Inside RAPID: The Proposed Route to Faster Medicare Device Coverage
Dr. Dereck Mush, MD, MBA
In partnership with
Nobody's coming to approve your idea
People assume that real businesses get built by other people with more resources. It's how great ideas get stuck in notes apps and conversations.
But you don't need six months and a developer's salary to validate your concept. You just need a weekend. Describe what you want to exist and Lovable builds it: a real site, a real product, ready to accept real payments from real customers. Not a mockup to show people. An actual thing they can use.
You don't need anyone's sign-off to get started. Take $5 off your first month.
Discount of $5 applies to first month of any paid plan. You need to sign up via this webpage in order to claim the discount. The discount applies to new and returning users without an active paid plan. Terms apply.
NEURAL HARDWARE & WEARABLES
1. RAPID’s Comment Window Closes: What the Proposed Coverage Route Would Change
FDA’s White Oak campus in Maryland. The proposed RAPID pathway would coordinate device development and Medicare coverage review.
With comments on CMS’s RAPID proposal due October 13, attention now turns to the agency’s response and final procedural notice. The pathway was announced in April and detailed in August. Its ambition is to coordinate device development and coverage evidence early enough to shorten the wait after FDA authorization.
The details:
The timing is a goal, not a guarantee. For qualifying devices with sufficient evidence, the proposal describes a proposed NCD alongside FDA authorization, followed by a final NCD roughly 60 days later for Class II devices or 90 days for Class III devices.
Eligibility is narrow. It covers specified Breakthrough devices at IDE pre-submission, including certain Class II TAP devices and eligible Class III PMA candidates. The proposal also includes benefit-category and separate-payability conditions; IVDs are excluded.
Evidence still matters. The planned study must address Medicare beneficiaries and relevant health outcomes. Additional evidence development may still be needed; a coverage decision should not be treated as automatic paid utilization.
The Signal: The useful shift is earlier planning. Device teams should work through the evidence and coverage questions while the study can still be shaped, and keep coding, payment and provider adoption visible as separate milestones.
AI DRUG DISCOVERY
2. AstraZeneca and insitro Strike AI Drug-Discovery Deal With $40M Upfront
Inside AstraZeneca’s Discovery Centre in Cambridge, UK. Its insitro collaboration targets new medicines for MASH and cardiomyopathies.
AstraZeneca and insitro announced an exclusive research collaboration on October 15 targeting metabolic dysfunction-associated steatohepatitis (MASH) and cardiomyopathies. The deal pairs insitro’s AI-enabled discovery platform with AstraZeneca’s development and commercial capabilities.
The details:
The committed payment is $40M upfront. Approximately $1.46B in additional milestones is contingent on future progress; potential single-digit royalties are separate.
The work starts before the clinic. insitro will apply its Virtual Human platform and advance AstraZeneca-nominated targets toward development candidates.
AstraZeneca owns the next stages. It will lead clinical development, regulatory activities and commercialization. No successful medicine or shorter development timeline has yet been demonstrated by this agreement.
The Signal: The meaningful commitment is the upfront payment and division of work. The larger headline value depends on candidates making it through a development process that still carries scientific and clinical risk.
CONNECTED CARE
3. Penn Tests AI That Lets Patients Communicate With Epilepsy Monitors
A patient uses a smartphone beside a hospital bed. Penn researchers tested a conversational interface linking patient questions and symptom reports with epilepsy-monitoring data.
A Nature Medicine study published October 13 explored a more interactive relationship between patients and monitoring technology. Thirteen adults undergoing inpatient epilepsy monitoring at Penn used a smartphone interface connected to EEG analytics, with an AI conversation layer for questions, alerts and symptom reports.
The details:
This was a hospital feasibility study. The single-center observational study did not change standard-of-care treatment or establish effectiveness for home use.
The live detector stayed fixed. Only the validated baseline seizure detector was deployed during patient sessions. Model fine-tuning was evaluated separately through sequential replay of data.
The false-alarm finding needs that context. The separate fine-tuning comparison reported a median 77.8% reduction in false alarms per hour across patients. That is not evidence of fewer clinical seizures or improved long-term outcomes.
The Signal: Patient feedback could become useful input for medical monitoring. This study supports further testing of that interaction; it does not yet establish a self-improving home-care device or autonomous treatment system.
Related reading
Dr. Dereck Mush, MD, MBA
Medicare finally pays for prescription digital therapeutics, and the test begins
Dr. Dereck Mush, MD, MBA
The MCED Inflection Point: What Galleri's FDA Panel Backing Means for Cancer Screening
Dr. Dereck Mush, MD, MBA
From IT Expense to Revenue Driver: How CMS NTAP Activates the Clinical AI Commercial Flywheel
Dr. Dereck Mush, MD, MBAKeep exploring