insights. According to a report, clinical care accounts for only 20% of health outcomes, while health behaviours, social and economic factors, and physical environments combined influence the remaining 80% of health outcomes. 

The organisation is required to streamline its strategies to enable engaged and patient-centric care across its system. To accomplish it, MercyOne PHSO set out on an aggressive data integration strategy to connect hundreds of disparate systems across its participant organisations while co-developing an integrated care management solution built on the same data activation platform.

Additionally, to ensure care delivery was holistic in every way, the organisation also needed to identify and address the prominent social determinants of health affecting their population while ensuring efficiency in care. However, the journey was obstructed by multiple challenges. Providing connectivity to tier-2 electronic health records used by rural ambulatory sites was a necessary component to deliver holistic care, but the process became costly and an inefficient venture. However, this data needed to be accessible by care teams in real-time to coordinate care across the network.

Additionally, decentralised care coordination staff and complicated workflows made task handoffs difficult across the care continuum. This also stretched and created challenges in engaging patients post-discharge. Lastly, a lot of the processes were manually-driven with paper-based surveys that had to be transcribed manually and then the data is fed into the EHR, after which it was further processed.

In order to effectively coordinate care, care teams required a daily update on admitted and discharged patients. Still, every acute facility had a different way of working lists that only captured their facility patients. Therefore, the ACO had to adopt a custom automation procedure for every practice site to absorb these feeds daily.

The Solution

In order to identify how the social determinants of health impacted population health, MercyOne PHSO developed strategies to capture non-clinical details from patients — initially deployed at three clinics and later, at four.

The healthcare provider incorporated a streamlined, AI-based data-driven approach powered by Innovaccer’s SDOH Management Solution built on top of their data activation platform to combat the clinical and non-clinical factors impeding quality of care.

Clinical data was ingested from more than 100 disparate clinical systems, including 15 different branded EHRs. Along with that the data also was standardised from multiple data sources such as payer claims, billing files, EHRs, scheduling data, public connections, and admission discharge transfer (ADT) collected from 35+ hospitals.

During this process, the patients were given surveys at registration or in the exam rooms that asked a series of questions, such as, “In the last 12 months, were you worried that your

food would run out before you got money to buy more?” When a patient completed the survey, the results were then evaluated, and based on the answers to these questions, and patients were flagged positive or negative.

In a scenario, if a patient responded ‘yes’ to requiring assistance or identified a need as urgent, a handoff occurred to a community health worker (CHW) to make sure that the patient’s social needs could be addressed. Over time, MercyOne PHSO switched to an app-based survey, compatible with iOS and supportive of multiple languages, which streamlined clinic communication with automatic email notification. This allowed community health workers to meet with patients while they were still on site and connect them with suitable community resources at the point of care.

Over time, MercyOne PHSO switched to Innovaccer’s app-based survey, compatible with iOS and supportive of multiple languages, which was given to patients at the time of registration. Leveraging the app-based survey, an automatic email notification streamlined clinic communication to allow community health workers to meet with patients, while they were still on site and connect them with suitable community resources at the point of care.


Decentralised care coordination staff and complicated workflows made the care management tasks difficult across the continuum. Innovaccer’s suite of solutions helped MercyOne PHSO to cut down on administrative burden significantly.

By utilising the right strategies, the organisation was able to achieve the following outcomes:

MercyOne PHSO successfully conducted screenings for more than 7,000 patients across four clinics in a year, out of which 5,152 were unique, and 487 patients were identified and helped with their social needs.

Switching to the app-based survey reduced the time to document results per patient to 47 seconds, compared to 2.5 minutes with paper-based surveys. From the surveys, it was concluded that food insecurity was the top domain where patients screened positive, followed by transportation needs and health literacy.

As of now, Innovaccer is assisting MercyOne PHSO in understanding the impacts of social determinants of health on an individual patient level for around 11,000 patients. With our SDOH Management solution, MercyOne is aiming to allow the organisation to trigger care protocol based on the responses received from the patient on the survey form. Also, the next steps include the tracking of the effectiveness of the patients working with community resources for different social factors. Also, MercyOne has been trying to enhance the level of transparency and effectiveness in the communications process with the solution within the care teams.

Download our Mobile App

Subscribe to our newsletter

Join our editors every weekday evening as they steer you through the most significant news of the day.
Your newsletter subscriptions are subject to AIM Privacy Policy and Terms and Conditions.

Our Recent Stories

Our Upcoming Events

3 Ways to Join our Community

Telegram group

Discover special offers, top stories, upcoming events, and more.

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Subscribe to our Daily newsletter

Get our daily awesome stories & videos in your inbox