27 November 2024 in Journal of Medical Internet Research
Background: Hereditary breast and ovarian cancer (HBOC) is a major type of hereditary cancer. Establishing effective screening to identify high-risk individuals for HBOC remains a challenge. We developed a prototype of a chatbot system that uses artificial intelligence (AI) for preliminary HBOC screening to determine whether individuals meet the National Comprehensive Cancer Network BRCA1/2 testing criteria. Objective: This study’s objective was to validate the feasibility of this chatbot in a clinical setting by using it on a patient population that visited a hospital. Methods: We validated the medical accuracy of the chatbot system by performing a test on patients who consecutively visited the Kanagawa Cancer Center. The participants completed a preoperation questionnaire to understand their background, including information technology literacy. After the operation, qualitative interviews were conducted to collect data on the usability and acceptability of the system and examine points needing improvement. Results: A total of 11 participants were enrolled between October and December 2020. All of the participants were women, and among them, 10 (91%) had cancer. According to the questionnaire, 6 (54%) participants had never heard of a chatbot, while 7 (64%) had never used one. All participants were able to complete the chatbot operation, and the average time required for the operation was 18.0 (SD 5.44) minutes. The determinations by the chatbot of whether the participants met the BRCA1/2 testing criteria based on their medical and family history were consistent with those by certified genetic counselors (CGCs). We compared the medical histories obtained from the participants by the CGCs with those by the chatbot. Of the 11 participants, 3 (27%) entered information different from that obtained by the CGCs. These discrepancies were caused by the participant’s omissions or communication errors with the chatbot. Regarding the family histories, the chatbot provided new information for 3 (27%) of the 11 participants and complemented information for the family members of 5 (45%) participants not interviewed by the CGCs. The chatbot could not obtain some information on the family history of 6 (54%) participants due to several reasons, such as being outside of the scope of the chatbot’s interview questions, the participant’s omissions, and communication errors with the chatbot. Interview data were classified into the following: (1) features, (2) appearance, (3) usability and preferences, (4) concerns, (5) benefits, and (6) implementation. Favorable comments on implementation feasibility and comments on improvements were also obtained. Conclusions: This study demonstrated that the preliminary screening system for HBOC using an AI chatbot was feasible for real patients.
28 August 2025 in Annals of Surgical Oncology
2 June 2026 in Thoracic Cancer
Background: For advanced non‐small cell lung cancer (NSCLC), biomarker testing using multiplex companion diagnostics has become the standard of care. However, challenges remain in detecting rare mutations and resistance mechanisms after targeted therapy. We evaluated the prevalence of druggable genetic aberrations and the clinical utility of comprehensive genomic profiling (CGP) performed after completion of standard treatment in real‐world practice. Methods: This retrospective study analyzed 108 patients with advanced or recurrent non‐small cell lung cancer who underwent comprehensive genomic profiling testing between January 2019 and December 2023 at the Kanagawa Cancer Center Hospital, Japan. Profiling was conducted using the OncoGuide NCC Oncopanel System, FoundationOne, and FoundationOne Liquid companion diagnostics. Results: Druggable genetic aberrations were detected in 37% of the patients, with epidermal growth factor receptor mutations being the most common. Resistance mechanisms were identified in 9 of 19 patients who underwent re‐biopsy after targeted therapy. Non‐smokers had a significantly higher rate of druggable mutations (55.6%) than did smokers (27.8%). Treatment based on comprehensive genomic profiling findings was recommended for 35.2% of the patients; however, only 16.6% received the suggested therapy. In a landmark survival analysis, patients who received genomically matched therapy demonstrated a trend toward prolonged overall survival compared with those who did not (log‐rank p = 0.054). Conclusions: CGP testing can identify actionable mutations missed by conventional diagnostics and may provide additional therapeutic opportunities in NSCLC.
31 August 2026 in Clinical Case Reports
This case highlights the importance of genetic evaluation during treatment in young patients with advanced ovarian cancer. Lynch syndrome caused by a germline MSH6 pathogenic variant was diagnosed during first‐line maintenance therapy, and pembrolizumab achieved a durable response in recurrent disease.
26 June 2026 in Cancer Science
Loss of SMARCB1/INI1 expression is a common feature of various types of tumors including malignant rhabdoid tumor, an aggressive cancer of children. Because SMARCB1/INI1 deficiency leads to genome‐wide transcriptional dysregulation, identifying a specific therapeutic target that acts on a wide range of SMARCB1/INI1‐deficient tumors has been challenging. This study aimed to establish if the personalized selection of effective drugs against SMARCB1/INI‐deficient tumors is possible by in vitro drug sensitivity profiling. The in vitro drug sensitivity profiles of tumors from SMARCB1/INI1‐deficient tumor cell line–derived mouse xenograft (CDX) models were evaluated by a short‐term collagen gel–embedded three‐dimensional culture–drug sensitivity test (3D‐DST). With the 3D‐DST, molecular targeting drugs, including inhibitors of aurora B kinase, mammalian target of rapamycin, mitogen‐activated protein kinase, WNT/β‐catenin, or mouse double minute 2 homolog (MDM2), were selected as therapeutic drug candidates in SMARCB1/INI1‐deficient tumors. A CDX tumor, which was resistant to MDM2 inhibitors in the 3D‐DST, expressed lower TP53 compared to an MDM2 inhibitor–sensitive tumor. In cultured cell lines, exposure to MI‐773, a MDM2 inhibitor, disturbed the expression of a significant number of genes and induced p21 protein expression in MDM2 inhibitor–sensitive cells. However, such changes were not observed in resistant cells. These results suggest that 3D‐DST can predict biologically relevant drug sensitivity profiles in SMARCB1/INI1‐deficient tumors.