AI in Healthcare: Transforming Physical Therapy Practice
AI is already transforming healthcare by increasing administrative efficiency, reducing cognitive load on providers, and streamlining health information for patients at home. The existence of this powerful but imperfect technology cannot be denied. During my 13 years of clinical experience in physical therapy (PT), I have watched AI move from the periphery of our work to the edges of our clinical thinking. As physiotherapists, we should not decide whether AI will find its way into our clinics, but rather how.
This shift can be uncomfortable, but it also presents us with an opportunity to use AI responsibly so that it enhances the strengths of physical therapists and fills known gaps, rather than replacing valuable experience and expertise. Technologies once reserved for administrative tasks can now help us uncover evidence faster, identify clinical patterns earlier, and extend patient care beyond the clinic.
The true promise of AI lies not in the autonomy of the doctor or the machine, but in balanced collaboration that strengthens the strengths of both.
Maximizing Patient Care
Providing the best possible care for our patients is our top priority as clinicians. It is our responsibility to make the most of the reliable technology available to us and to remain open to new advances.
We have long known that poor patient adherence is one of the main reasons for poor physical therapy outcomes. There are many reasons why a patient may struggle with this: uncertainty about whether they are doing the exercises correctly, difficulty integrating an exercise program into their daily schedule, or a lack of understanding of how the program will help their condition, to name a few. Patient integration into home programs is an impressive example of what can be meaningfully supported by AI.
Computer vision technology can be used to help patients perform their home exercises. The goal of this technology isn’t just to tell someone they’re moving incorrectly – it’s about more than just correcting form. As physical therapists, we want to promote movement by using this technology to teach patients new exercises, engage with them as they move, and collect valuable patient feedback. This technology can provide information about movement modifications if a patient is having difficulty or recommend progression so that the patient’s physical therapist can review the exercise if they think an exercise is too easy, rather than having the patient wait until the next appointment. Valuable insights can then be passed on to the physical therapist, who remains the primary decision maker for the patient’s care.
The use of AI agents or chatbots can also help expand medical care beyond the clinic. These tools can be developed to incorporate patients into their home routine and help them build habits to help them incorporate exercise into their schedule. Educational components of a treatment plan, such as education about pain neuroscience, can be reiterated through sensitive conversations. Again, the goal of these tools is not to replace the provider. When implemented carefully, these tools will engage patients while collecting information that can be summarized for a physical therapist to easily determine if changes to a treatment plan are needed.
The end result? It is responsible and necessary to use AI wisely to support adherence and engagement under the supervision of physical therapists.
Improving Clinical Decision Making
Clinical decision making is not purely mechanical or logistical, but rather interpretive, contextual, and relational. The potential of AI comes from strengthening the doctor’s intuition through reliable, reproducible input. Human doctors can vary greatly in their judgments and are prone to bias. Inter- and intra-rater variability is well documented in physical therapy assessments, including joint palpation, motion and posture analysis, and range of motion measurement.
For example, a 2016 study published in the Journal of Orthopaedic & Sports Physical Therapy (JOSPT) showed that physical therapists exhibited anchoring bias when measuring passive wrist range of motion when they were given different historical information about the patient before the measurement. AI algorithms can help reduce this variability by providing stable baselines and highlighting discrepancies.
We must strive to achieve synergy between AI and human clinicians, meaning that the best capabilities of both complement each other and become even greater than the sum of their parts. To achieve this, any tool developed to support clinical work must also incorporate expert clinical input into its development, from the brainstorming process through implementation, daily use, and regular iteration. If practicing clinicians perceive AI as opaque, intrusive, or inconsistent with their goals, they will rightly drop out or reflexively override it. The solution is a dynamic equilibrium in which clinicians neither reject nor bow to AI, but rather engage with it as a thought partner.
It can take decades for new research findings to be standardized across clinical care. AI can help make these new standards commonplace by synthesizing evidence and making important research quickly available to clinicians. However, many of these tools cannot yet consistently assess the quality of the sources or study design. The responsibility for determining the quality and reliability of these sources still lies solely with physicians.
Remember: Decision quality improves when reliable, reproducible input meets expert clinical interpretation.
Meet Patients Where They Are
The New York Times recently cited a survey by the health policy research group KFF that found, “Last year, about one in six adults — and about a quarter of adults under 30 — used chatbots to find health information at least once a month.”
These days, the world of advice for people in pain is so noisy that countless online voices offer recommendations that may ultimately lead to worsening of their symptoms. Currently, these online recommendations are louder than some of the more evidence-based and optimistic advice about pain and exercise, which may result in AI models uncovering less reliable information for people seeking relief. A 2025 study examined the performance of several widely used Large Language Models (LLMs) and found high variability and inconsistent accuracy compared to published clinical practice guidelines for lumbosacral radicular pain.
Since it’s no secret that patients are already using LLMs like ChatGPT to learn more about their conditions, I invite you to bring your insights to our sessions. This represents a valuable opportunity to explain how I combined their history, exam results, imaging if appropriate, and their goals with the best available evidence to create the plan. Using this method, we as experts can guide patients toward safer self-education and correct misinformation in real time.
Ultimately, AI should be viewed as a bridge and not a barrier. These teachable moments strengthen health literacy and ensure care is based on guidelines and context.
An Optimistic Future with Thoughtful Design
The promise of AI in the PT clinic is to redirect the cognitive energy of physicians toward the type of thinking that is uniquely human: interpreting data with a lens that incorporates clinical history, patient beliefs, and experience gained through years of treating patients.
I am excited about the potential of AI, when used responsibly, to shorten the distance between evidence and practice, help new clinicians build sound clinical reasoning, and give us earlier signals when a plan may need to change. At its best, AI can take our potential as clinicians to new levels, as long as we set guardrails, measure what matters, and maintain our identity as movement experts who combine science, skill, and relationship.
Photo: Irina_Strelnikova, Getty Images
Dr. Claire Morrow is a doctor of physical therapy and director of clinical consultation at Hinge Health. Their responsibilities include supporting members, educating physical therapists in evidence-based practices, advising product leaders, and contributing to commercial initiatives. She serves as the physical therapist representative on Hinge Health’s clinical leadership team. Dr. Morrow is a board-certified orthopedic clinical specialist and a member of the American Academy of Orthopedic Manual Physical Therapy. She is also a clinical instructor at the Kaiser Permanente Northern California Orthopedic Physical Therapy Residency and supervises newly licensed physical therapists. Her previous experience includes outpatient care in hospital clinics, on-site clinics with employers, and working with professional athletes. Her professional mission is to empower individuals to better understand pain, improve function, and improve their quality of life.
This article appears on the MedCity Influencer Program. Through MedCity Influencer, anyone can publish their views on business and innovation in healthcare on MedCity News. Click here to find out how.
Source: Here
“`
