Industry Insights: AI. The role of AI in MedComms - a bi-weekly update

Industry Insights: AI 11th August

Industry Insights: AI 11th August

  • Reading time:2 mins read

Industry Insights AI: 08/11/25

In this week’s insights post, we discuss some of the latest advancements in the application of artificial intelligence (AI) in healthcare.

Human-AI synergy may enhance surgical training
A recent study from JAMA Surgery has found that combining human expertise with AI-generated guidance dramatically improves surgical training outcomes. The study involved 88 surgical trainees from four medical schools in Canada. Trainees who received personalised feedback from instructors informed by AI insights outperformed those who received only AI feedback or human guidance, respectively. According to the study, a combination of human judgment and AI feedback significantly reduces trainee errors in complex tasks like managing bleeding and minimising injury risk. 

Link to study

AI-assisted ECG interpretation promises to revolutionise cardiology diagnostics
EchoNext, a sophisticated AI-assisted model, performed better than cardiologists in detecting structural heart disease (SHD) from routine electrocardiograms (ECGs). Structural heart diseases represent a largely common but still underdiagnosed group of diseases including valve disease, cardiomyopathy, pulmonary hypertension and heart thickening. EchoNext was trained on over 1 million ECG-echocardiography rhythm and imaging records to detect many forms of structural heart disease. In comparative testing, the model achieved 77% accuracy versus 64% for human specialists. 

Link to study

Machine learning can help assess prognosis in advanced colorectal cancer
A study published in Frontiers in Oncology has presented a new machine learning (ML) model that can predict 5‑year postoperative survival for patients with stage III colorectal cancer (CRC). CRC is the second leading cause of cancer-related deaths worldwide. The model used data from over 13,800 patients. It evaluated key demographic and clinical factors, such as age, lymph node ratio, chemotherapy status and T stage. The model outperformed traditional staging systems with strong predictive metrics. This ML approach promises to guide personalised CRC therapies and improve long-term patient survival.

Link to study

For more industry insights, visit elion.nz/insights/.

Want to get in touch? Contact us at https://elion.nz/get-in-touch/

Elion