Citations

Artificial intelligence (AI) is not merely a tool for the future of clinical medicine; it is already reshaping the landscape, challenging traditional paradigms, and expanding the horizons of what is achievable in healthcare [...]

Artificial Intelligence (AI) has the potential to revolutionize cytopathology by enhancing diagnostic accuracy, efficiency, and accessibility. However, the implementation of AI in this field presents significant challenges and opportunities. This review paper explores the current landscape of AI applications in cytopathology, highlighting the critical challenges, including data quality and availability, algorithm development, integration and standardization, and clinical validation. We discuss challenges such as the limitation of only one optical section and z-stack scanning, the complexities associated with acquiring high-quality labeled data, the intricacies of developing robust and generalizable AI models, and the difficulties in integrating AI tools into existing laboratory workflows. The review also identifies substantial opportunities that AI brings to cytopathology. These include the potential for improved diagnostic accuracy through enhanced detection capabilities and consistent, reproducible results, which can reduce observer variability. AI-driven automation of routine tasks can significantly increase efficiency, allowing cytopathologists to focus on more complex analyses. Furthermore, AI can serve as a valuable educational tool, augmenting the training of cytopathologists and facilitating global health initiatives by making high-quality diagnostics accessible in resource-limited settings. The review underscores the importance of addressing these challenges to harness the full potential of AI in cytopathology, ultimately improving patient care and outcomes.

Context.— A monthly pathology journal club has met for 24 years. It was established to help members stay apprised of the literature relevant to diagnostic pulmonary pathology. Objective.— To assess whether the journal club met its goal and to report on opportunities identified for improvement. Design.— To determine whether articles chosen for discussion as opposed to notation were more significant, Scopus citation indices for article types reviewed from January 2007 to November 2023 were compared. A survey of current faculty was undertaken to determine if the club was meeting expectations and to identify improvement opportunities. Results.— Articles from January 2007 to November 2023 included 858 discussed and 3385 noted. Mean (SD) citation count was 103.0 (409.80) for discussion and 64.9 (259.77) for notation articles ( P < .001). The citation count was noticeably right skewed, as articles with high citation counts inflated the mean. Members were mostly satisfied with the way the journal club was structured and managed. Members most valued the summary of the articles, followed by the live discussion. Opportunities for improvement included decreasing the number of journals scanned, decreasing detail in summaries, and using generative artificial intelligence (AI) to facilitate summary generation. A pilot using AI anecdotally reduced preparatory time, but the human-edited summary included more specific context, critical commentary, and enhanced take-home messages, providing a more nuanced analysis. Conclusions.— The journal club met its initial goal. Opportunities for improvement have been identified including the use of generative AI to facilitate article summarization.

Significant progress has been made in treating Coronavirus disease (COVID) – an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). An ominous turn in the pandemic is the evolving public health crisis emanating from persistent SARS-CoV-2 infection and its associated long-term impact. Long COVID or post–COVID syndrome describes protean symptoms that persist at least 3 months after the onset of acute illness and last for at least 2 months in individuals with a history of confirmed SARS-CoV-2 infection. Long COVID has become a public health concern. Millions of infected individuals are now facing chronic multi-organ failures, including neuropsychiatric, cardiovascular, pulmonary, and kidney complications. In general, the cause of long COVID syndrome is unclear but factors such as prolonged activation of immune responses, and viral persistence triggering transcription dysregulation of genes associated with normal thrombotic disease may play a role in cardiovascular complications. Although inflammatory biomarkers are reported in other disorders, it remains unclear whether similar biomarkers are associated with cardiovascular manifestations following COVID. Medications such as sulodexide directed at glycocalyx and coagulation have demonstrated benefits for long COVID in smaller studies. Here, we describe the outcomes of the symposium on the underlying cardiovascular mechanisms of the long COVID.

Abstract Introduction Despite the widespread use of telemedicine to assess patients with intestinal failure (IF) receiving home parenteral nutrition (HPN), satisfaction with remote consultation methods has not been comprehensively assessed. Here, we assessed patient and clinician attitudes to telephone and video IF consultations. Methods Telemedicine questionnaires were designed and distributed in paper form to patients with IF receiving HPN under the care of a UK national IF reference center and electronically to IF clinicians in Europe, North America, Australia, and New Zealand. Results Seventy‐eight patients (53 women and 25 men) and 110 clinicians agreed to complete the questionnaires. Sixty seven percent of patients who had telephone consultations and 50% of patients who had video consultations were satisfied with their consultations. Forty nine percent and 83% of patients who had telephone and video consultations, respectively, felt they were of the same standard as their face‐to‐face consultations. Despite 60% of clinicians feeling telemedicine training would be useful, 55% of clinicians stated they mostly or always met all of the needs of their patients via telephone consultations, whereas 96% of clinicians felt similarly for video consultations ( P = 0.002). A total of 33% and 57% of clinicians felt telephone and video consultations, respectively, were of the same standard as face‐to‐face consultations ( P = 0.004). Conclusion This study comprehensively assesses attitudes to IF telemedicine consultations. Our data show that a large proportion of patients and clinicians are satisfied with IF telephone and video consultations. However, there is an unmet need amongst clinicians for telemedicine training.

Abstract Although most cases of endogenous Cushing syndrome are caused by a pituitary adenoma (Cushing disease), approximately one-third of patients present with ectopic or adrenal causes. Surgery is the first-line treatment for most patients with Cushing syndrome; however, medical therapy is an important management option for those who are not eligible for, refuse, or do not respond to surgery. Clinical experience demonstrating that osilodrostat, an oral 11β-hydroxylase inhibitor, is effective and well tolerated comes predominantly from phase III trials in patients with Cushing disease. Nonetheless, reports of its use in patients with ectopic or adrenal Cushing syndrome are increasing. These data highlight the importance of selecting the most appropriate starting dose and titration frequency while monitoring for adverse events, including those related to hypocortisolism and prolongation of the QT interval, to optimize treatment outcomes. Here we use illustrative case studies to discuss practical considerations for the management of patients with ectopic or adrenal Cushing syndrome and review published data on the use of osilodrostat in these patients. The case studies show that to achieve the goal of reducing cortisol levels in all etiologies of Cushing syndrome, management should be individualized according to each patient’s disease severity, comorbidities, performance status, and response to treatment. This approach to osilodrostat treatment maximizes the benefits of effective cortisol control, leads to improvements in comorbid conditions, and may ameliorate quality of life for patients across all types and severities of Cushing syndrome.

ZUMA-12 is a multicenter phase 2 study evaluating axicabtagene ciloleucel (axi-cel) autologous anti-CD19 chimeric antigen receptor (CAR) T-cell therapy as part of first-line treatment for high-risk large B-cell lymphoma (LBCL). In the primary efficacy analysis (n = 37; median follow-up, 15.9 months), axi-cel demonstrated a high rate of complete responses (CR; 78%) and a safety profile consistent with prior experience. Here, we assessed updated outcomes from ZUMA-12 in 40 treated patients after ≥3 years of follow-up. Eligible adults underwent leukapheresis, lymphodepleting chemotherapy, and axi-cel infusion (2 × 106 CAR T cells/kg). Investigator-assessed CR, objective response, survival, safety, and CAR T-cell expansion were assessed. The CR rate among response-evaluable patients (n = 37) increased after the primary analysis to 86% (95% confidence interval [CI], 71%-95%), with a 92% objective response rate. After a median follow-up of 47.0 months (range, 37.1-57.8 months), 36-month estimates (95% CI) of duration of response and event-free, progression-free, and overall survival were 81.8% (63.9%-91.4%), 73.0% (55.6%-84.4%), 75.1% (57.5%-86.2%), and 81.1% (64.4%-90.5%), respectively. In total, 4 patients had new malignancies, 2 occurring after the data cutoff of the primary analysis; none were axi-cel–related. Eight patients died on study, 2 of whom died from nonrelapse mortality causes. After long-term follow-up, axi-cel demonstrated a high durable response rate, with no new safety signals after the primary analysis, suggestive of an effective first-line therapy with curative intent in high-risk LBCL. Further assessments are needed to determine its benefit vs standard of care. This trial was registered at clinicaltrials.gov, as NCT03761056.

The NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines) for Pediatric Acute Lymphoblastic Leukemia (ALL) were developed as a result of meetings convened by a multidisciplinary panel of pediatric ALL experts, with the goal of providing recommendations on standard treatment approaches based on current evidence. The NCCN Guidelines for pediatric ALL focus on risk assessment and stratification of risk-adapted therapy; treatment strategies for BCR::ABL1 (Philadelphia chromosome [Ph])-negative and BCR::ABL1-positive B-cell lineage, T-cell lineage, and infant ALL; and supportive care considerations. This selection from the NCCN Guidelines for pediatric ALL focuses on the diagnosis of and management of pediatric T-ALL.

This Viewpoint advocates for prompt aortic valve replacement (rather than clinical surveillance) as the default strategy for patients with asymptomatic severe aortic stenosis.

PURPOSE Newly approved drugs and combinations treating multiple myeloma (MM) have resulted in substantial improvements in patients' survival. To deliver rapid access to newer therapies, an earlier end point to expedite clinical trials is needed. Our objective was to evaluate the minimal residual disease–negative complete response (MRD-CR) as an intermediate end point for progression-free survival (PFS) and overall survival (OS) in newly diagnosed (ND) transplant-eligible (NDTE) patients, ND transplant-ineligible (NDTinE) patients, and patients with relapsed/refractory (RR) MM. PATIENTS AND METHODS Individual patient data from 20 randomized multicenter trials were collected. Eleven studies (4,773 patients) with sufficient data were analyzed to evaluate whether 9- or 12-month MRD-CR classified at a 10 –5 threshold could be reasonably likely to predict the clinical benefit of new agents regarding PFS and OS. Global odds ratio (OR) was estimated using the bivariate Plackett Copula model. Supportive evaluation included correlations of the treatment effects on MRD-CR end points and PFS/OS, evaluated by both linear regression ( R 2 weighted least squared ) and Copula ( R 2 Copula ) models. RESULTS The analysis demonstrated that both 9- and 12-month MRD-CR strongly correlated with PFS at patient level in NDTE patients, NDTinE patients, and patients with RRMM. Global ORs ranged from 3.06 to 16.24, all with 95% CIs excluding 1.0. Encouraging trial-level correlations ( R 2 , 0.61-0.70) were observed by pooling three populations and were stronger ( R 2 , 0.67-0.78) in the ND population. Similar results were observed for OS. CONCLUSION Our findings provided the support for use of MRD-CR classified at a 10 –5 threshold at either 9 or 12 months after starting of the treatment, as an intermediate end point to support accelerated approvals, in future trials in NDTE patients, NDTinE patients, and patients with RRMM.