Could we detect breast cancer with your fingerprint? | Simona Francese | TEDxManchester

Key Concepts:

• Breast cancer screening
• Mammography
• NHS backlogs
• Accessibility of screening
• Patient modesty and pain concerns
• Fingerprint analysis
• Mass spectrometry (MALDI)
• Molecular fingerprinting
• Biomarkers for breast cancer
• Machine learning for cancer detection
• Non-invasive screening

1. Breast Cancer Statistics and Screening Challenges:

• One in eight women will develop breast cancer, and one in 43 will die from it. Men are not immune.
• In 2022, there were 670,000 global deaths and 11,500 UK deaths from breast cancer (32 people every day). Cases are predicted to rise to 70,000 by 2040.
• Death rates are falling (44% reduction) due to interventions, better screening, and treatments, particularly early detection.
• Mammography is the gold standard for breast cancer screening, followed by biopsy if positive.
• The breast screening program invites women annually after a certain age, but uptake is often below the 70% target in some areas.
• Reasons for low uptake include NHS backlogs (exacerbated by COVID-19 and decades of underfunding), reduced resources, and a disproportion between screenings needed and available radiologists and equipment.
• Accessibility is a significant problem, especially for underserved populations.
• Modesty concerns, fear of radiation, and pain during mammography contribute to low uptake. A survey revealed that 21% of women avoid screening due to embarrassment and fear of pain.

2. Introducing a Novel Fingerprint-Based Screening Test:

• A potentially "game-changing" test is introduced that bypasses NHS backlogs, requires no additional NHS resources, preserves modesty, is non-invasive, and involves no radiation or pain.
• The test originates from fingerprint analysis techniques used in CSI.

3. The Science Behind Molecular Fingerprinting:

• Fingerprints are not just patterns of lines but molecular patterns unique to an individual.
• Sweat contains molecules produced, metabolized, and eliminated by the body, as well as substances picked up from the environment.
• Mass spectrometry (MALDI) measures the weight of molecules in fingerprints, identifying and visualizing them.
• Molecular images of fingerprints can reveal information about a person's lifestyle, medications, state of mind, and recent activities.
• Example: A fingerprint image showing the distribution of molecules from hair gel.
• Overlapping fingerprints can be resolved by identifying molecules unique to each print.

4. Fingerprint Analysis for Breast Cancer Detection:

• Research explored whether fingerprints could reveal a person's sex.
• Fingerprints were collected from donors, and MALDI was used to analyze protein profiles.
• Protein profiles differed significantly between men and women, allowing for sex identification with 86% accuracy.
• Serendipitously, some of these proteins were already identified in scientific literature as biomarkers for breast cancer.
• The idea emerged that proteins in fingertip smears might indicate whether a woman has breast cancer.

5. Proof-of-Concept Study and Results:

• A study was conducted with £45,000 in funding (plus additional funding).
• 15 women provided three fingerprint smears each, analyzed in three different locations (135 samples).
• Machine learning algorithms were trained to recognize protein patterns from women with early breast cancer, benign conditions, and metastatic cancer.
• The algorithm distinguished between these conditions with 97.8% accuracy, compared to 70-90% accuracy for mammograms.
• The confusion matrix showed two false positives but zero false negatives (the test identified every woman with cancer).

6. Potential Benefits and Future Vision:

• The fingerprint test could reduce NHS costs, bypass backlogs, require no additional resources, be non-invasive, painless, and radiation-free.
• It could increase accessibility by being administered at GP practices or even at home, with samples shipped for analysis.
• Increased compliance would save lives.
• The speaker believes this idea is worth investment, dedication, and perseverance.
• Cost of breast cancer interventions, treatment, and screening is estimated at 17.5 billion pounds.

7. Technical Terms:

• Mammography: An X-ray imaging method used to examine the breast for the early detection of breast cancer.
• Biopsy: The removal and examination of a tissue sample from a living body for diagnostic purposes.
• NHS: National Health Service, the publicly funded healthcare system in the United Kingdom.
• MALDI (Matrix-Assisted Laser Desorption/Ionization): A mass spectrometry ionization technique used for analyzing large molecules.
• Mass Spectrometry: An analytical technique that measures the mass-to-charge ratio of ions.
• Biomarkers: Measurable indicators of a biological state or condition.
• Machine Learning: A type of artificial intelligence that allows computer systems to learn from data without being explicitly programmed.
• Confusion Matrix: A table that summarizes the performance of a classification algorithm.
• False Positive: A test result that incorrectly indicates the presence of a condition when it is absent.
• False Negative: A test result that incorrectly indicates the absence of a condition when it is present.

8. Synthesis/Conclusion:

The video presents a compelling case for a novel, non-invasive breast cancer screening test based on fingerprint analysis. By leveraging mass spectrometry and machine learning, the test demonstrates promising accuracy in detecting breast cancer from protein patterns in fingerprints. This approach addresses key challenges associated with traditional mammography, such as NHS backlogs, accessibility issues, patient discomfort, and radiation exposure. The potential benefits include reduced healthcare costs, increased screening compliance, and ultimately, improved survival rates. The speaker advocates for further investment and development of this innovative technology.