BACKGROUND:Genomic assays such as Oncotype DX have transformed adjuvant treatment selection for hormone receptor-positive, HER2-negative, early breast cancer but remain inaccessible to many patients because of high cost and logistical barriers. We aimed to develop and validate an artificial intelligence (AI) model that estimates Oncotype DX 21-gene recurrence scores directly from routine histopathology slides and clinicopathological variables. METHODS:In this multicentre, model development and validation study, a multimodal deep-learning model was trained on digital whole-slide images and clinical features using a foundation model pre-trained on 171 189 histopathology slides for predicting Oncotype DX recurrence score. We included slides from patients with hormone receptor-positive, HER2-negative, invasive breast cancers and without scanning artifacts and with at least 100 tissue tiles (1·6 mm2). The model was fine-tuned and validated on the TAILORx randomised trial (8284 patients after quality control). Prognostic and predictive performance was assessed in the TAILORx-test set and externally validated in six independent cohorts (Carmel, Haemek, and Sheba medical centres [Israel], the University of Chicago Medical Center [USA], the Australian Breast Cancer Tissue Bank [Australia], and the Cancer Genome Atlas Breast Invasive Carcinoma project [USA]). FINDINGS:In the TAILORx-test set (n=2407), the AI model classified 1097 (45·6%) patients as low risk, 1021 (42·4%) as intermediate risk, and 289 (12·0%) as high risk. For identifying high genomic-risk disease (recurrence score ≥26), the area under the curve (AUC) was 0·898 (95% CI 0·879-0·913). AI-based risk stratification was prognostic for recurrence-free interval (hazard ratio 2·61 [95% CI 1·68-4·04]), distant recurrence-free interval (2·88 [1·73-4·79]), and disease-free survival (1·32 [0·92-1·89]). Chemotherapy benefit was evident in premenopausal patients classified by AI as being at high risk (0·63 [0·46-0·86]) but absent in postmenopausal patients classified by AI as being at low risk (0·94 [0·78-1·12]). 151 (31·3%) clinically high-risk postmenopausal women (by MINDACT criteria) were reclassified as low AI risk with no chemotherapy benefit. Analysis on external cohorts (5497 patients) showed that the model is transferable to new data with high generalisability (recurrence score ≥26 AUC ranging from 0·858 to 0·903). INTERPRETATION:These findings show that AI applied to routine histopathology can serve as a practical and scalable tool for guiding chemotherapy decisions in hormone receptor-positive, HER2-negative, early breast cancer. This approach has the potential to reduce unnecessary chemotherapy and broaden access to precision oncology, particularly in resource-limited settings where genomic testing remains unavailable or unaffordable. FUNDING:Israel Innovation Authority (Kamin), Zimin Institute for Artificial Intelligence Solutions in Healthcare, Israel Precision Medicine Partnership program, and Israel Cancer Research Fund.
OBJECTIVES:Eosinophilic bronchiectasis is defined by a blood eosinophil count (BEC) ≥300 cells/µL, but blood eosinophils imperfectly reflect airway eosinophilic inflammation. Here, we investigated the relationship between eosinophilic airway inflammation, blood eosinophils and clinical severity in bronchiectasis and explored the phenotype associated with eosinophilic bronchiectasis. METHODS:Sputum from 180 patients with stable CT-confirmed bronchiectasis was utilised to investigate airway levels of eosinophil proteins (eosinophil peroxidase (EPX), eosinophil derived-neurotoxin (EDN), eosinophil cationic protein (ECP), major basic protein (MBP) and Galectin-10 (Gal-10)) using a novel stable isotope dilution liquid chromatography-tandem mass spectrometry (LC-MS/MS) assay. To profile eosinophilic bronchiectasis, a nested analysis of patients with BEC <150 cells/µL (n=52) and ≥300 cells/µL (n=49) was conducted. RESULTS:Sputum concentrations of Gal-10, ECP and EDN were weakly but significantly associated with radiological severity, FEV1 and sputum culture positivity for Pseudomonas aeruginosa. Airway eosinophil protein concentrations did not associate with exacerbation frequency. Total eosinophil protein concentration moderately correlated with BECs (r=0.33 95% CI 0.14 to 0.49, p=0.0007). Nested analysis revealed increased sputum PCR-positivity for P. aeruginosa (26.7% vs 7.7%, p=0.033) and an increased frequency of patients showing signs of Aspergillus sensitisation (defined as Aspergillus-specific IgE titres >0.35 kUA/L, 24.5% vs 3.8%) in eosinophilic bronchiectasis. Sputum inflammatory biomarkers and clinical parameters did not differ between groups. CONCLUSIONS:LC-MS/MS can detect eosinophilic inflammation within bronchiectasis sputum. Weak associations between elevated airway eosinophil proteins, bronchiectasis severity and P. aeruginosa infection were observed. Direct measurement of eosinophilic airway inflammation provides additional information in addition to BECs. Eosinophilic bronchiectasis associated with P. aeruginosa infection and Aspergillus sensitisation.
Integrative complementary medicine (ICM) combines complementary therapies with conventional supportive and palliative care to address quality of life (QoL). Diabetes mellitus (DM) is prevalent among patients with cancer and has been associated with worse health-related QoL. We examined the impact of an ICM program on QoL-related concerns among patients being treated for cancer, with vs. without DM. This prospective, controlled and pragmatic study examined a 6-week ICM program, comparing DM to non-DM patients using the ESAS (Edmonton Symptom Assessment Scale) and EORTC QLQ-C30 (European Organization for Research and Treatment of Cancer Quality of Life Questionnaire) tools. The threshold for statistical significance was established at a P-value of less than 0.05. Of 671 patients, 135 (20
BACKGROUND:PFAPA (periodic fever, aphthous stomatitis, pharyngitis, adenitis) syndrome is the most common periodic fever disorder in children, causing recurrent debilitating episodes that impose a substantial burden on children and their families. Current therapeutic approaches primarily rely on corticosteroid administration, which provides rapid symptom resolution but fails to address the underlying inflammatory cascade, prevent future attacks, and carries the risk of side effects. OBJECTIVES:To determine the therapeutic efficacy of colchicine prophylaxis in reducing attack frequency and extending disease-free intervals in PFAPA patients, compared to standard of care management alone. METHODS:This retrospective cohort study included 55 pediatric PFAPA patients, 15 receiving colchicine prophylaxis, and 40 controls managed with standard care alone. The primary outcome was the change in inter-attack interval duration from baseline study completion. Secondary analyses examined treatment response by FMF genetic status and survival analysis for time to next attack. RESULTS:Both groups showed comparable baseline characteristics, except higher FMF mutation prevalence in the colchicine group (73.3% vs. 27.5%, P = 0.002). Patients receiving colchicine experienced a dramatic improvement in inter-attack intervals (median change: 60 days, IQR: 51) compared with controls (median change: 0 days, IQR: 0; P < 0.001). Colchicine's therapeutic benefit was consistent regardless of FMF genetic status. CONCLUSIONS:Colchicine prophylaxis significantly reduces PFAPA attack frequency, with therapeutic benefits that are independent of FMF genetic status. These findings support colchicine as an effective first-line prophylactic treatment for PFAPA patients with frequent episodes or families concerned about frequent steroid use, representing a paradigm shift from reactive to preventive management.
