Roupen Odabashian

Aims: Cardiac implantable electronic device (CIED) infection carries a substantial burden of morbidity, mortality, and cost. The Prevention of Arrhythmia Device Infection Trial (PADIT) risk score improves identification of high-risk patients and may guide targeted strategies to reduce infection. Recent work has categorized CIED infection into localized pocket vs. systemic infection, with early reports suggesting different risk factors for each. However, no current risk score has been validated for infection subtypes. ObjectivesIndependently validate the PADIT infection risk score.Compare risk factors for infection subtypes.Assess PADIT performance in predicting subtype-specific infection. Methods and results: A prospective registry was initiated at the University of Ottawa Heart Institute in 2007 to capture all CIED procedures and prospectively identify infections in collaboration with the infection prevention team. PADIT risk score components were documented for each procedure. All suspected infections were adjudicated independently by two physicians (with a third if required), blinded to PADIT score and baseline variables, and subclassified as pocket or systemic infection. Logistic regression models were generated to validate PADIT performance for each subtype, with evaluation using Akaike and Bayesian information criteria (AIC/BIC), C-statistics, and calibration slope. Between 2007 and 2020, 14,225 procedures were performed (mean age 72 ± 14 years, 35% female, 70% new implants, 18% generator changes, 11% upgrades). A total of 103 infections (0.73%) were adjudicated, of which 71 (69%) were pocket and 32 (31%) systemic. The PADIT score showed good predictive performance with a C-statistic of 0.687 (95% CI 0.655–0.743), similar to the derivation cohort (0.702, 95% CI 0.661–0.741). Notably, the number of prior procedures was strongly associated with pocket infection but not systemic infection. PADIT discrimination was consistent across subtypes: pocket infection C-statistic 0.691 (95% CI 0.649–0.761) and systemic infection 0.746 (95% CI 0.707–0.848). Calibration slopes demonstrated good agreement between predicted and observed events, with the best fit for systemic infection. Conclusion: The PADIT score was independently validated with discrimination and calibration similar to the original derivation cohort. Importantly, prior procedures predicted pocket but not systemic infection. Overall, PADIT performed well in predicting both subtypes, with the strongest model fit observed for systemic infection.

Neuroendocrine tumors (NETs) are heterogeneous neoplasms with different molecular characteristics and prognosis. Although slow-growing, NETs are often diagnosed at an advanced stage. The treatment choice depends on primary site, extent, grade, growth rate, somatostatin receptor status, functional status, performance status, and comorbidities. Precise knowledge of the biological and molecular features of NETs has led to the development of novel therapies. Therapeutic options include somatostatin analogs, multi-targeted tyrosine kinase inhibitors (e.g., sunitinib), or mammalian targets of rapamycin (mTOR) inhibitors (e.g., everolimus), telotristat ethyl, chemotherapy, and peptide-receptor radionuclide therapy. Pivotal studies that led to approval, treatment-related adverse events, and safety concerns, as demonstrated in clinical trials and real-world clinical practice. Questions, such as the optimal timing, selection, and sequence of therapies, and biomarkers that predict response to the novel agents in an individual patient, remain to be answered. We propose a stepwise approach for the management of advanced Gastro-entero-pancreatic (GEP)-NETs that utilizes a multidisciplinary team of experts. Biomarkers may assist in both the diagnosis and post-treatment follow-up in patients with GEP-NETs. The next decade of research on GEP-NETs is promising and should provide new insights into the molecular underpinnings of this disease, therapy selection, and the sequencing of the available therapies, along with the potential role of AL in NET pharmacotherapy.

BACKGROUND The integration of artificial intelligence (AI) in clinical oncology has the potential to enhance decision-making by synthesizing vast, evolving datasets. However, the accuracy and clinical utility of large language models (LLMs) for lung cancer treatment recommendations remain unclear. OBJECTIVE This study aimed to evaluate the potential of large language models (GPT-4O and Claude 3 Opus) as clinical decision support tools in medical oncology by assessing their ability to generate accurate, comprehensive, and clinically appropriate treatment recommendations for real-world lung cancer cases. The objectives included measuring the models’ performance across key domains—such as treatment accuracy, comprehensiveness, insight generation, and safety—and determining their suitability for integration into oncology practice. METHODS We conducted a prospective evaluation of GPT-4O (OpenAI) and Claude 3 Opus (Anthropic) in generating treatment recommendations for 25 real-world lung cancer cases from the Fellows Clinic at Karmanos Cancer Institute in Detroit, MI. AI-generated responses were assessed by thoracic oncologists, blinded to the models, using predefined metrics: accuracy, comprehensiveness of oncologic and supportive treatment plans, novel clinical insight, system hallucination or fabrications, and potential for harmful recommendations. Oncologists also reported their confidence in using LLM-generated responses for decision support. RESULTS GPT-4O demonstrated an accuracy score of 4.2 (95% CI, 3.9–4.4), outperforming Claude Opus, which scored 3.6 (95% CI, 3.1–4.1; p = 0.04). GPT-4O was deemed trustworthy in 16 of 25 cases (64%), compared to 11 of 25 cases (44%) for Claude Opus (p = 0.03). Neither model consistently provided novel insights. Both models generated potentially harmful recommendations (GPT-4O: 24%; Claude Opus: 36%) and demonstrated deficiencies in treatment plan comprehensiveness, including omission of maintenance immunotherapy and failure to integrate patient-specific factors such as molecular testing or their specific co-morbidities. CONCLUSIONS While LLMs exhibit moderate accuracy in lung cancer treatment recommendations, critical limitations in comprehensiveness and potential for harmful outputs preclude their standalone use in clinical practice. Domain-specific refinement and rigorous validation are necessary before LLMs can reliably support oncologic decision-making.

The landscape of available therapeutic options for treatment of genitourinary (GU) cancers is expanding dramatically. Many of these treatments have distinct, sometimes severe, skin toxicities including morbilliform, bullous, pustular, lichenoid, eczematous, psoriasiform, and palmoplantar eruptions. Pruritus and skin pigmentation changes have also been noted. This review aims to synthesize dermatologic events observed with antibody drug conjugates, poly (ADP-ribose) polymerase (PARP) inhibitors, androgen receptor pathway inhibitors, tyrosine kinase inhibitors, immune checkpoint inhibitors, and the combination of these agents used for the treatment of GU cancers. It provides a guide on diagnosis and initial management of these rashes for medical oncologists.

Background: ChatGPT (Open AI) is a state-of-the-art large language model that uses artificial intelligence (AI) to address questions across diverse topics. The American Society of Clinical Oncology Self-Evaluation Program (ASCO-SEP) created a comprehensive educational program to help physicians keep up to date with the many rapid advances in the field. The question bank consists of multiple choice questions addressing the many facets of cancer care, including diagnosis, treatment, and supportive care. As ChatGPT applications rapidly expand, it becomes vital to ascertain if the knowledge of ChatGPT-3.5 matches the established standards that oncologists are recommended to follow. Objective: This study aims to evaluate whether ChatGPT-3.5’s knowledge aligns with the established benchmarks that oncologists are expected to adhere to. This will furnish us with a deeper understanding of the potential applications of this tool as a support for clinical decision-making. Methods: We conducted a systematic assessment of the performance of ChatGPT-3.5 on the ASCO-SEP, the leading educational and assessment tool for medical oncologists in training and practice. Over 1000 multiple choice questions covering the spectrum of cancer care were extracted. Questions were categorized by cancer type or discipline, with subcategorization as treatment, diagnosis, or other. Answers were scored as correct if ChatGPT-3.5 selected the answer as defined by ASCO-SEP. Results: Overall, ChatGPT-3.5 achieved a score of 56.1% (583/1040) for the correct answers provided. The program demonstrated varying levels of accuracy across cancer types or disciplines. The highest accuracy was observed in questions related to developmental therapeutics (8/10; 80% correct), while the lowest accuracy was observed in questions related to gastrointestinal cancer (102/209; 48.8% correct). There was no significant difference in the program’s performance across the predefined subcategories of diagnosis, treatment, and other (P=.16, which is greater than .05). Conclusions: This study evaluated ChatGPT-3.5’s oncology knowledge using the ASCO-SEP, aiming to address uncertainties regarding AI tools like ChatGPT in clinical decision-making. Our findings suggest that while ChatGPT-3.5 offers a hopeful outlook for AI in oncology, its present performance in ASCO-SEP tests necessitates further refinement to reach the requisite competency levels. Future assessments could explore ChatGPT’s clinical decision support capabilities with real-world clinical scenarios, its ease of integration into medical workflows, and its potential to foster interdisciplinary collaboration and patient engagement in health care settings.

BACKGROUND Importance: ChatGPT is a state-of-the-art large language model that uses artificial intelligence (AI) to address questions across diverse topics. The American Society of Clinical Oncology Self-Evaluation (ASCO-SEP) program created a comprehensive educational program to help physicians keep up-to-date with the many rapid advances in the field. The question bank consists of multiple-choice questions (MCQs) addressing the many facets of cancer care, including diagnosis, treatment, and supportive care. OBJECTIVE As ChatGPT applications rapidly expand, we sought to investigate its performance in the field of medical oncology by using questions from ASCO-SEP. METHODS We conducted a systematic assessment of the performance of ChatGPT-3 on the American Society of Clinical Oncology Self-Evaluation Program (ASCO-SEP), the leading educational and assessment tool for medical oncologists in training and practice. Over 1000 multiple choice questions covering the spectrum of cancer care where extracted. Questions were categorized by cancer type/discipline, with sub-categorization as treatment, diagnosis or other. Answers were scored as correct if ChatGPT selected the answer as defined by ASCO-SEP. RESULTS Overall, ChatGPT achieved a score of 56% for correct answers provided (583/1040). The program demonstrated varying levels of accuracy across cancer types/disciplines. The highest accuracy was observed in questions related to developmental therapeutics (8/10; 80% correct), while the lowest accuracy was observed in questions related to gastrointestinal cancer (102/209; 49% correct). There was no significant difference in the program’s performance across the pre-defined sub-categories of diagnosis, treatment and other (p value = .16 > 0.05). CONCLUSIONS Although below the required passing rate, ChatGPT’s performance on the ASCO-SEP showed promise for future applications in cancer care and medical education. Current limitations of the technology include training data that does not extend beyond 2021, and the inability to process or interpret data tables or images. However, as the technology continues to evolve, it is expected that these limitations will be overcome, allowing for improved capabilities. CLINICALTRIAL Non applicable