Live
- Coronation of Nathdwara MLA Vishvaraj Singh as Mewar's 77th successor starts amid question mark over palace visit
- WhatsApp Outage: Global Users Face Issues with Messaging App on Web
- Post-poll violence breaks out in Jharkhand after announcement of results
- Spiking to be made criminal offence: British PM
- MP CM in UK to woo investors thanks High Commission, diaspora for support (Ld)
- India's Stunning 295-Run Victory Over Australia: Bumrah and Siraj Lead Charge
- Chinese rocket debris reenters atmosphere, mostly burning up
- Winter Session of Parliament Begins with Key Bills and Heated Debates
- BGT 2024-25: India begin trophy defence with triumph over Australia in Perth
- Supreme Court trashes pleas challenging insertion of ‘Socialist’, ‘Secular’ in Preamble to Constitution
Novel model to predict lung cancer survival developed
Researchers have developed a deep-learning model that may help predict lung cancer survival and outcomes.
New York:Researchers have developed a deep-learning model that may help predict lung cancer survival and outcomes.
The findings suggests that the model, using serial image scans of tumours from patients with non-small cell lung cancer (NSCLC), predicted treatment response and survival outcomes better than standard clinical parameters.
"Our research demonstrates that deep-learning models integrating routine imaging scans obtained at multiple time points can improve predictions of survival and cancer-specific outcomes for lung cancer," said Hugo Aerts, Associate Professor at Harvard University.
"By comparison, a standard clinical model relying on stage, gender, age, tumour grade, performance, smoking status, and tumour size could not reliably predict two-year survival or treatment response," Aerts added.
For the study, published in the journal Clinical Cancer Research, the researchers built deep-learning models to see if they could extract more predictive insights as cancers evolve.
They trained their models using serial CT scans of 179 patients with stage 3 NSCLC who had been treated with chemoradiation. They included up to four images per patient obtained routinely before treatment and at one, three, and six months after treatment for a total of 581 images.
The investigators analysed the model's ability to make significant cancer outcome predictions with two datasets -- the training dataset of 581 images and an independent validation dataset of 178 images from 89 patients with non-small cell lung cancer who had been treated with chemoradiation and surgery.
The team found that the models' performance improved with the addition of each follow-up scan. The area under the curve, a measure of the model's accuracy, for predicting two-year survival based on pre-treatment scans alone was 0.58, which improved significantly to 0.74 after adding all available follow-up scans.
Patients classed as having low risk for mortality by the model had six-fold improved overall survival compared with those classed as having high risk.
