AI clinical decision support that shows its sources
Clinical decision support (CDS) is a digital tool that gives clinicians timely, person-specific information to improve care, as ONC defines it. Arkangel AI is clinical AI for decision support: it answers clinical questions with the guidelines and studies cited, so the clinician can review the basis of each recommendation before acting.
Start with a real clinical question
Pick a question to ask Arkangel AI — we keep it through sign in and answer with cited evidence.
Already have an account? Sign in
Last updated:
Reviewed by: Arkangel AI clinical review team, Medical AI content
How AI clinical decision support works in Arkangel AI
1. Ask the clinical question
Diagnosis, treatment, dosing or follow-up, in plain language and without patient identifiers.
2. Evidence is retrieved and cited
The answer draws on clinical guidelines and studies and links each one, so the basis of the recommendation is visible.
3. Options, not a verdict
Guideline-supported options with benefits, risks and the patient factors that change the choice.
4. The clinician reviews and decides
You review the basis independently, apply it to the individual patient and decide with them.
As of November 2026
Clinical AI for decision support: Arkangel AI vs OpenEvidence, UpToDate, Doximity GPT and ChatGPT
Clinical AI tools that answer questions at the point of care, compared on how they show sources, who can use them, price, security and languages.
Competitor information comes from the public sources linked in each cell, read between October 10 and November 1, 2026. Terms change often, so confirm with each vendor before you decide.
| Criteria | Arkangel AI | OpenEvidence | UpToDate (Expert AI) | Doximity Ask (formerly Doximity GPT) | ChatGPT (consumer plans) |
|---|---|---|---|---|---|
| Answers and sources | Answers cite the studies and guidelines behind them, so you can open and check each source. | Answers cite the medical literature.Source: openevidence.com | Expert-written topics; Expert AI answers only from UpToDate content.Source: wolterskluwer.com | Answers come with their sources; physician experts review AI answers (PeerCheck); UpToDate shown alongside answers.Source: doximity.com (Doximity Ask)Source: doximity.com | General-purpose chatbot; OpenAI warns that ChatGPT can make mistakes.Source: chatgpt.com |
| Availability and access | Available on the web and on WhatsApp; used by healthcare teams in Latin America and the United States, and in the EU under specific conditions with an Enterprise license. | Verified U.S. healthcare professionals; not available in the EU or UK since late April 2026.Source: openevidence.com/registerSource: telehealth.org | Expert AI launched in late 2025, first for Enterprise customers.Source: wolterskluwer.com | Verified U.S. clinicians, on desktop and mobile; also built into Doximity Scribe.Source: doximity.comSource: blog.doximity.com (Sep 14, 2026) | Broadly available to consumers.Source: chatgpt.com |
| Pricing model | Free plan with limited searches; Pro from US$20/month; Team and Enterprise plans.Source: arkangel.ai/pricing | Free for verified U.S. healthcare professionals.Source: openevidence.com | Paid subscription, individual or institutional.Source: wikipedia.org/wiki/UpToDate | Free for verified U.S. clinicians.Source: doximity.comSource: doximity.com (Doximity Ask) | Free and paid individual plans.Source: openai.com/chatgpt/pricing |
| Security and compliance | ISO 27001:2022 certified; HIPAA compliance and a BAA on Enterprise plans.Source: compliance.arkangel.ai | States full HIPAA compliance, handles PHI under its standard BAA and reports SOC 2 Type II (Security).Source: openevidence.com/security | Not stated in the vendor sources reviewed.Source: wolterskluwer.com | States it is HIPAA-compliant.Source: doximity.com (Doximity Ask) | No BAA for consumer plans; OpenAI offers a BAA only on eligible enterprise products.Source: help.openai.com |
| Languages | English, Spanish, Portuguese and French. | Not stated in the vendor sources reviewed.Source: openevidence.com | Not stated in the vendor sources reviewed.Source: wolterskluwer.com | Not stated in the vendor sources reviewed.Source: doximity.com (Doximity Ask) | Multilingual.Source: chatgpt.com |
Clinical decision support software: what it is and how the FDA treats it
Clinicians face more guidelines, trials and drug updates than anyone can track during a visit. Clinical decision support (CDS) software brings that knowledge to the point of care: alerts and order sets in the EHR, drug-interaction checkers, risk calculators and, more recently, AI that answers clinical questions in plain language.
The problem CDS has to solve
An answer a clinician cannot verify is hard to act on. When a tool does not show why it recommends something, clinicians either ignore it or lean on it too much. Useful clinical decision support is specific to the question, current, and transparent about its sources.
FDA's four criteria for non-device CDS
Section 3060(a) of the 21st Century Cures Act (2016) added section 520(o)(1)(E) to the Federal Food, Drug, and Cosmetic Act, which excludes certain CDS software functions from the definition of a medical device. FDA's guidance "Clinical Decision Support Software" (docket FDA-2017-D-6569; current version dated January 2026, as of October 2026) explains how the agency reads the criteria. A software function is non-device CDS only if it meets all four:
- It is not intended to acquire, process or analyze a medical image, a signal from an in vitro diagnostic device, or a pattern or signal from a signal acquisition system.
- It is intended to display, analyze or print medical information about a patient or other medical information, such as peer-reviewed clinical studies and clinical practice guidelines.
- It is intended to support or provide recommendations to a health care professional about the prevention, diagnosis or treatment of a disease or condition.
- It is intended to enable that health care professional to independently review the basis for the recommendations, so that the professional does not rely primarily on them to make a clinical diagnosis or treatment decision about an individual patient.
What the criteria mean in practice
A function that fails any one criterion may be a device subject to FDA oversight: for example, software that analyzes an ECG waveform or a medical image, software meant for patients or caregivers rather than professionals, or software whose basis the clinician cannot review. Whether a specific product qualifies depends on its intended use and labeling, and the guidance gives examples on both sides of the line. This section summarizes the law; it is not legal or regulatory advice.
Where Arkangel AI fits
Arkangel AI is a medical search assistant for health professionals. It answers clinical questions with the guidelines and studies cited, so the clinician can review the basis of each answer before acting. This page makes no claim of FDA clearance or of an FDA determination for any Arkangel AI product; check your own regulatory and institutional requirements before clinical use.
How Arkangel AI supports clinical decisions
Evidence-cited answers that you review before you act.
Answers with citations
Each answer links to the guidelines and studies it draws on, so you can check the basis of a recommendation instead of trusting a summary.
Options and trade-offs, not a verdict
For diagnostic and treatment questions it lays out the guideline-supported options, their benefits and risks, and the patient factors that change the choice.
The decision stays with you
Arkangel AI organizes the evidence; the clinician reviews it, applies it to the individual patient and decides with them.
Evidence-based search built for clinicians
Ask any clinical question and get a concise, cited answer drawn from peer-reviewed literature and clinical guidelines.
Explore potential documentation gaps
Review available, supported records for potential billing details and documentation gaps. Validate findings against the complete clinical context.
Evidence at your fingertips
Explore available clinical guidelines and literature, and check the sources and relevance of each finding before applying it.
Findings for clinical review
Surface potential clinical risks and documentation gaps in supported records for professional review. Timing and coverage depend on the configured workflow.
Review potential billing gaps
Identify possible missing charges or coding gaps in supported records. Billing professionals validate the documentation and applicable payer rules before making changes.
ISO 27001 Certified. HIPAA on Enterprise.
70+ security controls, penetration tested, and continuously monitored via Vanta.
Compliance Center
ISO 27001:2022 certified and penetration tested, with HIPAA compliance and a BAA on Enterprise plans. With 70+ security controls covering infrastructure, data privacy, and audit procedures—plus continuous monitoring via Vanta—Enterprise deployments protect PHI with cryptographic controls and information access restrictions.
Security & complianceBuilt for Healthcare Teams
Role-based access control, secure development policies, and system change procedures let your team collaborate safely. Scale across departments with audit trails, asset handling controls, and subprocessors like Azure for anonymization—all documented in our public Compliance Center.
Book a demoFrequently asked questions
What is clinical decision support software?
Clinical decision support (CDS) software gives clinicians patient-specific information or recommendations at the point of care: EHR alerts and order sets, drug-interaction checks, risk calculators and AI assistants that answer clinical questions. It supports the clinician's judgment; it does not replace it.
How is AI used in clinical decision support?
AI clinical decision support reads a clinical question written in plain language and returns an answer drawn from guidelines and studies. Arkangel AI cites the sources behind each answer so the clinician can verify it before acting.
Is clinical decision support software regulated by the FDA?
It depends on the function. Under section 520(o)(1)(E) of the FD&C Act, added by the 21st Century Cures Act, CDS software that meets four criteria is not a medical device. Functions that analyze medical images or device signals, that are meant for patients rather than professionals, or whose basis a clinician cannot independently review may be devices. FDA's guidance "Clinical Decision Support Software" (January 2026 version, as of October 2026) explains the criteria.
What are the four criteria for non-device CDS?
All four must be met: (1) the software does not acquire, process or analyze medical images or signals from in vitro diagnostic devices or signal acquisition systems; (2) it displays, analyzes or prints medical information, such as patient information, clinical studies or guidelines; (3) it supports or provides recommendations to a health care professional about prevention, diagnosis or treatment; and (4) it lets that professional independently review the basis for the recommendations, so they do not rely primarily on them.
Does Arkangel AI replace clinical judgment?
No. It lays out the evidence and the options with their sources; the clinician reviews them and makes the decision with the patient.
What does CDS stand for in medicine?
CDS stands for clinical decision support. AHRQ describes it as providing clinicians, staff, patients or others with knowledge and person-specific information, intelligently filtered or presented at appropriate times, to enhance health and health care. Examples include EHR alerts, order sets, guideline references and AI assistants such as Arkangel AI.
What are examples of clinical decision support tools?
ONC lists order sets tailored to specific conditions, patient data summaries and reports, documentation templates, diagnostic support, reference materials relevant to the situation, clinical guidelines, and computer alerts and reminders. AHRQ's CDS Connect shares free, interoperable CDS artifacts. AI assistants like Arkangel AI add cited answers to clinical questions.
What is clinical AI?
Clinical AI is artificial intelligence used in patient care workflows: decision support, documentation, imaging, risk prediction and chart review. For decision support, the safest clinical AI shows the guidelines and studies behind each answer so the clinician can review them. Arkangel AI works that way and keeps the decision with the clinician.
Compare Arkangel AI with other clinical tools
Clinical decision support, not a replacement
Arkangel AI supports clinical decision-making and does not replace clinician judgment. Always confirm recommendations against primary sources and your local protocols before acting.