Optellum, Johnson & Johnson Launch Strategic Collaboration in Lung Cancer

Sam Janes, MD

Optellum, a lung-health medical technology startup based in the United Kingdom, and the Lung Cancer Initiative at Johnson & Johnson in August have announced an ongoing partnership. The 2 companies plan to use Optellum’s artificial intelligence (AI)-based decision support software in an effort to increase lung cancer survival rates via disease prevention and early intervention.¹

In March 2021, the FDA gave clearance to Optellum’s Virtual Nodule Clinic, an AI-powered clinical decision support software for pulmonologists and radiologists treating patients with small lesions that could represent early-stage lung cancer.² This is the first time the FDA has cleared such an application of AI decision support for early lung cancer diagnosis.

The software incorporates an AI-powered digital biomarker that is based on neural networks and imaging analytics. Virtual Nodule Clinic identifies and tracks patients at elevated risk and assigns a Lung Cancer Prediction score to lung nodules that may be malignant and are usually detected in chest CT scans.

In the pivotal clinical study measuring physicians’ average accuracy in classifying nodules as malignant or benign, the AI was associated with a statistically significant improvement in accuracy in all readers.^3,4 Investigators observed an average improvement of 6.85 area under the curve (AUC) points (P <.001) overall and an improvement of 2.4 to 12.1 AUC points for individual physicians. In addition to improved diagnostic accuracy, use of the AI resulted in more consistency among physicians.

In an independent validation study, investigators compared the AI’s risk-prediction model vs the Brock University model recommended in UK guidelines. There were 1397 nodules in 1187 patients, of which 234 nodules in 229 (19.3%) patients were cancer. The AUC for Virtual Nodule Clinic was 89.6% (95% CI, 87.6%-91.5%) compared with 86.8% (95% CI, 84.3%-89.1%) for the Brock model (P ≤.005).

Investigators found that 24.5% of nodules scored below the lowest cancer nodule score with the AI compared with 10.9% using the Brock score. Using predefined thresholds, investigators concluded that the AI delivered 1 (0.4%) false positive while the Brock model delivered 6 (2.5%). Specificity statistics were similar between the 2 models.

Physicians can use the software to develop accurate early diagnosis and optimal treatment decisions. The companies hope to improve survival rates by treating patients earlier, even at the precancerous stage.

“I believe the next step in lung cancer diagnosis and treatment is seeing the emerging new technologies coming together. AI is key to enabling integration of imaging, clinical, and molecular data—such as liquid biopsies—to diagnose disease even earlier,” Sam Janes, MD, head of the Respiratory Research Department at UCL Hospitals, vice-chair of the UK National Clinical Reference Group for Lung Cancer, and member of the Optellum Medical Advisory Board, said in a news release. “This convergence of technologies has tremendous potential to help physicians prevent, intercept, and ultimately cure patients with early-stage lung cancer.”

Lung cancer is the leading cause of cancer deaths and is the second-most common cancer in the United States—annually, more people die of lung cancer than of colon, breast, and prostate cancers combined. The American Cancer Society predicted 131,880 deaths from lung cancer in 2021, with 119,100 new diagnoses in men and 116,660 new diagnoses.⁵

The 5-year survival rate for non-small cell lung cancer (NSCLC), the most common form of the disease, is 25% for all disease stages. However, survival is significantly better when the disease is detected early. The 5-year relative survival rate is 63% for localized disease compared with just 7% for metastatic NSCLC.⁶

This move is part of Johnson & Johnson’s larger efforts to address lung cancer. In 2018, the company announced that it would fund a Lung Cancer Center at Boston University (BU) Medical Center led by Avrum Spira, MD, professor of medicine, pathology and bioinformatics at BU and global head of the company’s Lung Cancer Initiative.

“This collaboration is a significant milestone for Optellum,”Václav Potěšil, PhD, Optelum founder and CEO said in the news release. “It brings us one step closer to our vision of redefining early lung cancer treatment by helping every clinician, in every hospital to make the right decisions and provide their patients the best chance to fight back.”

References

1. Optellum Announces Strategic Collaboration with the Lung Cancer Initiative at Johnson & Johnson, Applying Ai To Transform Early Lung Cancer Treatment. News release. Optellum. August 18, 2021. September 1, 2021. https://bit.ly/3tordj9
2. Optellum Receives Fda Clearance for the World’s First Ai-Powered Clinical Decision Support Software for Early Lung Cancer Diagnosis. News release. Optellum. March 23, 2021. Accessed September 1, 2021. https://optellum.com/2021/03/fda-clearance.
3. Vachani A, Massion PP, Munden RF, et al., Imaging AI/”Radiomics” decision support improves physicians’ stratification of indeterminate pulmonary nodules: An MRMC study presented to the Baldwin DR, Gustafson J, Pickup L, et al. External validation of a convolutional neural network artificial intelligence tool to predict malignancy in pulmonary nodules. Thorax. 2020;75(4):306-312. doi:10.1136/thoraxjnl-2019-214104
4. American Cancer Society National Lung Cancer Roundtable (NLCRT) 2020. https://vimeo.com/487367357
5. American Cancer Society. Key Statistics for Lung Cancer. Revised January 12, 2021. Accessed September 3, 2021. https://www.cancer.org/content/cancer/en/cancer/lung-cancer/about/key-statistics.html
6. American Cancer Society. Lung Cancer Survival Rates Revised January 29, 2021. Accessed September 3, 2021. https://www.cancer.org/cancer/lung-cancer/detection-diagnosis-staging/survival-rates.html