Health Scanner

Accepts medical records in DICOM, PDF, image, and printed document formats via web upload or phone camera, automatically extracting structured health data (test results, prescriptions, diagnoses) using a combination of proprietary image neural networks for visual content and OCR-based text extraction. The system normalizes heterogeneous input formats into a unified internal representation for downstream AI analysis, handling variable image quality from phone photos to professional medical prints.

Provides conversational Q&A interface over uploaded medical records using GPT-3.5, GPT-4, and Google Gemini as interchangeable backend models, with free tier restricted to GPT-3.5/Gemini and paid tier unlocking GPT-4 access. The system retrieves relevant sections from stored medical records in response to user queries, though the exact retrieval mechanism (RAG, semantic search, or keyword matching) is undocumented. Supports 40 languages for query input and response generation.

Implements pricing-based access control to AI models, with free tier restricted to GPT-3.5 and Google Gemini, while paid tier unlocks GPT-4 access. Users can select which model to use for analysis (if multiple are available in their tier), with model choice affecting response quality and potentially latency. The pricing structure and tier definitions are not publicly documented.

Supports analysis of NHS app screenshots and UK-specific medical record formats, enabling British users to upload records directly from the NHS digital health platform. The system recognizes NHS-specific data structures and can extract information from NHS app screenshots without requiring manual transcription.

Announced but not yet live feature providing AI-based psychiatric consultation and mental health analysis. The system will analyze mental health symptoms and provide preliminary psychiatric guidance, though implementation details, model architecture, and launch timeline are undocumented. Feature status is 'coming soon' with no ETA.

Analyzes uploaded medical records and user queries to identify potential drug-drug interactions, contraindications, and medication safety concerns by cross-referencing extracted medication lists against an undocumented drug interaction database. The system integrates with the chatbot interface, allowing users to ask about specific medication combinations or receive proactive warnings based on their prescription history.

Analyzes extracted blood test values from medical records using LLM-based interpretation, providing context-aware explanations of test results (normal/abnormal ranges, clinical significance, potential causes of abnormalities). The system compares values against reference ranges and generates natural language summaries of findings, supporting multi-test analysis when multiple lab reports are uploaded.

Offers optional human expert review of uploaded medical records and AI analysis, with a licensed medical team generating detailed reports that synthesize AI findings with professional clinical judgment. The exact workflow (manual review, AI-assisted review, or hybrid) is undocumented, as are SLAs, pricing, and which medical specialties are available. Reports are generated asynchronously with unknown turnaround time.

Offers optional 'privacy mode' for medical record uploads where the system claims to process records without retaining them in persistent storage, addressing user concerns about sensitive health data being stored long-term. The technical implementation (in-memory processing, immediate deletion, encryption) is undocumented, and retention policies for standard mode are not disclosed.

Supports medical record uploads and AI analysis in 40 languages, with the system accepting queries and generating responses in user's native language. Language support extends to both input processing (record extraction, query understanding) and output generation (chatbot responses, interpretations), though expert review language coverage is undocumented.

Processes extracted medical text from records using proprietary knowledge graphs to identify relationships between symptoms, diagnoses, medications, and conditions. The system maps unstructured medical narrative to structured knowledge representations, enabling contextual understanding of medical information beyond simple keyword matching or LLM pattern recognition.

Analyzes user symptoms and medical history to provide region-specific health recommendations, including localized allergy information based on geographic prevalence of allergens and environmental factors. The system infers user location (likely from IP or explicit input) and tailors health guidance to regional disease prevalence, seasonal patterns, and common allergens.

Provides dual authentication pathways: traditional email login and Metamask cryptocurrency wallet integration. Users can authenticate using either method, with wallet login enabling anonymous access and potential integration with blockchain-based reward systems (mechanism undocumented). Email authentication likely uses standard OAuth or password-based flows.