Optellum, Johnson & Johnson launch strategic collaboration in lung cancer
In March 2021, the FDA cleared Optellum’s Virtual Nodule Clinic, an AI-based clinical decision support software for pulmonologists and radiologists treating patients with small lesions that may represent lung cancer to an early stage.2 This is the first time that the FDA has authorized such an AI decision support application for the early diagnosis of lung cancer.
The software integrates an AI-based digital biomarker based on neural networks and imaging analyzes. Virtual Nodule Clinic identifies and follows high risk patients and assigns a lung cancer prediction score to lung nodules which may be malignant and are typically detected in chest CT scans.
In the pivotal clinical study measuring physicians’ mean accuracy in classifying nodules as malignant or benign, 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) (P <.001 overall and an improvement of to auc points for each physician. in addition improving diagnostic accuracy the use ai has resulted greater consistency among physicians.>
In an independent validation study, researchers compared AI’s risk prediction model to Brock University’s model recommended in UK guidelines. There were 1397 nodules in 1187 patients, of which 234 nodules in 229 (19.3%) patients were cancerous. AUC for Virtual Nodule Clinic was 89.6% (95% CI, 87.6% to 91.5%) versus 86.8% (95% CI, 84.3% to 89.1%) for the Brock model (P .005).
The researchers found that 24.5% of the nodules had a score lower than the lowest cancerous nodule score with AI, compared to 10.9% with the Brock score. Using predefined cut-offs, investigators concluded that the AI delivered 1 (0.4%) false positive while the Brock model delivered 6 (2.5%). The specificity statistics were similar between the 2 models.
Doctors 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 in the precancerous stage.
“I believe the next step in diagnosing and treating lung cancer is to see new emerging technologies come together. AI is essential to enable the 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 Hospitals of the ‘UCL, vice chairman of the UK National Clinical Lung Cancer Reference Group and member of Optellum’s medical advisory board, said in a press release. “This convergence of technologies has enormous potential to help physicians prevent, intercept and ultimately cure patients with early stage lung cancer.”
Lung cancer is the leading cause of cancer death and the second most common cancer in the United States. Each year, more people die from lung cancer than from colon, breast and prostate cancers combined. The American Cancer Society predicted 131,880 lung cancer deaths 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 stages of the disease. However, survival is significantly better when the disease is detected early. The 5-year relative survival rate is 63% for localized disease compared to only 7% for metastatic NSCLC.6
The move is part of Johnson & Johnson’s larger efforts to fight lung cancer. In 2018, the company announced that it would fund a Lung Cancer Center at Boston University Medical Center (BU) led by Avrum Spira, MD, professor of medicine, pathology and bioinformatics at the BU and global head of the company’s Lung Cancer Initiative.
“This collaboration is an important step for Optellum,” said Václav Potěšil, PhD, founder and CEO of Optelum in the press release. “This brings us one step closer to our vision of redefining early treatment for lung cancer by helping every clinician, in every hospital, make the right decisions and give their patients the best chance to fight back. “
- Optellum announces strategic collaboration with the Lung Cancer Initiative at Johnson & Johnson, applying AI to transform early treatment of lung cancer. Press release. Optellum. August 18, 2021. September 1, 2021. https://bit.ly/3tordj9
- Optellum receives FDA clearance for the world’s first AI-based clinical decision support software for the early diagnosis of lung cancer. Press release. Optellum. March 23, 2021. Accessed September 1, 2021. https://optellum.com/2021/03/fda-clearance.
- Vachani A, Massion PP, Munden RF, et al., Decision Aid Imaging AI / “Radiomics” Improves Stratification of Lung Nodules Undetermined by Physicians: an MRMC Study Presented to Baldwin DR, Gustafson J, Pickup L, et al. External validation of a convolutional neural network artificial intelligence tool to predict malignancy in lung nodules. Thorax. 2020; 75 (4): 306-312. doi: 10.1136 / thoraxjnl-2019-214104
- American Cancer Society National Lung Cancer Roundtable (NLCRT) 2020. https://vimeo.com/487367357
- 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
- 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