Improving prediction of cervical cancer using KNN imputer and multi-model ensemble learning

by Turki Aljrees

Cervical cancer is a leading cause of women’s mortality, emphasizing the need for early diagnosis and effective treatment. In line with the imperative of early intervention, the automated identification of cervical cancer has emerged as a promising avenue, leveraging machine learning techniques to enhance both the speed and accuracy of diagnosis. However, an inherent challenge in the development of these automated systems is the presence of missing values in the datasets commonly used for cervical cancer detection. Missing data can significantly impact the performance of machine learning models, potentially leading to inaccurate or unreliable results. This study addresses a critical challenge in automated cervical cancer identification—handling missing data in datasets. The study present a novel approach that combines three machine learning models into a stacked ensemble voting classifier, complemented by the use of a KNN Imputer to manage missing values. The proposed model achieves remarkable results with an accuracy of 0.9941, precision of 0.98, recall of 0.96, and an F1 score of 0.97. This study examines three distinct scenarios: one involving the deletion of missing values, another utilizing KNN imputation, and a third employing PCA for imputing missing values. This research has significant implications for the medical field, offering medical experts a powerful tool for more accurate cervical cancer therapy and enhancing the overall effectiveness of testing procedures. By addressing missing data challenges and achieving high accuracy, this work represents a valuable contribution to cervical cancer detection, ultimately aiming to reduce the impact of this disease on women’s health and healthcare systems.

Access to therapy for child sexual abuse survivors: Preliminary dialogue of barriers and facilitators between caregivers

by Jonathan Jin, Huda Al-Shamali, Lorraine Smith-MacDonald, Matthew Reeson, Wanda Polzin, Yifeng Wei, Hannah Pazderka, Peter H. Silverstone, Andrew J. Greenshaw

Background

Difficulties in access to therapy were highlighted by COVID-19 measures restricting in-person gatherings. Additional challenges arise when focusing on caregivers of child sexual abuse (CSA) survivors in particular, which are a population that has been historically difficult to engage with due to issues of stigma and confidentiality.

Objectives

To present preliminary qualitative results from caregivers of CSA survivors.

Methods

This study was conducted with caregivers of CSA survivors. Two hybrid webinar/focus groups were conducted using a video conferencing platform in fall of 2021 with two groups of stakeholders (11 caregivers and 5 moderators/clinical staff at Little Warriors, an intensive episodic treatment facility). Sessions were recorded, transcribed, and thematically-analyzed using standard qualitative methodology.

Results

A total of 11 caregivers contributed to the data. Themes include: (1) Challenges of starting and maintaining treatment (i.e., emotional impact of intake day, challenges of enrolling), (2) Therapeutic benefits of specialized treatment (i.e., feeling safe and supported and the importance of trauma-informed care), and (3) Barriers and facilitators of treatment (i.e., avenues to scale-up and self-care).

Conclusion

The importance of a strong therapeutic alliance was highlighted by both caregivers/clinical staff and further support is needed for families post-treatment. The present hybrid webinar/focus group also achieved engagement goals in a population that is typically difficult to reach. Overall, the response rate (12%) was equivalent to reported registrant attendance rates for general business to consumer webinars and the recommended focus group size. This preliminary approach warrants replication in other populations outside our clinical context.