
Table of Contents
You’re looking up your symptoms online, and increasingly, so is your clinician. They’re not using Google but a new generation of AI clinical decision support tools. CDS tools, including clinical guidelines, medication alerts, and diagnostic checklists, have been part of the health care system for decades, but the emergence of large language models and machine learning-based systems has transformed what these tools can do.
Why Community Health Centers Are Exploring AI Clinical Decision Support
Community health centers are starting to explore the benefits of AI clinical decision support tools to support clinicians who manage patients’ wide-ranging medical, social, and behavioral health needs. When Rural Health Quarterly spoke with CHCs, they expressed excitement about the value these tools can bring to clinical care but also real concerns about the accuracy of the recommendations generated, overreliance that may impair clinical judgment, and bias in the underlying data.
Key Questions Before Adoption
Dr. Hakeem Adeniyi, Jr., chief clinical officer at the Sacramento Native American Health Center, says he always asks: “Is it HIPAA compliant? Is it evidence-based? Where is the information coming from, and what is its source material?” when considering AI clinical decision support tools for his clinic.
How AI Clinical Decision Support Tools Work in Practice
New AI CDS tools are spreading quickly partly because they are so accessible. Many are free or low-cost and are embedded directly into electronic health records or available on clinicians’ phones, allowing use at the point of care without toggling to another system. Clinicians can ask questions in plain language and get clarifying questions back in near-real time, with the tools synthesizing new information dynamically. “It will incorporate the previous questions into its new answer. It’s not static, but a dynamic process that tries to incorporate additional things as you go along,” Adeniyi notes.
Personalizing Care for Diverse Populations
A clinician can take a photo of a rash and instantly compare it across a full spectrum of skin tones, or ask for tailored nutrition guidance for a patient with diabetes. This personalization capability makes AI clinical decision support especially valuable for health centers serving clients with diverse ethnic, cultural, and linguistic backgrounds. “Telling patients to stop eating tortillas, when they grew up on tortillas and ate them their whole life, is not a practical solution,” Adeniyi notes.
AI Clinical Decision Support as a Workforce Multiplier
For CHCs facing persistent workforce shortages and rising patient complexity, these tools can feel like adding another colleague to the team. “It is like having a Ph.D. research assistant,” says Dr. Liz Powers, health services officer at Winding Waters Clinic in eastern Oregon. “It doesn’t give you a medical degree. But if you have a medical degree and understand what you’re asking and what you’re looking for, it is game-changing.”
Why Keeping Clinicians in the Driver’s Seat Matters
Retaining clinician oversight over AI clinical decision support is essential. Though some specific AI tools have shown empirical benefits for patient health, a recent evaluation of publicly available tools shows they consistently perform poorly on tasks related to early diagnostic reasoning, a keystone of primary care practice. According to the study, the risk is not just that these models are sometimes wrong, but that their reasoning is brittle precisely where uncertainty and nuance matter most.
Testing AI Clinical Decision Support Before Rollout
To alleviate concerns about accuracy, Adeniyi says he tested the tool against his own clinical judgment before introducing it to colleagues. “I used [the tool] for several weeks beforehand just to see how it worked. I really tested it out, asking a ton of clinical questions to validate that it was something I could use. Then I introduced it to the other clinicians. I wanted them to experiment and see how it felt,” he says.
Concerns About Diagnostic Skill Erosion
Still, some worry these tools will mean clinicians become less practiced at the slow, effortful diagnostic reasoning in which they were trained. “When it just gets fed to you, you stop doing the mental math of having to look things up and think things through and put things together,” says Dr. Jason Cunningham, chief executive officer at West County Health Centers. At the same time, Cunningham notes these tools can be an important support for newer clinicians who make up a substantial portion of CHC staff. “It’s helpful for my right-out-of-school clinicians making really complex decisions. I want them to feel comfortable staying in this complex environment.”
Oversight Challenges Facing AI Clinical Decision Support
Given the low-cost, accessible, real-time guidance these tools offer, use is growing rapidly, sometimes without an organization’s endorsement or awareness. Keeping abreast of the changing landscape, with new tools marketed directly to individuals rather than organizations, poses new liability and leadership challenges. “I’m sure [clinicians] are using things we don’t even know about, so it’s important we stay informed and can offer things we’d like them to use,” notes Alison Connelly-Flores, chief medical information officer at Urban Health Plan in New York City.
Building a Framework for Governance
Community health centers need new approaches to govern AI clinical decision support tools. The American Medical Informatics Association highlights several key recommendations for further research, validation, and oversight to address significant concerns about patient safety and equity. Kimberly Beauchesne, vice president of digital strategy and innovation at CHAS Health, describes the importance of selecting a high-quality, nonproprietary, transparent, and flexible AI decision support vendor. “We’re putting pieces of a puzzle together,” she says, “and the picture keeps changing. That’s just the reality we are in… The strategy is flexibility and not committing until we see where the front-runners emerge. The list is getting shorter.”
