Utilizing artificial intelligence to analyze GP records for hidden patterns has significantly improved cancer detection rates for doctors.
The “C the Signs” AI tool used by general practitioner practices has increased cancer detection rates from 58.7% to 66.0%. This tool examines patients’ medical records, compiling past medical history, test results, prescriptions, treatments, and personal characteristics like age, postcode, and family history to indicate potential cancer risks.
Additionally, the tool prompts doctors to inquire about new symptoms and recommends tests or referrals for patients if it detects patterns suggesting a heightened risk of certain cancer types.
Currently in use in about 1,400 practices in England, “C the Signs” was tested in 35 practices in the East of England in May 2021, covering 420,000 patients.
Published in the Journal of Clinical Oncology, a study revealed that cancer detection rates rose from 58.7% to 66.0% by March 31, 2022, in clinics using the system, while remaining similar in those that did not utilize it.
Dr. Bea Bakshi, who developed “C the Signs” with colleague Miles Paling, emphasized the importance of early and quick cancer diagnosis through their system detecting over 50 types of cancer.
The tool was validated in a previous study analyzing 118,677 patients, where 7,295 were diagnosed with cancer and 7,056 were accurately identified by the algorithm.
Notably, the system’s ability to predict if a patient was unlikely to have cancer resulted in only 2.8% of these cases being confirmed with cancer diagnosis within six months.
Concerned by delays in cancer diagnosis, Bakshi developed the tool after witnessing a patient’s late pancreatic cancer diagnosis three weeks before their death, highlighting the importance of early detection.
“With two-thirds of deaths from untestable cancers, early diagnosis is crucial,” Bakshi emphasized.
In the UK, GPs follow National Institute for Health and Care Excellence guidelines to decide when to refer patients for cancer diagnosis, guided by tools like “C the Signs.”
The NHS’s long-term cancer plan aims to diagnose 75% of cancers at stage 1 or 2 by 2028, utilizing innovative technologies like the Garelli blood test for early cancer detection.
Decision support systems like “C the Signs,” improving patient awareness of cancer symptoms, and enhancing access to diagnostic technologies are essential for effective cancer detection, according to healthcare professionals.
NHS England’s national clinical director for cancer, Professor Peter Johnson, highlighted the progress in increasing early cancer diagnoses and access to timely treatments, emphasizing the importance of leveraging technology for improved cancer care.
Source: www.theguardian.com
