A multi-institutional research team led by Dr Raj Nagarkar, Managing Director and Chief of Surgical Oncology and Robotic Services, HCG Manavata Cancer Centre (HCGMCC), Nashik, has developed a blood test that can detect 30 different types of cancers including pancreatic, lung, and ovarian cancers, with an average accuracy of 98.4 per cent. The study, recently published in Cancer Reports, utilised a novel serum metabolome-based diagnostic platform powered by machine learning to identify distinct metabolic signatures associated with cancer.
The trial included 6,445 participants, with over 2,800 confirmed, treatment-naïve cancer patients across four stages of the disease. Remarkably, the platform showed consistently high sensitivity even in early-stage (Stage I/II) cancers, a feat rarely achieved by current diagnostic standards.
“The test profiles over 8,000 metabolites in blood serum. In a clinical trial involving 6,445 participants, including 2,831 cancer patients, the test demonstrated near-perfect accuracy across all stages (I–IV) and age groups (20 to 80+ years). Notably, it identified Stage I cancers with 98.9 per cent sensitivity, addressing a critical gap in oncology where most tumours are diagnosed too late for curative treatment,” says Dr Nagarkar.
The model’s robustness was validated across multiple age groups, showing detection sensitivity consistently above 96 per cent across all demographics and cancer stages.
“Cancer’s stealth lies in its silence during early stages. By decoding the metabolic ‘fingerprint’ tumours leave in blood, we’ve created a universal sentinel that alerts us before symptoms arise. Early detection remains the single most effective strategy in reducing cancer-related mortality. Our metabolomics-based approach not only improves accuracy but also offers the potential for population-scale screening with minimal invasiveness,” adds Dr Nagarkar.
Unlike other multi-cancer early detection (MCED) tests that rely on detecting tumour DNA or cells that are often limited by low biomarker concentration, this test captures changes in metabolites, providing a more reliable and sensitive readout, especially for early-stage cancers. The serum samples were analysed using high-resolution mass spectrometry, and the data were interpreted through a proprietary Cancer Detection Artificial Intelligence (CDAI) algorithm developed in collaboration with PredOmix Technologies.
Dr Nagarkar highlights, “With cancer projected to become the leading cause of global mortality by 2030, early detection remains the most viable strategy to curb deaths. Current screening methods cover only five cancers and suffer from high false-positive rates. The new test, validated in a single-blinded trial, reduces over-diagnosis risks while expanding coverage to thirty malignancies. We believe this test has the potential to redefine cancer screening, especially in low- and middle-income countries like India. Its scalability, accuracy and ability to detect cancers early could enable Governments and healthcare providers to offer timely intervention, which ultimately saves lives and reduces the cost burden of late-stage treatment.”
This study is registered under CTRI/2023/03/050316 and has received all necessary ethics approvals. The research was conducted in collaboration with PredOmix Health Sciences; North East Cancer Hospital; Department of Radiotherapy, IPGME&R; Indoriv Clinical and multiple partner hospitals across India.
Dr Nagarkar concludes, “Currently, plans are underway to initiate larger, multi-centre clinical trials and eventually work toward commercial deployment. There are also ongoing efforts to integrate tissue-of-origin prediction capabilities, which would further support physicians in initiating precise follow-up diagnostics and treatment strategies. This isn’t just science; it’s hope. By catching cancer in its infancy, we transform survival odds and reduce the physical, emotional and financial toll of advanced disease.”