AI/ML, Software as a Medical Device, Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K240786 · Oct 10, 2024
AutoChamber
HeartLung Corporation
Multi-Ethnic Study of Atherosclerosis (MESA) database; Retrospective clinical study databases (cardiac MRI and CT scan cohorts)
Retrospective analysis of existing clinical study databases was used to validate the device's performance by comparing AutoChamber measurements against cardiac MRI ground truth and across different CT scan modalities.
Retrospective analysis; Clinical validation; Cardiac imaging; MESA study
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Comparison with cardiac MRI; Retrospective analysis
5003 cases who underwent both non-contrast cardiac CT scan and cardiac MRI; Sample Size: 5003
Cardiac MRI
Comparison of AutoChamber measurements with cardiac MRI measurements
Paired CT scan comparison; Retrospective analysis
1433 patients with paired non-contrast and contrast-enhanced cardiac CT scans; Sample Size: 1433
Not applicable for this study
Comparison of AutoChamber results in paired scans
ECG-gated vs. non-gated scan comparison; Retrospective analysis
171 patients who underwent both ECG-gated cardiac CT scan and non-gated full chest lung scan; Sample Size: 171
Not applicable for this study
Comparison of AutoChamber results across scan types
AI Performance
Output
Algorithm
Acceptance
Observed
Dev DS
Dev Readers
Test DS
Test Readers
Cardiac chamber volumes
Deep learning model
—
—
—
—
Retrospective analysis of 5003 cases (compared to cardiac MRI); 1433 patients (paired non-contrast and contrast-enhanced CT); 171 patients (ECG-gated vs non-gated CT); 131 cases (compared to reference device K060937).
—
Cardiothoracic ratio (CTR)
Deep learning model
—
—
—
—
Retrospective analysis of 5003 cases (compared to cardiac MRI); 1433 patients (paired non-contrast and contrast-enhanced CT); 171 patients (ECG-gated vs non-gated CT); 131 cases (compared to reference device K060937).
—
Indications for Use
The AutoChamber software is an opportunistic AI-powered quantitative imaging tool that measures and reports cardiac chambers volumes comprising left atrium (LA), left ventricle (LV), right atrium (RA), right ventricle (RV), and left ventricular wall (LVW) from non-contrast chest CT scans including coronary artery calcium (CAC) scans and lung CT scans. AutoChamber is not intended to rule out the risk of a cardiovascular disease, and the results should not be used for any purpose other than to enable physicians to investigate patients that AutoChamber shows signs of enlarged heart (cardiomegaly), enlarged cardiac chambers, and left ventricular hypertrophy (LVH) whose conditions are otherwise missed by human eyes in non-contrast CT scans. AutoChamber similarly measures and reports LA, LV, RA, RV, and LVW in contrast-enhanced coronary CT angiography (CCTA) scans. Additionally, AutoChamber measures and reports cardiothoracic ratio (CTR) in both contrast and non-contrast CT scans where the entire thoracic cavity is in the axial field of view. AutoChamber quantitative imaging measurements are adjusted by body surface area (BSA) and are reported both in cubic centimeter volume (cc) and percentiles by gender using reference data from 5830 people who participated in the Multi-Ethnic Study of Atherosclerosis (MESA). AutoChamber should not be ordered as a standalone CT scan but instead should be used as an opportunistic add-on to existing and new CT scans of the chest, such as CAC and lung CT scans, as well as CCTA scans. Using AutoChamber quantitative imaging measurements and their clinical evaluation, healthcare providers can investigate asymptomatic patients who are unaware of their risk of heart failure, atrial fibrillation, stroke and other life-threatening conditions associated with enlarged heart, enlarged cardiac chambers, and LVH that may warrant additional riskassessment or follow-up. AutoChamber quantitative imaging measurements are to be reviewed by radiologists or other medical professionals and should only be used by healthcare providers in conjunction with clinical evaluation.
Device Story
AutoChamber is an AI-powered post-processing software module for opportunistic cardiac analysis on chest CT scans (non-contrast and contrast-enhanced). It inputs DICOM CT images; uses a deep learning model to segment and identify cardiac chambers (LA, LV, RA, RV) and LV wall; calculates volumes in cc; adjusts for body surface area (BSA); and compares results against MESA reference percentiles. It also calculates cardiothoracic ratio (CTR) when the full thoracic cavity is in the axial field of view. The software is installed by trained personnel and executed via a parent system; it provides no direct user controls or editing capabilities. Radiologists or medical professionals review the output to confirm correct anatomical placement of segmentations. The device assists in identifying asymptomatic patients with potential cardiomegaly, enlarged chambers, or LVH for further clinical investigation. It does not provide individualized risk scores or diagnostic predictions.
Clinical Evidence
No prospective clinical studies were required. Clinical validation relied on retrospective analysis of existing databases: 5,003 cases compared AutoChamber vs. cardiac MRI; 1,433 patients compared non-contrast vs. contrast-enhanced CT; 171 patients compared ECG-gated vs. non-gated scans; and 131 cases compared AutoChamber vs. a reference device (K060937).
Technological Characteristics
Software-only device (SaMD). Operates on Linux. Uses deep learning-based segmentation for cardiac chambers. Inputs: DICOM CT images. Outputs: Volumetric measurements (cc), BSA-adjusted volumes, and percentiles based on MESA reference data. No hardware components.
Indications for Use
Indicated for patients undergoing chest CT scans (including CAC, lung CT, and CCTA) to measure and report cardiac chamber volumes (LA, LV, RA, RV) and LV wall mass to assist physicians in identifying cardiomegaly, enlarged cardiac chambers, and LVH in asymptomatic patients.
Regulatory Classification
Identification
A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.
Special Controls
*Classification.* Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.