Lung Cancer Prediction AI
Optellum’s Lung Cancer Prediction AI helps physicians make optimal clinical decisions
A vast majority of incidentally detected pulmonary nodules fall into the indeterminate category between 5% and 65% cancer risk, the most challenging to manage. Patients bounce around from one procedure to another for many months before a definite diagnosis. This often leads to delayed start of treatment for patients with cancer and unnecessary aggressive procedures for patients with benign conditions.

In March 2021 Optellum received FDA 510(k) clearance for Virtual Nodule Clinic. Read the full announcement on our news and events pages.
For diagnosis of incidental pulmonary nodules, the Lung Cancer Prediction AI:
Increases the accuracy of malignancy assessment
Pulmonologists and Radiologists improved both their sensitivity and specificity at high-risk (65%) and low-risk (5%) ACCP guideline thresholds*.
Reduces variations between individual physicians
Improves the diagnostic accuracy of every pulmonologist and radiologist and makes them more consistent with each other*.
Improves clinical management decision making
22% of patients with malignant nodules were given more appropriate decisions**.
Has been independently clinically validated in multi-center studies
Published by guidelines co-authors in leading medical journals (see clinical validation)**.
How to compute the score for one or more nodules of interest
Optellum Lung Cancer Prediction AI integrates with Virtual Nodule Clinic to provide diagnostic assistance to clinicians.
Read more about the Optellum platform or contact our sales team.
Optellum Lung Cancer Prediction (LCP) FDA 510(K).
* results from an enriched clinical study.
** [1] Massion, Pierre P., et al. “Assessing the accuracy of a deep learning method to risk stratify indeterminate pulmonary nodules.” American journal of respiratory and critical care medicine 202.2 (2020): 241-249.
[2] Baldwin, David R., et al. “External validation of a convolutional neural network artificial intelligence tool to predict malignancy in pulmonary nodules.” Thorax 75.4 (2020): 306-312.
[3] Dotson, T. L., et al. “AI-Based Computer-Aided Diagnosis (CADx) Improves Stratification Decisions on Indeterminate Pulmonary Nodules: An MRMC Reader Study.” D99. ADVANCING RISK ASSESSEMENT FOR PULMONARY NODULES. American Thoracic Society, 2020. A7691-A7691. (paper in review)