Medical Newsletter Writer

Medical Newsletter Writer

Create high-quality, evidence-based medical newsletters in the style of Eric Topol's Ground Truths. This skill guides the complete newsletter creation process: from analyzing your PDF of topic ideas, to deep PubMed research, to writing in Topol's distinctive authoritative-yet-accessible voice.

Quick Start

Simple 3-Step Process:

1. Upload PDF - Upload your PDF with topic ideas in the chat 2. Select Topic - Review engagement predictions and pick one topic 3. Get Newsletter - Receive complete, publication-ready newsletter (~3,000 words with 20-30 PubMed citations)

The skill handles everything: PDF extraction, trend analysis, PubMed research, and writing in Eric Topol's exact voice.

Complete Workflow

The newsletter creation process has 5 phases:

1. Extract Topics from PDF - Read user's uploaded PDF of topic ideas 2. Trend Analysis - Analyze each topic for engagement potential 3. Topic Selection - User approves topics based on data-driven predictions 4. Deep Research - Comprehensive PubMed literature review 5. Newsletter Writing - Write complete newsletter in Topol's style

Phase 1: Extract Topics from PDF

PDF Upload

User will upload a PDF containing potential newsletter topic ideas in the chat.

Extract Topics

• Read the PDF using available tools
• Extract all topic ideas mentioned
• Clean and organize the list
• If PDF contains notes/context about topics, capture that too

Phase 2: Trend Analysis & Engagement Prediction

Analyze Each Topic (Automatically)

For each topic extracted from the PDF, conduct comprehensive trend analysis:

1. News Coverage (Google News, medical news sites)

• Search past 30 days
• Note which outlets covering
• Identify breaking developments
• Count article frequency

2. Search Interest

• Use web_search to assess current discussion
• Look for rising interest signals
• Note if topic is trending

3. Social Media Signals

• YouTube: Search for videos, note view counts
• Check if medical professionals are discussing
• Assess virality potential

4. Academic Momentum (PubMed)

• Count recent publications (6 months)
• Check for major journal coverage
• Identify ongoing trials
• Note if field is active

Engagement Prediction Scoring

For each topic, score 1-10 on:

1. Readability: Can this be explained clearly to physicians? 2. Controversy: Is there debate/opposing views? 3. Clinical Relevance: Will this affect patient care? 4. Timeliness: How current is this? Breaking news? 5. Share Potential: Will physicians share with colleagues?

Overall Engagement Score = Average of 5 metrics

Present Analysis

Create comparison table with:

• Topic name
• Brief trend summary (2-3 sentences)
• Individual scores (1-10)
• Overall engagement score
• Priority recommendation (High/Medium/Low)

Sort by overall score, present top 5-10 topics to user.

Phase 3: Topic Selection

Present findings to user with:

• Top topics by engagement prediction
• Rationale for scores
• Notable timeliness factors

User selects ONE topic - then the skill automatically proceeds to research and writing.

Phase 4: Deep Research (Automatic)

PubMed Search Strategy

Before searching, read workflow.md for detailed research guidance.

Initial searches: 1. Broad topic overview 2. Recent findings (<1 year) 3. Systematic reviews/meta-analyses 4. Major clinical trials

Paper Prioritization:

• Tier 1: Large RCTs in NEJM, Lancet, JAMA, Science, Nature
• Tier 2: Meta-analyses and systematic reviews
• Tier 3: Large observational studies
• Tier 4: Mechanistic studies in high-impact journals
• Tier 5: Pre-clinical (use sparingly)

Target: 15-30 highly relevant papers

Extract Key Information

For each major paper:

• Study design and sample size
• Key findings (quantitative)
• Limitations
• How it fits the narrative
• Potential quotes/figures

Find Related Work

• Use PubMed related articles
• Check major paper citations
• Look for responses/commentary
• Identify consensus vs. controversy

Phase 5: Newsletter Writing (Automatic)

Before Writing

CRITICAL: Read topol-style-guide.md first - This contains essential voice patterns, phrases, and stylistic requirements.

Structure

Opening (1-2 paragraphs)

• Hook using Topol's opening patterns (see style guide)
• Why this matters NOW
• What will be covered

Background/Context (optional)

• Define key terms: "To review: [term] is..."
• Historical perspective if relevant
• Current state of field

Main Content (3-5 sections with clear headers)

• Each section = one major subtopic
• Build logically
• Include data/studies in each
• Use tables to compare studies/treatments
• Reference figures from papers

Implications/Future Directions

• What this means for practice
• Research gaps
• What's next

Bottom Line (required)

• Synthesize key takeaways
• Clear conclusions based on evidence
• Call for more evidence if needed

Standard Closing (required)

Thanks for reading and subscribing to Ground Truths.

If you found this interesting PLEASE share it!

That makes the work involved in putting these together especially worthwhile.

All content on Ground Truths—its newsletters, analyses, and podcasts, are free, open-access.

Paid subscriptions are voluntary and all proceeds from them go to support Scripps Research. They do allow for posting comments and questions, which I do my best to respond to. Please don't hesitate to post comments and give me feedback. Let me know topics that you would like to see covered.

Writing Requirements

Voice & Style:

• First person engaged ("I recently fielded questions...")
• Authoritative but accessible
• Critical and evidence-based
• Use Topol's signature phrases (see style guide)

Citations:

• EVERY factual claim needs a PubMed citation with hyperlink
• Format: link text embedded in prose
• Cite original studies, not news articles
• Include author names for major findings: "Professor X and colleagues at Y University published in Z..."

Critical Analysis:

• Always discuss study limitations
• Note conflicts of interest if relevant
• Present alternative interpretations
• Flag when evidence is preliminary
• Call out hype vs. data

Length: 2,000-3,500 words

Visual Elements:

• Create tables comparing studies/treatments
• Describe figures from papers
• Use clear section headers

Quality Checks

Before finalizing:

• [ ] Engaging opening hook?
• [ ] Clear why-this-matters framing?
• [ ] Every claim cited?
• [ ] Limitations discussed?
• [ ] Topol's voice consistent?
• [ ] Tables/figures included?
• [ ] Logical flow?
• [ ] "Bottom Line" section?
• [ ] Standard closing?
• [ ] 2,000-3,500 words?

Delivery

Final Format

• Complete newsletter in Markdown
• All hyperlinked citations to PubMed
• 2,000-3,500 words
• Ready for user's newsletter platform

Customization Note

User may want to change "Scripps Research" in the standard closing to their own institution/practice name.

Essential References

ALWAYS READ BEFORE WRITING:

• topol-style-guide.md - Complete guide to Topol's voice, phrases, patterns
• workflow.md - Detailed research and writing process

Key Success Factors

1. Evidence-based: Every claim must be cited 2. Critical thinking: Discuss limitations, not just positives 3. Voice consistency: Sound like Topol throughout 4. Comprehensive: Cover topic thoroughly with multiple studies 5. Accessible: Technical accuracy without excessive jargon 6. Timely: Focus on recent developments 7. Visual: Include tables/figures to enhance understanding 8. Engaging: Hook readers immediately, maintain interest

Example Opening Lines (Topol Style)

• "In fielding questions recently from patients and colleagues about [topic], I was prompted to look into the field at more depth."
• "[Term] was coined in the late [year]. Now, about [X] years later, we've yet to achieve [goal]."
• "This week [major development] was published in [journal]. Several important reports have since been published. I've incorporated them in this updated version."
• "There's no question that the use of [intervention] has surged, in part because of [claims], along with endorsements by [influencers]."

Common Pitfalls to Avoid

• Don't rely on single studies - use multiple sources
• Don't ignore study limitations - they're critical
• Don't cherry-pick data - present full picture
• Don't get too technical - stay accessible
• Don't use bullet points excessively - prefer prose
• Don't skip the critical analysis - it's essential
• Don't forget visual elements - tables enhance understanding
• Don't deviate from Topol's voice - consistency matters

Eric Topol's Writing Style Guide

This guide captures the distinctive voice, structure, and patterns from Ground Truths newsletters to replicate Eric Topol's authoritative yet accessible medical writing style.

Core Voice Characteristics

Tone

• Authoritative yet conversational: Combines deep expertise with readability
• Evidence-obsessed: Every claim backed by research, often multiple studies
• Critically analytical: Points out limitations, conflicts, and lack of evidence
• First-person engaged: Uses "I" naturally ("I recently fielded questions...", "I hope this review...")
• Mission-driven: Clear commitment to evidence-based medicine over hype

Signature Phrases

• "No less" (for adding emphasis)
• "Suffice it to say"
• "That said"
• "To review:" (when defining something)
• "Ironically"
• "Bottom line"
• "Let me know topics you would like to see covered"
• "I've previously reviewed/written about"
• "As you know" / "As seen below"
• "Across the board"
• "Here's the contrast"

Newsletter Structure

Opening Pattern (Choose one approach)

1. Personal connection: "In fielding questions recently from patients and physician colleagues about..." 2. Historical context: "Primary Prevention means... The term was coined in the late 1940s..." 3. Recent publication tie-in: "This week I published an essay in Science on..." 4. Current events: Reference to recent news, studies, or trends

Body Organization

1. Introduction (~200-300 words)

• Why this topic matters NOW
• Brief context/background
• What will be covered

2. Main Content (organized by clear sections)

• Use subheadings liberally
• Tables summarizing key information
• Figures/images from cited papers
• Each section builds on previous

3. Visual Elements

• Summary tables (especially for comparing treatments, studies, drugs)
• Figures from papers with captions
• Schematics showing mechanisms
• Performance metrics graphs

4. Concluding Remarks

• "Bottom Line" or "Concluding Remarks" section
• Synthesize key takeaways
• Future implications
• Call for evidence/trials needed

5. Standard Closing

• Optional: Personal note about book or current projects
• "Thanks for reading and subscribing to Ground Truths"
• "If you found this interesting PLEASE share it!"
• "All content on Ground Truths—its newsletters, analyses, and podcasts, are free, open-access"
• "Paid subscriptions are voluntary and all proceeds go to support Scripps Research"

Length

• Target: 2,000-3,500 words
• Comprehensive but digestible
• Dense with information, not fluff

Citation Style

Hyperlinking

• Extensive use of hyperlinks embedded in text
• Link to original studies, not aggregators
• Link to own previous Ground Truths posts
• Format: "as we recently saw for migraine and the one—Alzheimer's disease— that we await"

Reference Pattern

• Cite specific papers with embedded links
• Include author names in narrative when relevant: "Professor Shana Kelley and colleagues at Northwestern"
• Reference institutions: "at Northwestern University published in Science"
• Use figure captions: "From Schindler et al head-to-head comparison..."

Evidence Hierarchy

• Prioritize: Large RCTs > observational studies > preclinical > expert opinion
• Always note study design: "randomized, placebo-controlled trial"
• Call out sample sizes: "over 100,000 participants for 30 years"
• Note validation: "externally validated in the Denmark population of 1.9 million"

Critical Analysis Patterns

Calling Out Problems

• Lack of evidence: "The evidence base for use of these drugs... is wanting"
• Conflicts of interest: "with endorsements by celebrities, longevity, and 'wellness' influencers"
• Hype vs. reality: "unfounded", "putative", "unsubstantiated health claims"
• Missing data: "there are very limited ongoing clinical trials"

Balanced Reporting

• Always mention limitations: "Of course, there are many limitations..."
• Note caveats: "Despite that...", "That said..."
• Acknowledge uncertainty: "There is a chance that..."
• Present counterarguments: Include dissenting views or study limitations

Technical Content Presentation

Defining Terms

• Pattern: "To review: a peptide is a short chain of amino acids..."
• Keep definitions accessible but accurate
• Use analogies when helpful

Presenting Data

• Use specific metrics: "AUC (area under the curve) was 0.76"
• Include confidence intervals, p-values when relevant
• Compare to benchmarks: "as good or slightly better than..."
• Show temporal relationships: "20 years before mild cognitive impairment"

Discussing Mechanisms

• Include schematics/diagrams when possible
• Explain pathophysiology clearly: "It takes at least 20 years for aggregates of misfolded β-amyloid and tau proteins to accumulate..."
• Connect mechanism to clinical relevance

Controversial Topics

Approach

• Be direct but fair
• Let evidence speak: "with as rigorous datasets as we've ever seen (e.g. >70,000 participants...)"
• Acknowledge complexity: "Why have peptides become so popular without data?"
• Stay non-partisan on medical issues
• Call out pseudoscience firmly but constructively

Examples

• On peptides: "The peptide craze is unfounded"
• On prevention: "we've yet to achieve any substantive primary prevention with the notable exception of vaccinations"
• On AI: "There's currently a lot of negativism about generative A.I. I get it. But..."

Topic Integration

Connecting to Broader Themes

• Link to prevention: "This represents a jump from my prior piece on precision medical forecasting"
• Reference book content: "As I presented in SUPER AGERS..."
• Connect to other research: "I've previously reviewed the GLP-1 family extensively"
• Show convergence: "These are a sampling of evaluations..."

Future-Facing

• "We're at the dawn of..."
• "For the first time, we are seeing..."
• "This may well turn out to be..."
• "It will take time to get this to be standard of care"

Engagement Elements

Polls (occasional)

• Simple 2-question polls at end
• Related to newsletter content
• Example: "Have you heard of p-tau217?" Yes/No

Reader Interaction

• Invite comments: "Please don't hesitate to post comments and give me feedback"
• Respond to questions: "In fielding questions recently..."
• Thank contributors: "Many thanks to those who have contributed"

What NOT to Do

• Don't oversimplify for dramatic effect
• Don't make unsupported claims
• Don't use excessive jargon without explanation
• Don't skip discussing limitations
• Don't ignore conflicting evidence
• Don't be unnecessarily inflammatory
• Don't use too many bullet points (prefer prose with embedded data)

Example Opening Patterns

Pattern 1: Question-driven

"In fielding questions recently from [audience] about [topic], I was prompted to look into the field at more depth. [Context about surge/interest/controversy]. [What will be covered in this post]."

Pattern 2: Historical context

"[Concept/Term] was coined and introduced by [names] in the [time period]. Now, about [X] years later, [current state]. [Why this matters now]."

Pattern 3: Breaking news

"This week [major development]. That was written a few weeks ago and several important reports have since been published. I've incorporated them in this updated version of [topic]."

Pattern 4: Contrast setup

"There's currently [misconception/trend]. [What data actually shows]. In this Ground Truths post I'll review [what will be covered]."

Newsletter Creation Workflow

This document outlines the complete workflow for creating evidence-based medical newsletters in Eric Topol's style.

Phase 1: Topic Discovery & Trend Analysis

Step 1.1: Gather Seed Topics

• User provides list of potential newsletter topics
• Topics can be from any source (news, papers, ideas, clinical questions)
• No minimum/maximum number

Step 1.2: Conduct Trend Analysis

For each seed topic, analyze:

News Trends

• Search Google News for recent articles (past 30 days)
• Identify breaking medical news
• Note frequency of coverage
• Track which outlets are covering

Search Volume

• Assess Google Trends data if available
• Look for rising search interest
• Note geographic concentration
• Identify related queries

Social Media Signals

• YouTube: Search for recent videos, note view counts
• X/Twitter: Look for discussion volume
• Medical Twitter: Check if topic is trending among physicians
• LinkedIn: Note if medical professionals are discussing

Academic Momentum

• PubMed search: Count recent publications (past 6 months)
• Note if major journals are publishing
• Check for clinical trials registered
• Identify if new research is emerging

Step 1.3: Engagement Prediction

For each topic, create a predictive score based on:

Readability Score (1-10)

• Can this be explained clearly?
• Is it too technical for general medical audience?
• Are there relatable analogies?

Controversy Score (1-10)

• Is there debate in the field?
• Are there opposing viewpoints?
• Will this generate discussion?

Clinical Relevance (1-10)

• Does this affect patient care?
• Is this actionable for physicians?
• Will readers encounter this in practice?

Timeliness (1-10)

• How current is this topic?
• Is there breaking news?
• Is a major trial result pending?

Share Potential (1-10)

• Will physicians share this with colleagues?
• Does it challenge conventional wisdom?
• Is there a "wow" factor?

Overall Engagement Score: Average of above metrics

Step 1.4: Present Analysis

Create a comparison table showing:

• Topic name
• Key news/trend summary (2-3 sentences)
• Individual scores
• Overall engagement prediction
• Recommended priority (High/Medium/Low)

Sort by engagement score descending.

Phase 2: Topic Selection

Present Findings

• Show top 5-10 topics by predicted engagement
• Include rationale for each score
• Note any topics with exceptional timeliness

User Approval

• User selects topic(s) for newsletter
• User may combine related topics
• User confirms target length/scope

Phase 3: Deep Research

Step 3.1: PubMed Literature Search

Initial Search Strategy

• Broad search for topic overview
• Narrow search for recent findings (<1 year)
• Search for systematic reviews/meta-analyses
• Search for major clinical trials

Search Terms

• Use MeSH terms when appropriate
• Include variations (acronyms, full names)
• Use filters: publication date, article type
• Target: 20-50 relevant papers initially

Paper Prioritization

1. Tier 1: Large RCTs in major journals (NEJM, Lancet, JAMA, Science, Nature) 2. Tier 2: Meta-analyses and systematic reviews 3. Tier 3: Large observational studies 4. Tier 4: Mechanistic studies in high-impact journals 5. Tier 5: Pre-clinical research (use sparingly)

Step 3.2: Full-Text Analysis

For key papers:

• Read abstract and conclusions
• Identify sample size, design, endpoints
• Note limitations explicitly stated
• Extract key figures/tables
• Save for potential inclusion in newsletter

Step 3.3: Related Citations

• Use PubMed "Related Articles" feature
• Check citations in key papers
• Look for response papers or commentary
• Identify consensus vs. controversy

Step 3.4: Research Documentation

Create structured notes with:

• Paper citation (authors, journal, year)
• Study design and sample size
• Key findings (quantitative when possible)
• Limitations
• How it fits the narrative
• Direct quote-worthy passages

Phase 4: Newsletter Composition

Step 4.1: Outline Creation

Based on research, create structure:

1. Opening (1-2 paragraphs)

• Hook using one of Topol's opening patterns
• Why this matters now
• What will be covered

2. Background/Context (optional section)

• Define key terms
• Historical perspective if relevant
• Current state of field

3. Main Content (3-5 sections)

• Each section = one major subtopic
• Build logically from one to next
• Include data/studies in each section

4. Implications/Future Directions

• What this means for practice
• Research gaps
• What's coming next

5. Bottom Line

• Synthesize key takeaways
• Clear conclusions
• Call for evidence/action if appropriate

Step 4.2: Writing Guidelines

Style Requirements:

• Read topol-style-guide.md before writing
• Match his voice patterns
• Use first person naturally
• Maintain critical, evidence-based tone

Citation Requirements:

• Every factual claim needs citation
• Link to original studies
• Use hyperlinked text (not footnotes)
• Format: "link text" or "study showed link"
• Prefer: Author names + journal when introducing major findings

Visual Elements:

• Create or describe tables comparing studies/treatments
• Reference figures from papers (describe them)
• Use clear section headers
• Consider including comparison graphics

Length Target:

• Aim for 2,000-3,500 words
• Comprehensive but readable
• Every paragraph should advance understanding

Step 4.3: Critical Analysis

Include Throughout:

• Study limitations
• Conflicts of interest if relevant
• Evidence gaps
• Alternative interpretations
• Degree of certainty

Questions to Address:

• What's the quality of evidence?
• What are we still uncertain about?
• Are there conflicting findings?
• What would change our understanding?

Step 4.4: Draft Review

Before finalizing, check:

• [ ] Opens with engaging hook?
• [ ] Clear why-this-matters framing?
• [ ] Every claim cited with hyperlink?
• [ ] Limitations discussed?
• [ ] Topol's voice maintained?
• [ ] Tables/figures described/included?
• [ ] Sections flow logically?
• [ ] "Bottom Line" section present?
• [ ] Standard closing included?
• [ ] Length appropriate (2,000-3,500 words)?
• [ ] Accessible to physician audience?

Phase 5: Formatting & Delivery

Markdown Format

• Use ## for section headers
• Use bold for key terms (sparingly)
• Use link text for citations
• Include image markdown if describing figures
• Use > for block quotes if including any

Standard Closing

Always include Topol's standard closing:

Thanks for reading and subscribing to Ground Truths.

If you found this interesting PLEASE share it!

That makes the work involved in putting these together especially worthwhile.

All content on Ground Truths—its newsletters, analyses, and podcasts, are free, open-access.

Paid subscriptions are voluntary and all proceeds from them go to support Scripps Research. They do allow for posting comments and questions, which I do my best to respond to. Please don't hesitate to post comments and give me feedback. Let me know topics that you would like to see covered.

Note: User should customize the "support Scripps Research" part to their own institution/practice if desired.

Quality Standards

Evidence Quality

• Prefer large, well-designed studies
• Note when evidence is preliminary
• Flag when claims exceed evidence
• Cite systematic reviews when available

Writing Quality

• Clear, active voice
• Technical accuracy without jargon
• Accessible to physicians, not just specialists
• Engaging narrative flow

Citation Quality

• Original sources, not news summaries
• Links work (verify before publishing)
• Appropriate study types for claims made
• Recent publications prioritized

Common Pitfalls to Avoid

1. Over-reliance on single study: Use multiple sources 2. Ignoring limitations: Every study has them 3. Cherry-picking data: Present full picture 4. Too technical: Remember audience 5. Missing context: Connect to bigger picture 6. Weak opening: Hook reader immediately 7. No visual elements: Tables/figures enhance understanding 8. Inconsistent voice: Stay in Topol's style throughout 9. Under-citing: When in doubt, cite 10. Ignoring controversy: Address conflicting evidence

Topic-Specific Guidance

For New Drugs/Treatments

• Mechanism of action
• Trial data (phase, size, endpoints)
• Efficacy vs. existing treatments
• Safety profile
• Cost/accessibility
• FDA status
• Comparisons to alternatives

For Diagnostic Tests

• Sensitivity/specificity
• Clinical utility
• Comparison to gold standard
• Cost-effectiveness
• Availability
• When to use vs. existing tests

For Public Health Issues

• Magnitude of problem (epidemiology)
• Current interventions
• Evidence for new approaches
• Policy implications
• Implementation challenges
• Equity considerations

For Controversial Topics

• Present evidence objectively
• Acknowledge uncertainty
• Discuss why controversy exists
• Separate hype from data
• Note vested interests
• Clear bottom line based on evidence