Symptom Article Summarizer

WHAT IT DOES

AI-powered symptom article summarizer that translates symptom-related content into plain-English summaries for patients and individuals researching health concerns. The script reads symptom article content from the current page—symptoms, causes, descriptions, severity indicators, onset patterns, and associated conditions—and generates an easy-to-understand summary. The AI produces a concise summary covering what the symptom is, possible causes, how to recognize it, and when to seek medical attention. You can customize the summary length, reading level, and toggle inclusion of causes, severity indicators, and when to seek help. The user reviews the output before copying or using it.

WHERE IT RUNS

Works on all symptom and health article pages (match pattern *://*/*), including medical websites, health portals, symptom checkers, patient information sites, and any page containing symptom-related content. Also works on health blogs and medical reference sites.

HOW TO USE

Install the script and the Symptom Article Summarizer appears in the panel. Configure your preferred summary length, reading level, and toggle inclusion of causes, severity indicators, and when to seek help using the settings controls. Click "Summarize" to analyze the current page. The AI extracts symptom information and generates a plain-English summary. Review the output in the panel. Click "Copy to Clipboard" to copy the summary for personal use, patient communication, or sharing with a healthcare provider. Adjust the settings and regenerate if you want a different level of detail or reading level.

REAL MECHANISM: DOM CONTENT EXTRACTION WITH AI PLAIN-LANGUAGE SYMPTOM SUMMARIZATION AND REVIEW GATE

This script uses a hybrid extraction approach that prioritizes structured content when available. First, it checks for WebMCP (navigator.modelContext), a W3C proposal that exposes structured tools on the page. If available, it calls getContent() to obtain structured symptom data. If WebMCP is not present—the common case today—it falls back to DOM scraping using targeted selectors for symptom article sections (symptom-article, symptom-info, health-symptom, symptom-details, symptom-description, symptom-causes, and symptom-list). It also scans for symptom-related keywords (symptom, sign, pain, fever, cough, nausea, fatigue, headache, rash, swelling, dizziness) in paragraphs and headings. The extracted text is sent to an AI backend via GM_xmlhttpRequest, which processes it with a system prompt that includes the user's reading level, summary length, and inclusion preferences. The AI returns a plain-English summary (150-250 words depending on the selected length) covering what the symptom is, possible causes, how to recognize it, and when to seek medical attention, with a disclaimer that it is not medical advice. The response is displayed in a bordered container for review before copying. Copy-to-clipboard uses GM_setClipboard. All settings (summary length, reading level, includeCauses, includeSeverity, includeWhenToSeek) are persisted via GM_setValue. The script enforces a review-before-use pattern: the user must read and approve the AI output before copying it.

THE PANEL

Drag the panel anywhere on screen by clicking and holding the header. It snaps to screen edges when released. Collapse it to a small bubble by clicking the minimize button, and expand it back by clicking the bubble. Resize the panel from any corner. Press Escape to close the configuration panel. Your position and size preferences are saved automatically per site.

PLEASE NOTE

This script requires the free BotGentz browser extension and an active AI subscription for the summarization service. AI-generated summaries should be reviewed for accuracy before use—the AI may misinterpret symptom information or omit important details. This is for informational purposes only and not medical advice—always consult a healthcare professional for medical decisions. The script reads the current page content and sends it to the AI backend for processing; no data is stored or logged. Websites change frequently; if the script stops detecting symptom content, check for updates to the extraction selectors.