This study aimed to investigate the feasibility and potential value of predictive models for human epidermal growth factor receptor 2 (HER2)-positive status in breast cancer (BC) based on radiomics features from conventional ultrasound images and machine learning models.

Ultrasound images of 437 patients with surgically and pathologically confirmed BC were retrospectively analyzed, including 144 HER2-positive and 293 HER2-negative cases, which were used as a training and validation dataset. Key features highly correlated with HER2-positive status were identified and selected using the least absolute shrinkage and selection operator (LASSO), t-test, and principal component analysis (PCA). After the selection of relevant features, the dataset was randomly split into five equal parts for five-fold cross-validation to identify the optimal machine learning method and hyperparameters. A predictive model was then developed based on ultrasound imaging and radiomics features. After feature selection and model development, an additional cohort of 88 patients from other hospitals was utilized as an external validation dataset. The model's internal validation performance was assessed through receiver operating characteristic (ROC) curve analysis, and metrics including area under the curve (AUC), sensitivity, and specificity were calculated. The generalizability of the model was further evaluated using the external validation.

Five radiomics features were found to correlate with HER2-positive status in BC and used for model construction. Among the machine learning models generated, the best predictive model achieved area under the ROC curve values of 0.893 (95% confidence interval [CI], 0.860-0.920) in the training and validation dataset and 0.854 (95% CI, 0.775-0.927) in the external validation dataset.

Machine learning models based on ultrasound radiomics features have potential clinical value for predicting HER2-positive status in BC.

We aimed to identify the unmet health care needs of and proposed potential solutions for patients with thyroid diseases, including those with thyroid cancer, among the Bangladeshi population. We performed a qualitative study using structured interviews with healthcare professionals involved in care management and surgery for thyroid diseases. The interviews were conducted in four hospitals across three large cities in Bangladesh, with participants gathered through convenience sampling. Key findings were categorised and summarised into themes by topic, such as challenges, barriers, unmet needs, and solutions. The most common triggers for visiting the hospital were thyroid (neck) swelling and palpitations. All facilities mentioned thyroid patients' delayed arrival at the hospital and delayed diagnosis as problems, while incomplete treatment, incomplete follow-up, and inadequate specialised medical care emerged as challenges among thyroid cancer patients, specifically. Solutions to each issue and unmet need among thyroid patients focussed on improving awareness of thyroid disease, with raising awareness being the most important solution.

Autologous stem cell transplantation (ASCT) requires efficient collection of peripheral blood stem cells. At London Health Sciences Centre (LHSC), high-risk multiple myeloma patients are routinely booked for three-day apheresis collections to meet higher CD34+ cell count targets, though many do not require all scheduled days, leading to resource inefficiencies. A quality improvement initiative was implemented to reduce unnecessary apheresis sessions through two interventions: (1) lowering CD34+ cell count target thresholds (from 6 × 10⁶ to 5 × 10⁶ cells/kg for tandem collections and from 3 × 10⁶ to 2.5 × 10⁶ for single collections), and (2) increasing total blood volume (TBV) processed from 3× to 4× for patients within certain target thresholds. Two Plan-Do-Study-Act (PDSA) cycles were conducted between March 2024 and March 2025 involving 76 patients. Outcome measures included collection days saved and cost savings, and post-transplant engraftment times served as a balancing measure. A total of 39.4% of patients avoided at least one collection day due to these interventions. Third-day collection usage in high-risk myeloma patients decreased from 25% to 5.9%. Mean collection days fell significantly in this group (2.21-1.8; p = 0.0015), with total cost savings of CAD $72 734.97. No significant differences were observed in neutrophil or platelet engraftment times, confirming preserved clinical efficacy. Implementing lower CD34+ cell count targets and increased TBV processing significantly reduced apheresis sessions and costs without compromising engraftment outcomes. These changes have become the standard of care at LHSC and may serve as a feasible model for other transplant centers.

Mainstream genetic testing (MGT) refers to genetic testing conducted at the time of a cancer diagnosis without undergoing comprehensive genetic counseling. MGT has been the standard of care for patients with breast or ovarian cancer in Norway for several years. The aim of this study is to explore how newly diagnosed patients with breast or ovarian cancer and healthcare professionals' (HCPs), experience the use of the Rosa chatbot in mainstream genetic testing (MGT) and explore potential barriers to the implementation of chatbots in MGT. We conducted a qualitative study using semi-structured interview guides with selected patients and HCPs. The interviews were done either: in-person, over the digital platform Teams, or over the telephone, depending on the participants' wishes. We chose the Stepwise-Deductive Inductive approach for analyzing the transcripts. Both patients and HCPs viewed the Rosa chatbot positively, describing it as user-friendly, useful, accessible, safe, professional, and trustworthy. They reported that the volume and complexity of information during MGT could be overwhelming and viewed the chatbot as a trustworthy resource for patients to revisit at their own pace, supporting informed decision-making after a positive genetic test result. However, concerns were raised about potential misunderstandings, the impersonal nature of digital communication, and the risk of reduced patient-provider interaction, which together were perceived as an emotional barrier to integrating chatbots into genetic counseling practice.

Reduced circulating estrogen levels around the time of menopause can induce symptoms that affect health and well-being. Estrogen therapy is the most effective treatment, but may be associated with some adverse health outcomes, including endometrial pathology. This is an update of a review first published in 1999 and last updated in 2012.

• To assess the effects of hormone therapy regimens for protecting postmenopausal women against endometrial hyperplasia and endometrial cancer. • To define the lowest effective dose(s) of progestogen used in combination with estrogen therapy for protecting the endometrium.

We searched for trials in the Cochrane Gynaecology and Fertility Group specialized register, CENTRAL (containing output from two trial registers and CINAHL), MEDLINE, Embase, and PsycINFO to 22 July 2024. We also checked references and contacted study authors to identify additional studies.

Interventions of interest were unopposed estrogen, continuous combined estrogen and progestogen, and sequential combined estrogen and progestogen, administered for at least one year. These interventions could be compared head to head or with placebo. Trials had to report rates of endometrial hyperplasia or endometrial cancer (histologic diagnosis).

Our critical outcomes were endometrial hyperplasia and endometrial cancer at one year and after one year. Our important outcomes were adherence to therapy, requirement for additional interventions, and withdrawal due to adverse events.

We used the original Cochrane risk of bias tool (RoB 1).

Where meta-analysis was possible, we calculated odds ratios (ORs) with 95% confidence intervals (CIs). We used GRADE to assess the certainty of evidence for each outcome.

This update included 72 studies (involving 40,652 women) conducted worldwide. There were 42 multicenter trials.

There were too few studies with events to draw conclusions about endometrial cancer. The results for endometrial hyperplasia are presented below. Unopposed estrogen versus placebo Unopposed estrogen probably increases the risk of endometrial hyperplasia at one year compared with placebo (22-43 events/1000 women versus 5 events/1000 women; OR 5.86, 95% CI 4.09 to 8.40; I² = 0%; 6 RCTs, 2493 women; moderate-certainty-evidence). Unopposed estrogen probably increases the risk of endometrial hyperplasia after one year (40-68 events/1000 women versus 6 events/1000 women; OR 8.97, 95% CI 6.78 to 11.87; I² = 49%; 9 RCTs, 2539 women; moderate-certainty-evidence). Continuous combined estrogen plus progestogen versus placebo Continuous combined therapy may have little to no effect on the risk of endometrial hyperplasia at one year compared with placebo (0-16 events/1000 women versus 5 events/1000 women; OR 0.51, 95% CI 0.08 to 3.38; I² = 48%; 4 RCTs, 3893 women; low-certainty-evidence). We are unsure about the effect of continuous combined therapy after one year (OR 0.25, 95% CI 0.04 to 1.40; I² = 47%; 4 RCTs, 789 women; very low-certainty evidence). Sequential combined estrogen plus progestogen versus placebo Sequential combined therapy may increase the risk of endometrial hyperplasia at one year compared with placebo (6-27 events/1000 women versus 2 events/1000 women; OR 5.53, 95% CI 2.60 to 11.76; I² = 0%; 4 RCTs, 1030 women; low-certainty-evidence). Sequential combined therapy may result in little to no difference in the risk of endometrial hyperplasia after one year (16-97 events/1000 women versus 20 events/1000 women; OR 2.30, 95% CI 0.76 to 6.99; I² = 0%; 3 RCTs, 534 women; low-certainty-evidence). Unopposed estrogen versus continuous combined estrogen plus progestogen Unopposed estrogen probably increases the risk of endometrial hyperplasia at one year compared with continuous combined therapy (46-75 events/1000 women versus 3 events /1000 women; OR 21.90, 95% CI 16.76 to 28.62; I² = 53%; 11 RCTs, 7856 women; moderate-certainty-evidence). Unopposed estrogen probably increases the risk of endometrial hyperplasia after one year compared with continuous combined therapy (33-73 events/1000 women versus 3 events/1000 women; OR 16.78, 95% CI 11.01 to 25.55; I² = 69%; 3 RCTs, 1191 women; moderate-certainty-evidence). Unopposed estrogen versus sequential combined estrogen plus progestogen Unopposed estrogen may increase the risk of endometrial hyperplasia at one year compared with sequential combined therapy (156-301 events/1000 women versus 16 events/1000 women; OR 17.19, 95% CI 11.27 to 26.22; I² = 70%; 5 RCTs, 2354 women; low-certainty-evidence). Unopposed estrogen may increase the risk of endometrial hyperplasia after one year compared with sequential combined treatment (379-612 events/1000 women versus 49 events/1000 women; OR 19.21, 95% CI 11.95 to 30.90; I² = 15%; 2 RCTs, 417 women; low-certainty-evidence). Continuous combined estrogen plus progestogen versus sequential combined estrogen plus progestogen All analyses had insufficient events to draw conclusions. Continuous combined estrogen plus progestogen - dose comparisons We are unsure about the effect of moderate-dose estrogen plus low-dose progestogen compared with moderate-dose estrogen plus moderate-dose progestogen on the risk of endometrial hyperplasia at one year (OR 1.18, 95% CI 0.24 to 5.84; I² = 36%; 2 RCTs, 2363 women; very low-certainty-evidence). The remaining dose comparisons had insufficient events to draw conclusions. Sequential combined estrogen plus progestogen - dose comparisons Moderate-dose estrogen plus low-dose progestogen may result in little to no difference in the risk of endometrial hyperplasia at one year compared with moderate-dose estrogen plus moderate-dose progestogen (3-32 events/1000 women versus 6 events/1000 women; OR 1.66, 95% CI 0.49 to 5.65; I² = 0%; 4 RCTs, 1072 women; low-certainty-evidence). The remaining dose comparisons had insufficient events to draw conclusions.

Unopposed estrogen probably increases the risk of endometrial hyperplasia versus placebo and continuous combined therapy at one year and later. Sequential combined therapy may increase the risk of endometrial hyperplasia at one year versus placebo. The evidence is less certain for continuous versus sequential combined regimens and dose comparisons of continuous and sequential combined regimens. The trials had few events, and long-term follow-up was challenging. For endometrial cancer, events were rare and trials were underpowered to draw meaningful conclusions.

This review had no dedicated funding.

Original review (1999) DOI: 10.1002/14651858.CD000402 Review update (2004) DOI: 10.1002/14651858.CD000402.pub2 Review update (2009) DOI: 10.1002/14651858.CD000402.pub3 Review update (2012) DOI: 10.1002/14651858.CD000402.pub4.

This is a protocol for a Cochrane Review (intervention). The objectives are as follows: To evaluate the benefits and harms of complete mesocolon excision (CME) compared to conventional colectomy in people undergoing surgery for resectable colon cancer, focusing on survival, recurrence, postoperative complications, and quality of life.

Patient outcomes in advanced renal cell carcinoma (RCC) remain poor, with five-year survival rates ranging from ~10% to 30%. Early projections of therapeutic outcomes could optimize precision medicine and accelerate drug development. While machine learning (ML) models integrating tumor growth inhibition (TGI) metrics have improved survival predictions over traditional models, their application in RCC remains unexplored. Herein, we used TGI metrics and baseline data to evaluate parametric (PM) and semi-parametric (SPM) survival models alongside ML approaches for predicting progression-free (PFS) and overall survival (OS) in 1839 RCC patients from four trials (evaluating sunitinib, axitinib, sorafenib, interferon-alpha, and avelumab + axitinib). Data were split into training (70%) and testing (30%), and feature selection was used to determine parsimonious and robust models. Bootstrap resampling (n = 100) was employed for models' validation, and performance was assessed using C-index and Integrated Brier Score. In brief, training data results demonstrated that tree-based ML models (random survival forest (RSF) and XGBoost) outperformed PM and SPM models in predicting PFS (C-index: 0.783-0.785 vs. 0.725-0.738 for PM and SPM; p < 0.05) and OS (C-index: 0.77-0.867 vs. 0.750-0.758 for PM and SPM; p < 0.05), with RSF achieving better prediction of PFS and OS using only 3-5 covariates, compared to 9-35 with other tested methods. Tree-based methods were also superior in the testing data. SHapley Additive exPlanations revealed nonlinear relationships among top predictors, including TGI metrics, underscoring the ability of tree-based methods to capture complex prognostic interactions. Further validation is required to confirm models' generalizability to additional therapies and patients with differing tumor severity.

Reliable labels are essential when training Artificial Intelligence (AI) tools. Whereas some diseases allow biopsy-based labeling, others rely on subjective criteria. For the diagnosis of basal cell carcinoma (BCC), dermatologists detect certain dermoscopic criteria, whose presence (or absence) serves as the basis for determining a diagnosis of BCC. Therefore, an AI tool assisting in BCC diagnosis should provide such criteria to explain its output.

This study analyzes the agreement among four dermatologists in detecting dermoscopic criteria and compares the performance of an AI model trained with labels from a single dermatologist versus a consensus-based standard. A total of1230 dermoscopic images, collected in around 60 primary health centers, sent via teledermatology, and diagnosed by four dermatologists, were used to train an AI tool. They were randomly selected from the teledermatology platform (2019-2021). Subsequently, 204 new images were used to test the AI tool prospectively. A standard reference (SR) was built using Expectation Maximization on the four diagnoses. The performance of the AI tool trained using the reference standard of one dermatologist versus the reference standard statistically inferred from the consensus of four dermatologists was analyzed using McNemar's test and Hamming distance.

Agreement among dermatologists was high for BCC versus non-BCC (Kappa = 0.9079; PPV = 0.9670), but lower for specific criteria. Statistical differences were found in the performance of AI models trained with individual and consensus labels.

Deriving an SR from multiple expert opinions mitigates individual bias and enhances AI interpretability, key for its clinical adoption.

Struma ovarii is a rare monodermal ovarian teratoma predominantly composed of thyroid tissue. It is usually benign, although malignant transformation is occasionally observed. Non-invasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP) is a recently defined non-malignant entity with indolent behavior, and its emergence in struma ovarii is very uncommon. It requires careful histological analysis, and because of the unusual occurrence of this tumor, its management and follow-up remain challenging and debated. We report a case of NIFTP arising in struma ovarii in a 48-year-old patient. To the best of our knowledge, this is the second case report of this nature.