Deep learning techniques can be used to triage suspected cases of Barrett oesophagus, a precursor to oesophageal cancer, potentially leading to faster and earlier diagnoses, say researchers at the University of Cambridge. When researchers applied the technique to analysing samples obtained using the'pill on a string' diagnostic tool Cytosponge, they found that it was capable of reducing by half pathologists' workload while matching the accuracy of even experienced pathologists. Early detection of cancer often leads to better survival because pre-malignant lesions and early stage tumours can be more effectively treated. This is particularly important for oesophageal cancer, the sixth most common cause for cancer-related deaths. Patients usually present at an advanced stage with swallowing difficulties and weight loss.

Dr. Diagnosio that uses deep learning, matures to a virtual doctor with the capability to make both differential diagnoses and to triage patients. Dr. Diagnosio is now able to triage patients based on a questionnaire on the patient symptoms progression. The Swedish company BraineHealth recently launched Dr. Diagnosio – a virtual doctor that proposes diagnoses from vital patient data such as age, gender and patient symptoms. Dr. Diagnosio uses machine-learning methods to match the most relevant diagnoses based on a validated database. The virtual doctor Diagnosio has now extended its capabilities by asking the patient additional essential questions about how the symptoms are developing, current discomfort, medication, medical condition and more.

Two decades on from artificial intelligence beating chess grandmaster Garry Kasparov, AI is proving it can do some conventionally human jobs. One UK-based health app now hopes its AI can take over some tasks that would usually only be trusted to a doctor or nurse. In a swish new office in London's Chelsea on Tuesday, health technology firm Babylon pitted its app against a junior doctor and a nurse with 20 years of accident and emergency experience. The machine and the medical professionals were tasked with deciding the priority of treatment for an ailment, a process known in the medical profession as triage. Irwin Nazareth, professor of primary care and population sciences at UCL and a committee chairman at Health Education England, moderated the challenge and ruled the artificial intelligence was as accurate as the nurse and doctor in its assessments.