Opinion | AI Helped Heal My Chronic Pain

My lab tests came up normal, and nothing I tried worked. Then Claude came along.

Tom Rosenblatt

May 13, 2025 at 4:49 pm ET

Some content could not be imported from the original document. View content ↗

Journal Editorial Report: The week’s best and worst from Kim Strassel, Allysia Finley and Kyle Peterson.

I used to pride myself on my quick mind—before unexplained, relentless pain stole my focus. My days blurred with crushing headaches, stomach spasms and overwhelming fatigue, even though my lab tests read “normal” for a 30-year-old. Five months on a carnivore diet, medications, water-only fasts and qigong did nothing to lift the fog. Then, an unexpected lifeline arrived in the form of an artificial-intelligence chatbot named Claude.

I turned to AI out of desperation, after cycling through countless specialists with no unified approach. A neurologist focused on my head pain but not my diet; a gastroenterologist examined gut inflammation and ignored my migraines; an ear, nose and throat doctor probed sinus inflammation, missing other factors. Each offered partial help, but no one connected all the dots.

Modern medicine is compartmentalized, which can work for acute injuries. But chronic conditions demand cross-specialty coordination. Inflammation, diet and stress are intertwined. AI’s broad-based knowledge provided the holistic lens I needed.

AI already is being used to read X-rays and help develop new drugs. I needed it to sort through a mountain of daily pain logs, sleep patterns and academic studies. Each morning, I would note whether migraines spiked after a midnight snack or if magnesium supplements helped. Claude’s pattern analysis spotted connections that time-crunched doctors simply aren’t equipped to see.

A study of 2008 data found that chronic pain costs today’s U.S. economy about $900 billion a year, adjusted for inflation. That’s more than heart disease and cancer combined, according to the National Academy of Medicine. One in 5 American adults— 50 million people—live with chronic pain. Our healthcare system is great at treating broken bones but falters when dealing with lingering aches and fatigue. Who unifies the data from many specialists? Meanwhile, physicians—nearly half of whom report burnout—juggle thousands of patients. These doctors don’t have time to parse months of smart-watch logs during a 15-minute appointment.

That’s precisely where AI excelled. It kept track of my treatments, suggested overlooked interventions and uncovered trigger patterns. While ChatGPT often defaults to strict guardrails around medical advice, platforms like Grok and Claude are less restricted. Instead of being told, “Try this drug, come back in four months,” I had immediate insights into medicine and lifestyle tweaks that, taken together, made a big difference.

Armed with these insights, I came up with a three-part plan: medications coordinated across six specialists; lifestyle changes, such as a strict bedtime and daily walks; and practices including qigong and meditation. After no success with numerous insurance-mandated cheaper drugs, I found a migraine medication—ultimately covered by insurance—that offered partial relief with minimal side effects. Meanwhile, Claude suggested taking the supplement quercetin before meals to reduce inflammation—a step that I believe slashed my post-meal flares.

By harnessing AI to recognize patterns, we can transform chronic-illness treatment. Imagine an integrated clinic in which specialists, nurses and patients feed data into one AI-powered platform—combining wearable sensors like smart watches, daily symptom logs and complete patient histories. That isn’t science fiction. The logistics and finance industries have done this for decades, and healthcare should follow suit. AI can weave together oncology, endocrinology, nutrition and mental health, reflecting that the body is one interconnected system.

Picture an AI concierge guiding a person’s care 24/7, flagging the precise moments a doctor is needed. That would ease emergency-room overload, save billions of dollars in lost productivity, and spare patients years of diagnostic limbo. The Association of American Medical Colleges forecasts a shortfall of 83,000 physicians by 2030—already causing long waits for care—positioning AI to fill gaps where overextended providers fall short. Yes, liability concerns are real, but banning medical AI over malpractice fears is shortsighted. Well-crafted policies can shape AI’s integration responsibly.

Here are three steps to make it mainstream: First, implement “medical accuracy” scoring for AI models—similar to how we benchmark coding or math models—to ensure safe, high-quality medical guidance. Second, teach medical students and doctors to embrace AI as an indispensable ally, not a rival. Third, empower patients with AI access so they can share detailed information, and not just random recollections, with clinicians.

If AI could discern a plan after my so-called normal tests—and help me reclaim clarity—imagine what it could do for millions who were otherwise told simply to manage stress or live with pain. AI isn’t a magic bullet. But it uncovers hidden connections in data at speeds no human can match, freeing doctors to focus on what they do best: care. For chronic illness sufferers, that data-driven guidance may be the difference between endless agony and a path out of pain.

Mr. Rosenblatt is a recent graduate of the Stanford Graduate School of Business.

Photo: Thomas Fuller/Zuma Press

Appeared in the May 14, 2025, print edition as 'AI Helped Heal My Chronic Pain'.