AI in Medicine — Cancer & Rare Disease — 2026-09-28 (Mon) Morning News

Latest news on AI and cancer treatment

Overview

Several movements were seen in the diagnostic/imaging field (breast cancer screening, pancreatic cancer risk prediction, pathology/image-based technology). In the field of treatment selection and drug discovery, an AI drug discovery partnership with Roche was reported. Separate regulatory approval/designation information is not included in the heading.

Breast cancer

- Target: Breast cancer recurrence risk assessment. Study shows AI can provide more precise prediction of recurrence risk (MedicalNewsToday, no detailed research stage). - Target: Mammography for breast cancer detection. It was reported that India's PGIMER (Institute of Medical Research and Education) is proceeding with the introduction of AI-assisted mammography equipment (introduction stage, no clinical results listed).

lung cancer

No relevant information (there is a general oncology-related report in the headline stating that AI informs doctors of the uncertainty regarding the success of cancer treatment, but there is no mention specific to lung cancer).

Malignant brain tumor

No applicable information

Leukemia/lymphoma

No applicable information

Colon cancer/digestive organ

- Target: Pancreatic cancer risk. It was reported that a research team at the Mayo Clinic has developed an AI model that predicts the risk of pancreatic cancer up to three years before the onset of the disease (single-center study, development stage; forward-looking/retrospective and accuracy indicators are not listed in the headline).

Rare cancer

No applicable information

Diagnosis/Pathology/Image

- It was reported that there is a system in which AI notifies doctors when AI is uncertain about the likelihood of success in cancer treatment (Bioengineer.org, target cancer type and verification stage not listed). - The introduction of "Agentic AI" (autonomous AI) into the field of medical oncology and its development from AI joint decision-making support to autonomous tumor board operations was discussed (Oncodaily, concept/perspective article). - A survey on knowledge, attitude, and awareness of AI among medical students was reported (Cureus, an education/awareness survey, not an evaluation of clinical performance).

Treatment selection/drug discovery

- It was reported that Roche Holding has entered into a new AI drug discovery partnership (Yahoo Finance, no details on development stage or target disease). - It was reported that Heidelberg was recruiting for medical AI-related postdocs, engineers, and researchers (information on research infrastructure, not an announcement of results).

Regulations/Approval

No relevant information (There is an editorial titled ``Why excellent medical AI continues to fail in clinical practice,'' but the heading does not include information on approval and designation of individual products by FDA, EMA, and PMDA.)

Clinical trial implementation status

No relevant information (No specific description of the trial name, target cancer type, phase, or registration status from ClinicalTrials.gov can be found in the provided text).

Japanese movements

No applicable information

Remarks from VIPs

No relevant information (the list of important people being tracked is blank, and quotations with titles are not included in the headings).

Note: This report is based solely on the headline text provided and does not refer to the text of the linked article. Numerical values, causal relationships, and clinical significance are not described beyond the scope specified in the heading.

Latest news on AI and rare and incurable diseases

Overview

Only three headlines were collected this time, and there is little concrete content indicating major progress in diagnosis, therapeutic drugs, or systems. There are fragments of stock news on genome-related stocks, a doctoral student's efforts on applying machine learning to gene therapy, and an academic conference presentation on retinal inflammation detection using AI. There are no headlines that directly refer to shortening the diagnosis of designated intractable diseases, approving therapeutic drugs, or reforming the system.

Diagnosis of rare diseases

No applicable information

Gene analysis/genome

A stock-related article about TEMPUS AI (NASDAQ: TEM) was found, but the content was chart information for investors, and it was not possible to confirm from the headline what kind of genetic analysis and mutation determination the company had conducted in the rare disease field. Since there is no description of specific analysis methods, judgment accuracy, or target diseases, it is not possible to evaluate the content.

Development of therapeutic drugs

There is a headline that a doctoral student at the University of North Carolina at Chapel Hill in the US is working on gene therapy research using machine learning. The stage is not clear from the headline, and it is not possible to determine whether it is in the preclinical stage or the basic research stage. There is no specific description of target disease names, drug names, or effects.

Nerve/muscular diseases

No applicable information

Immunology/Collagen disease

At Retina Society 2026, it was announced that AI can detect retinal inflammation without using staining. The target disease name, number of cases, and detection accuracy are unclear from the headline, and the information is only at the presentation stage at an academic conference (it is not possible to confirm whether it is a peer-reviewed paper or a case report). A direct relationship with the immunological disease group listed in the heading (Takayasu's arteritis, Behcet's disease, etc., 348 diseases included in the above list) has not been shown.

Rare metabolic/endocrine diseases

No applicable information

System/Patient Support

No applicable information

Japanese movements

No applicable information

Remarks from VIPs

No applicable information