ISSN: 1935-1232 (P)

ISSN: 1941-2010 (E)



AI-Enabled Study of Funding Cuts in the UK: Exploring Regional Mental Health Disparities through Machine Learning
Author(s): Md Abu Sufian, Jayasree Varadarajan, Md Sipon Miah and Mingbo Niu*

Background: The UK’s mental health services are grappling with significant challenges due to extensive funding cuts, resulting in elongated waiting times, a dearth of professionals and heightened stigma surrounding mental health.

Objective: This research sets out to decipher the ramifications of these funding cuts on regional disparities in mental health services in the UK by harnessing Artificial Intelligence (AI) and Machine Learning (ML) methodologies, specifically Support Vector Machines (SVM) and ridge regression.

Methods: In our approach, we constructed Support Vector Regression (SVR) and ridge regression models to predict patient outcomes, which stand as indicators of service quality. Alongside, sentiment analysis was employed on patient feedback to elucidate evolving perceptions of mental health services over temporal and regional spectra.

Findings: Our analysis unveiled that while the SVR model demonstrated accuracy constraints, the ridge regression model adeptly elucidated approximately 57.6% of the variance in patient outcomes. The sentiment assessment pinpointed the South region amassing the peak sentiment score of (84.36%), an emblem of overwhelmingly positive sentiments regarding mental health services. A nuanced positive correlation materialized between funding levels and sentiment-driven patient outcomes. Moreover, a pronounced nexus surfaced between funding and staffing levels, with profound implications for patient outcomes.

Significance: These revelations accentuate glaring regional disparities, ushering in a clarion call for harmonized resource distribution and tenable funding stratagems in the mental health domain. By weaving in sentiment analysis with AI and ML paradigms, we dive deeper into the quagmire of patient sentiments, amplifying our prognostic prowess concerning funding trajectories and service quality.

Conclusion: At the heart of this inquiry lies an emphatic appeal for sustainable funding blueprints and the untapped potential of AI and ML to unravel the intricate interplay between funding truncations, staffing paradigms and sentiment-informed patient outcomes within the UK’s mental health tapestry.