%PDF-1.4 %âãÏÓ 1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj 2 0 obj << /Type /Pages /Count 4 /Kids [5 0 R 7 0 R 9 0 R 11 0 R] >> endobj 3 0 obj << /Type /Font /Subtype /Type1 /BaseFont /Helvetica >> endobj 4 0 obj << /Type /Font /Subtype /Type1 /BaseFont /Helvetica-Bold >> endobj 5 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 595.28 841.89] /Resources << /Font << /F1 3 0 R /F2 4 0 R >> >> /Contents 6 0 R >> endobj 6 0 obj << /Length 5671 >> stream BT /F2 22 Tf 0.06 0.08 0.12 rg 1 0 0 1 46 789.89 Tm (Best AI Workflow for Doctors Outside the US:) Tj ET BT /F2 22 Tf 0.06 0.08 0.12 rg 1 0 0 1 46 762.89 Tm (Using Perplexity, Claude and Gemini Together for) Tj ET BT /F2 22 Tf 0.06 0.08 0.12 rg 1 0 0 1 46 735.89 Tm (CPD, Exam Prep and Journal Clubs) Tj ET BT /F2 11 Tf 0.72 0.14 0.18 rg 1 0 0 1 46 698.89 Tm (TechRounder PDF Edition) Tj ET BT /F1 9.5 Tf 0.36 0.39 0.46 rg 1 0 0 1 46 682.89 Tm (Live article:) Tj ET BT /F1 9.5 Tf 0.36 0.39 0.46 rg 1 0 0 1 46 670.39 Tm (https://www.techrounder.com/ai/best-ai-workflow-for-doctors-outside-the-us-using-perplexity-claude-and-gemini-to) Tj ET BT /F1 9.5 Tf 0.36 0.39 0.46 rg 1 0 0 1 46 657.89 Tm (gether-for-cpd-exam-prep-and-journal-clubs/) Tj ET q 0.82 0.85 0.9 RG 1 w 46 639.39 m 549.28 639.39 l S Q BT /F1 10 Tf 0.24 0.27 0.32 rg 1 0 0 1 46 627.39 Tm (By Vipin PG | Published July 31, 2026 | Updated July 31, 2026 | Format: Explainer | 8 min read) Tj ET BT /F2 13 Tf 0.72 0.14 0.18 rg 1 0 0 1 46 604.39 Tm (In brief) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 584.39 Tm (If you practice medicine outside the US or UK, "which AI tool is best" is the wrong question.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 569.39 Tm (OpenEvidence needs a US National Provider Identifier and has been pulled back from the UK and EU.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 554.39 Tm (iatroX only covers UK guidelines. Claude for Healthcare's health-record features are US-only. That) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 539.39 Tm (leaves general-purpose AI - Perplexity, Claude, and Gemini - as the realistic option for most of the) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 524.39 Tm (world's doctors. The right move isn't picking a favourite. It's giving each tool the one job it's actually) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 509.39 Tm (good at, and matching how carefully you check its answer to where that answer is going to end up: a) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 494.39 Tm (quick curiosity check, a study note you'll memorise, or a slide your colleagues will see.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 469.39 Tm (Search for "best AI tool for doctors" and you'll get one of two articles. Either it's a generic) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 454.39 Tm (ChatGPT-vs-Claude-vs-Gemini comparison with no medical context at all, or it's a review of) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 439.39 Tm (specialised clinical platforms - OpenEvidence, iatroX, UpToDate Expert AI - built to answer bedside) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 424.39 Tm (questions safely. Both are useful in their own way. Neither one is written for the doctor who isn't) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 409.39 Tm (standing at a bedside right now, and isn't in the US or UK either.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 387.39 Tm (That's a much bigger group than the existing articles assume. A large share of the world's physicians) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 372.39 Tm (spend a good part of their week not treating patients, but preparing to know more: reading up for a) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 357.39 Tm (specialist exam, building a journal club presentation, writing structured notes they'll revise before an) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 342.39 Tm (oral exam, or just trying to keep up with a paper that changed practice last month. That work happens) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 327.39 Tm (with general AI chatbots, whether anyone writes a guide for it or not.) Tj ET BT /F2 15 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 299.39 Tm (Why the tools built specifically for doctors don't reach most doctors) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 275.39 Tm (It's worth being specific about this, because the gap isn't a vague "access issue" - it's a set of hard) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 260.39 Tm (walls.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 238.39 Tm (OpenEvidence, the platform many US doctors now use daily for cited, guideline-grounded answers, is) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 223.39 Tm (free only for verified US healthcare professionals who supply an NPI number. It has also been) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 208.39 Tm (reported as withdrawn from the UK and the EU, with OpenEvidence's own privacy policy noting that its) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 193.39 Tm (infrastructure and hosting sit in the US and warning that it isn't built to meet EU data-protection) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 178.39 Tm (standards. It's an excellent tool - if you're a doctor practising in the United States.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 156.39 Tm (iatroX runs the same logic in reverse. It's genuinely free for anyone, no professional verification) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 141.39 Tm (required, but it's architecturally built around UK guidance - NICE, CKS, the BNF. Ask it a question) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 126.39 Tm (rooted in a different country's treatment protocols and you're outside what it was designed to do.) Tj ET q 0.86 0.88 0.92 RG 1 w 46 42 m 549.28 42 l S Q BT /F1 8.4 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 30 Tm (TechRounder | Page 1 of 4) Tj ET BT /F1 7.2 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 19 Tm (https://www.techrounder.com/pdf/blog/best-ai-workflow-for-doctors-outside-the-us-using-perplexity-claude-and-gemini-together-for-cpd-exam-prep-an) Tj ET BT /F1 7.2 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 11.2 Tm (d-journal-clubs.pdf) Tj ET endstream endobj 7 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 595.28 841.89] /Resources << /Font << /F1 3 0 R /F2 4 0 R >> >> /Contents 8 0 R >> endobj 8 0 obj << /Length 6444 >> stream BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 789.89 Tm (Then there's Claude for Healthcare, Anthropic's healthcare-focused toolkit announced in January) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 774.89 Tm (2026. Its most talked-about feature - syncing lab results and health records so Claude can summarise) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 759.89 Tm (your history in plain language - is currently available to Claude Pro and Max subscribers in the US,) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 744.89 Tm (connecting to US-specific data sources like Apple Health and the CMS coverage database.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 722.89 Tm (Put those three together and a pattern shows up: the "safe," purpose-built clinical AI tools are almost) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 707.89 Tm (all fenced to a single country. If you're practising in India, the Gulf, Southeast Asia, most of Africa, or) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 692.89 Tm (large parts of Europe, none of them are really built with you in mind. You're left with the same) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 677.89 Tm (general-purpose tools everyone else uses for everything else - Perplexity, Claude, and Gemini.) Tj ET BT /F2 15 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 649.89 Tm (Doctors are already using general AI - heavily) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 625.89 Tm (This isn't a fringe workaround. The American Medical Association's most recent physician sentiment) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 610.89 Tm (survey found that 81% of physicians now use AI in some part of their professional life, up from 66%) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 595.89 Tm (in 2024 and just 38% in 2023 - one of the fastest adoption curves the AMA says it has tracked in) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 580.89 Tm (health tech. Research summarisation is already one of the most common uses. In other words, doctors) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 565.89 Tm (have already answered the "should I use AI" question for themselves. What's missing is guidance on) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 550.89 Tm (doing it well when you don't have a specialised, guideline-locked tool doing the safety work for you.) Tj ET BT /F2 15 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 522.89 Tm (Stop comparing the three tools. Start assigning them jobs.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 498.89 Tm (Most comparison articles frame Perplexity, Claude, and Gemini as competitors - pick a winner, cancel) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 483.89 Tm (the rest. For a doctor's actual weekly workload, that framing doesn't hold up. The three tools are) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 468.89 Tm (strong at genuinely different things, and the smartest workflow uses all three in sequence rather than) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 453.89 Tm (one in isolation.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 431.89 Tm (Perplexity's strength is grounded retrieval. It searches the live web and attaches citations to what it) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 416.89 Tm (tells you, which makes it the right starting point when you need to know what the current literature or) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 401.89 Tm (guideline actually says on a topic - the "quick literature lookup" part of the job. Treat its citations as a) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 386.89 Tm (starting point to verify, not a finished answer.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 364.89 Tm (Claude's strength is structuring and reasoning over long material. Once you have the raw information) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 349.89 Tm (- a set of papers, your rough notes, a transcript of a lecture - Claude is the stronger tool for turning) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 334.89 Tm (that into something usable: a condensed study note organised around what an exam is likely to test, a) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 319.89 Tm (presentation outline with a logical flow from background to critique, or a set of self-quiz questions) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 304.89 Tm (pulled from material you've fed it. This is document-structuring work, and it's a different skill from) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 289.89 Tm (web retrieval.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 267.89 Tm (Gemini's strength is sheer volume. If you're trying to work through an entire textbook chapter, a) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 252.89 Tm (bundle of trial PDFs, or a long recorded lecture in one pass, Gemini's larger context window lets you) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 237.89 Tm (feed in more material at once without breaking it into chunks first.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 215.89 Tm (None of the three is "the winner." Each one removes a different bottleneck.) Tj ET BT /F2 15 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 187.89 Tm (The real risk isn't hallucination in general - it's where the wrong fact) Tj ET BT /F2 15 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 168.89 Tm (lands) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 144.89 Tm (Every article on AI in medicine repeats the same warning: verify everything, hallucination is a) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 129.89 Tm (dealbreaker. That's true, but it treats every use of AI as equally risky, which isn't how the risk) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 114.89 Tm (actually works. One evaluation of general-purpose chatbots found they fabricated medical citations) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 99.89 Tm (roughly a third of the time when asked directly for references - a real and well-documented problem.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 84.89 Tm (But a fabricated reference matters very differently depending on what happens to it next.) Tj ET q 0.86 0.88 0.92 RG 1 w 46 42 m 549.28 42 l S Q BT /F1 8.4 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 30 Tm (TechRounder | Page 2 of 4) Tj ET BT /F1 7.2 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 19 Tm (https://www.techrounder.com/pdf/blog/best-ai-workflow-for-doctors-outside-the-us-using-perplexity-claude-and-gemini-together-for-cpd-exam-prep-an) Tj ET BT /F1 7.2 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 11.2 Tm (d-journal-clubs.pdf) Tj ET endstream endobj 9 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 595.28 841.89] /Resources << /Font << /F1 3 0 R /F2 4 0 R >> >> /Contents 10 0 R >> endobj 10 0 obj << /Length 6054 >> stream BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 789.89 Tm (It helps to think in four tiers, rather than one blanket rule:) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 767.89 Tm (- Casual curiosity. You're skimming a topic out of interest, not building anything from it. Low stakes - read) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 754.09 Tm (it, move on, verify later if it matters.) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 737.29 Tm (- Study notes you'll memorise for an exam. This is a quieter risk than most guides mention. A wrong fact) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 723.49 Tm (here doesn't get caught at the moment of use - it gets absorbed, and it can sit in your memory uncorrected) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 709.69 Tm (for years. This deserves more scrutiny than a casual query, even though it feels like "just studying.") Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 692.89 Tm (- Journal club or conference slides. Public and peer-reviewed in real time - if a number is wrong, a) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 679.09 Tm (colleague in the room is likely to say so. That built-in correction mechanism makes this lower-risk than it) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 665.29 Tm (feels, but you should still check the actual trial numbers against the source paper, not just the AI's summary) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 651.49 Tm (of them.) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 634.69 Tm (- Anything touching an actual clinical decision. This is the one tier where the existing "always verify against) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 620.89 Tm (a primary source" advice is non-negotiable and where general-purpose AI should never be the final word -) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 607.09 Tm (cross-check against a guideline, drug reference, or senior colleague, every time, regardless of which tool) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 593.29 Tm (you used.) Tj ET BT /F2 15 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 570.49 Tm (A practical, step-by-step workflow) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 546.49 Tm (Here's what this looks like put together, using a realistic example: preparing a journal club) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 531.49 Tm (presentation on a recent hypertension trial while also turning the same material into exam-recall notes.) Tj ET BT /F2 13 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 503.49 Tm (Step 1: Retrieve with Perplexity) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 481.49 Tm (Start with a specific, narrow question - "what were the primary and secondary endpoints of [trial) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 466.49 Tm (name], and how do the results compare with the current guideline recommendation." Let Perplexity pull) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 451.49 Tm (the trial and any guideline commentary, and open the actual cited sources rather than trusting the) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 436.49 Tm (summary alone. This step exists to get you to the real paper faster, not to replace reading it.) Tj ET BT /F2 13 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 408.49 Tm (Step 2: Structure with Claude) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 386.49 Tm (Once you've confirmed the core facts against the source, feed the trial details, your own notes, and) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 371.49 Tm (any related guideline text into Claude and ask it to do two separate things: build a presentation outline) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 356.49 Tm (\(background, methods, results, critique, relevance to practice\), and separately, condense the same) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 341.49 Tm (material into short recall-style notes organised by what's likely to be tested or discussed. Keep these) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 326.49 Tm (as two distinct outputs - a slide outline and a study note are structured differently, and asking for both) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 311.49 Tm (in one pass tends to produce a worse version of each.) Tj ET BT /F2 13 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 283.49 Tm (Step 3: Generate a self-quiz) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 261.49 Tm (Ask the same tool to write ten to fifteen short-answer questions based only on the notes you just) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 246.49 Tm (approved - not on the internet, not on anything beyond what you've verified. This keeps the quiz) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 231.49 Tm (anchored to material you've already checked, rather than introducing new, unverified claims through) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 216.49 Tm (the back door.) Tj ET BT /F2 13 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 188.49 Tm (Step 4: Verify, matched to the tier) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 166.49 Tm (Apply the risk framework from above. For the study notes, spot-check the specific numbers - trial) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 151.49 Tm (size, endpoint results, confidence intervals - against the original paper, since these are the details) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 136.49 Tm (you'll carry into an exam. For the presentation slides, do the same check on anything you'll say out) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 121.49 Tm (loud, since that's what a colleague could challenge on the spot.) Tj ET BT /F2 15 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 93.49 Tm (Making this count toward your CPD, not just your to-do list) Tj ET q 0.86 0.88 0.92 RG 1 w 46 42 m 549.28 42 l S Q BT /F1 8.4 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 30 Tm (TechRounder | Page 3 of 4) Tj ET BT /F1 7.2 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 19 Tm (https://www.techrounder.com/pdf/blog/best-ai-workflow-for-doctors-outside-the-us-using-perplexity-claude-and-gemini-together-for-cpd-exam-prep-an) Tj ET BT /F1 7.2 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 11.2 Tm (d-journal-clubs.pdf) Tj ET endstream endobj 11 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 595.28 841.89] /Resources << /Font << /F1 3 0 R /F2 4 0 R >> >> /Contents 12 0 R >> endobj 12 0 obj << /Length 4291 >> stream BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 789.89 Tm (For doctors practising in India, this workflow has a practical bonus: it can double as documented) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 774.89 Tm (professional development. Under the National Medical Commission's Registered Medical Practitioner) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 759.89 Tm (regulations, doctors under 65 need to complete 30 CPD credit hours every five years to renew their) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 744.89 Tm (licence, and journal club participation and presentations are recognised activities under that structure.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 729.89 Tm (A journal club talk you built using this workflow isn't just useful preparation - with the right) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 714.89 Tm (documentation from your institution or state medical council, it's also a credit-bearing activity toward) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 699.89 Tm (that requirement. The same logic applies under most countries' equivalent CME/CPD systems, even) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 684.89 Tm (where the exact credit rules differ.) Tj ET BT /F2 15 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 656.89 Tm (A short verification checklist) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 632.89 Tm (- Never treat an AI-generated citation as confirmed until you've opened the actual source.) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 616.09 Tm (- For anything you'll memorise, re-check the specific numbers, not just the general claim.) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 599.29 Tm (- For anything you'll present publicly, re-check whatever you plan to say out loud, since that's what gets) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 585.49 Tm (challenged.) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 568.69 Tm (- For anything touching a real patient decision, AI is a starting point for research, never the final source -) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 554.89 Tm (confirm against a guideline or clinical reference.) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 538.09 Tm (- Keep retrieval \(Perplexity\) and structuring \(Claude\) as separate steps rather than asking one tool to do both) Tj ET BT /F1 10.5 Tf 0.2 0.23 0.28 rg 1 0 0 1 46 524.29 Tm (- it makes errors easier to catch, because you're checking a smaller thing at each stage.) Tj ET BT /F2 15 Tf 0.08 0.1 0.14 rg 1 0 0 1 46 501.49 Tm (Frequently asked questions) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 477.49 Tm (Can I use Perplexity, Claude, and Gemini for actual patient care decisions? Use them for background) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 462.49 Tm (research and to move faster, but the final decision should always be checked against a proper clinical) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 447.49 Tm (reference, guideline, or colleague - not left with a general-purpose chatbot, none of which are) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 432.49 Tm (approved medical devices.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 410.49 Tm (Do I need to subscribe to all three tools? No. Free tiers of Perplexity, Claude, and Gemini cover this) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 395.49 Tm (entire workflow for most doctors. A paid plan is worth it only if you're hitting daily usage limits.) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 373.49 Tm (Is Claude for Healthcare coming to other countries? Anthropic hasn't given a public timeline for) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 358.49 Tm (expanding Claude for Healthcare's record-syncing features beyond the US. Until it does, the) Tj ET BT /F1 11 Tf 0.14 0.16 0.2 rg 1 0 0 1 46 343.49 Tm (general-purpose version of Claude remains what's available to most doctors outside the US.) Tj ET q 0.86 0.88 0.92 RG 1 w 46 42 m 549.28 42 l S Q BT /F1 8.4 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 30 Tm (TechRounder | Page 4 of 4) Tj ET BT /F1 7.2 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 19 Tm (https://www.techrounder.com/pdf/blog/best-ai-workflow-for-doctors-outside-the-us-using-perplexity-claude-and-gemini-together-for-cpd-exam-prep-an) Tj ET BT /F1 7.2 Tf 0.42 0.45 0.5 rg 1 0 0 1 46 11.2 Tm (d-journal-clubs.pdf) Tj ET endstream endobj xref 0 13 0000000000 65535 f 0000000015 00000 n 0000000064 00000 n 0000000140 00000 n 0000000210 00000 n 0000000285 00000 n 0000000427 00000 n 0000006149 00000 n 0000006291 00000 n 0000012786 00000 n 0000012929 00000 n 0000019035 00000 n 0000019179 00000 n trailer << /Size 13 /Root 1 0 R >> startxref 23522 %%EOF