Sponsored by
Every year, 795,000 Americans are killed or permanently disabled because a doctor got the diagnosis wrong. That makes diagnostic errors the third leading cause of death in the U.S. — behind only heart disease and cancer.
Pratik Desai's mother nearly became one of them. When she was diagnosed with Stage 4 duodenal adenocarcinoma — a rare and aggressive small-intestine cancer — Desai, a 34-year-old systems integrator from New Jersey with zero medical training, did something unusual. He built an AI workflow to fight back.
Trading options is complicated. Liquid simplifies your trading strategies.
Trading options can be highly profitable; it can also be highly unprofitable. The problem is that trading options is tough:
Option decay is real
Picking expiration dates is crucial
Market makers scalp retail traders
Liquid allows anyone to trade perpetual futures, or “perps”. Perps are options without an expiration date.
This means you don’t need to worry about Greeks, simply
Pick an asset
Pick long or short
Determine your collateral
Determine your leverage
Place your trade
Getting started is simple too; start to finish in less than 10 minutes:
Login with google
No-KYC
Deposit with Apple Pay or your bank account
Trade
Trading volatility doesn’t need to be harder than absolutely necessary.
A non-medical professional used Claude and NotebookLM to manage his mother's cancer care — and the AI caught a CAT scan error, identified a Christmas Day pulmonary embolism, and detected a hidden bleeding pattern her doctors missed. Three interventions that likely extended her life. Plus: a prompt that turns you into your family's AI-powered medical advocate.
🧠 The Workflow That Caught What Doctors Missed
Desai's system was deceptively simple: export his mother's daily records from Epic, feed them into NotebookLM to synthesize the data, then run the synthesis through Claude to generate questions for her care team.
As her records ballooned to 1,600 pages, no single doctor could hold the full picture in their head. The AI could.
The results were staggering. On at least three separate occasions, the AI flagged emergencies her doctors either missed or would have caught too late:
🔴 A CAT scan report error — The AI identified anomalies in imaging reports before they affected her treatment plan.
🔴 A Christmas Day pulmonary embolism — No doctor answered the phone on December 25th. Desai typed his mother's symptoms into Claude. It identified probable pulmonary embolism complications. The ER line would have taken 4-5 hours to call back. His cousin — a doctor — confirmed, and they got her to the hospital.
🔴 A hidden post-transfusion bleeding pattern — The AI detected that his mother was bleeding out every seven days after blood transfusions. The cause: being moved from a liquid diet to solid food 48 hours post-infusion, which irritated her ulcer. No human had connected those dots across 1,600 pages.
🔄 The Uncomfortable Truth
Doctors often push back on AI in medicine by saying it "hallucinates." Desai's response is worth sitting with: what if we graded the medical system by the same standards we grade AI?
A 2024 JAMA study found that 23% of hospitalized patients who died or were transferred to ICU had experienced a diagnostic error. Johns Hopkins estimates that cutting diagnostic errors by just 50% for five conditions — stroke, sepsis, pneumonia, blood clots, and lung cancer — would prevent 150,000 deaths per year.
Desai's mother lived 76 days after her diagnosis. She spent 67 of them as an inpatient. The AI didn't cure her cancer. But it gave her family more time — and it gave her dignity.
The Prompt (Copy This)
You are a medical records analyst and patient advocacy assistant. Before you help me, ask me these questions one at a time and wait for my response to each:
1. What is the patient's diagnosis or primary medical concern?
2. What is your relationship to the patient (self, spouse, parent, child, other)?
3. How would you rate your medical knowledge? (No background / Some familiarity / Healthcare professional)
4. What specific concern or question are you trying to address right now? (Example: understanding test results, preparing for a doctor visit, spotting inconsistencies in treatment, tracking symptoms over time)
5. Do you have any medical documents, test results, or notes you'd like me to help analyze? (If yes, paste them after this conversation)
Once you have my answers, do the following:
- Summarize what you understand about my situation in plain language
- Based on my concern, generate 5 specific questions I should ask the care team at the next appointment
- Flag any areas where I should request a second opinion or additional testing
- If I paste medical records or test results, scan for inconsistencies, flag anything that looks unusual, and explain what each result means in language matched to my medical knowledge level
- Create a simple tracking template I can use going forward to log symptoms, medications, and questions between visits
Important: You are not a doctor. Always recommend professional medical consultation. Your role is to help me be a better-informed advocate — not to diagnose or prescribe.
Prompt Proof Table
| PROFILE | SITUATION | AI OUTPUT HIGHLIGHTS |
|---|---|---|
| 👩 Sarah, 41 Daughter caring for father with Parkinson's |
No medical background. Father's medication list keeps changing. Confused by conflicting info from specialists. | Generated questions about drug interactions between new Parkinson's meds and existing heart medication. Flagged that two specialists prescribed overlapping drugs. Created a medication tracking sheet. |
| 👨 Marcus, 58 Recently diagnosed with Type 2 diabetes |
Self-advocate. Some medical familiarity. Wants to understand his A1C results and treatment options before next visit. | Explained A1C ranges in plain English. Generated 5 questions about metformin vs. lifestyle-first approach. Flagged that his fasting glucose trend suggests he should ask about continuous glucose monitoring. |
| 👩⚕️ Dr. Priya, 36 Pediatrician managing her own mother's cancer care |
Healthcare professional but NOT an oncologist. Pasted 12 pages of lab results and imaging notes. Wants a second-opinion checklist. | Matched output to professional-level terminology. Identified a declining platelet trend across three lab draws that warranted urgent discussion. Generated oncology-specific second opinion questions. |
| 👴 Robert, 72 Managing wife's post-stroke recovery |
No medical background. Wife discharged with 8-page care plan he can't parse. Overwhelmed by follow-up schedule. | Translated discharge instructions into a simple daily checklist. Created a calendar of follow-up appointments with prep notes for each. Flagged warning signs to watch for between visits. |
| Same prompt. YOUR situation. Try it. | ||
The AI didn't save Pratik Desai's mother. Cancer did what cancer does. But somewhere in those 1,600 pages of records, the patterns were hiding — and no human had the bandwidth to find them. A chatbot did.
How Marketers Are Scaling With AI in 2026
61% of marketers say this is the biggest marketing shift in decades.
Get the data and trends shaping growth in 2026 with this groundbreaking state of marketing report.
Inside you’ll discover:
Results from over 1,500 marketers centered around results, goals and priorities in the age of AI
Stand out content and growth trends in a world full of noise
How to scale with AI without losing humanity
Where to invest for the best return in 2026
Download your 2026 state of marketing report today.
About This Newsletter
AI Super Simplified is where busy professionals learn to use artificial intelligence without the noise, hype, or tech-speak. Each issue unpacks one powerful idea and turns it into something you can put to work right away.
From smarter marketing to faster workflows, we show real ways to save hours, boost results, and make AI a genuine edge — not another buzzword.
Get every new issue at AISuperSimplified.com — free, fast, and focused on what actually moves the needle.
If you enjoyed this issue and want more like it, subscribe to the newsletter.
Brought to you by Stoneyard.com • Subscribe • Forward • Archive