MMMegan McNichol

Megan McNichol

*This is an algorithmically generated author record based on publicly available information.

Megan McNichol has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Non clinic-Based Interventions to Mitigate Post-Intensive Care Syndrome: A Scoping Review

    by Yasmeen Abu Fraiha, James Devanney, Megan McNichol, Thomas Cummiskey, Abirami Kumaresan, Somnath Bose

    OBJECTIVES: Survivors of critical illness and their caregivers often experience a complex constellation of sequelae in the aftermath of their recovery, termed post-intensive care syndrome (PICS) and PICS-Family (PICS-F), respectively. These can have a dire impact on patients and families, and thus require coordinated rehabilitative efforts. However, optimal modes of providing support services remain unclear, with traditional clinic-based strategies showing mixed results. This scoping review aimed to summarize the feasibility and effectiveness of nonclinic-based follow-up and rehabilitation strategies for adult survivors of critical illness and their caregivers. DATA SOURCES: Databases were searched on July 8, 2025, and included Cochrane, Embase, PubMed, and Web of Science. STUDY SELECTION: Studies reporting interventions and follow-up options for adult survivors of critical illness requiring ICU stay and targeting PICS and PICS-F were included. Studies examining interventions in the outpatient clinic or ICU settings exclusively were excluded. DATA EXTRACTION: Two team members used Covidence to screen all the deduplicated citations, with a third team member acting as a tiebreaker. The studies included were reviewed in full to extract general data, the studied syndrome (PICS, PICS-F, or both), component of PICS studied, study population, study objectives, methods, inclusion and exclusion criteria, intervention details, general results, and study conclusions. DATA SYNTHESIS: We screened 8608 studies; 45 studies met criteria and were included in this review. Most (64%) focused on the physical and psychological sequelae of PICS. Interventions varied widely, by setting, duration, and approach. Outcome measures were heterogeneous, limiting comparisons. Most studies evaluated the feasibility of interventions and not effectiveness. Only six articles targeted PICS-F exclusively. CONCLUSIONS: This scoping review summarizes the status of different nonclinic-based follow-up and rehabilitation strategies for adult ICU survivors. Future research focused on studies that evaluate effectiveness of these strategies in mitigating the burden of PICS and PICS-F, especially within the cognitive domain, is likely to improve aftercare for both patients and their families.

  • Detecting and Mitigating the Clever Hans Effect in Medical Imaging: A Scoping Review

    by Constanza Vásquez-Venegas, Chenwei Wu, Saketh Sundar, Renata Prôa, Francis Joshua Beloy, Jillian Reeze Medina, Megan McNichol, Krishnaveni Parvataneni, Nicholas Kurtzman, Felipe Mirshawka, et al.

    The Clever Hans effect occurs when machine learning models rely on spurious correlations instead of clinically relevant features and poses significant challenges to the development of reliable artificial intelligence (AI) systems in medical imaging. This scoping review provides an overview of methods for identifying and addressing the Clever Hans effect in medical imaging AI algorithms. A total of 173 papers published between 2010 and 2024 were reviewed, and 37 articles were selected for detailed analysis, with classification into two categories: detection and mitigation approaches. Detection methods include model-centric, data-centric, and uncertainty and bias-based approaches, while mitigation strategies encompass data manipulation techniques, feature disentanglement and suppression, and domain knowledge-driven approaches. Despite the progress in detecting and mitigating the Clever Hans effect, the majority of current machine learning studies in medical imaging do not report or test for shortcut learning, highlighting the need for more rigorous validation and transparency in AI research. Future research should focus on creating standardized benchmarks, developing automated detection tools, and exploring the integration of detection and mitigation strategies to comprehensively address shortcut learning. Establishing community-driven best practices and leveraging interdisciplinary collaboration will be crucial for ensuring more reliable, generalizable, and equitable AI systems in healthcare.