Katherine Parkin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Katherine Parkin has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Anna Moore
Department of Psychiatry, University of Cambridge , Cambridge CB2 0SZ
2 shared publications - Ryan J. Crowley
Department of Medicine, Stanford University School of Medicine, Stanford, CA
2 shared publications - Ann John
Swansea University Medical School
1 shared publication - Carol Brayne
Cambridge Public Health, University of Cambridge School of Clinical Medicine, Cambridge, UK
1 shared publication Efthalia Massou
Department of Public Health and Primary Care, University of Cambridge, Cambridge, UK
1 shared publication- Emilio Fernandez-Egea
University of Cambridge
1 shared publication
Latest Publications
- Open Access
- 3 November 2025
- Published by Oxford University Press (OUP) in JAMIA Open
- Vol. 8 (6)
Development of a risk factor framework to inform machine learning prediction of young people’s mental health problems: a Delphi study
Objectives: To create a theoretical framework of mental health risk factors to inform the development of prediction models for young people’s mental health problems. Materials and Methods: We created an initial prototype theoretical framework using a rapid literature search and stakeholder discussion. A snowball sampling approach identified experts for the Delphi study. Round 1 sought consensus on the overall approach, framework domains, and life course stages. Round 2 aimed to establish the points in the life course where exposure to specific risk factors would be most influential. Round 3 ranked risk factors within domains by their predictive importance for young people’s mental health problems. Results: The final framework reached consensus after 3 rounds and included 287 risk factors across 8 domains and 5 life course stages. Twenty-five experts completed round 3. Domains ranked as most important were “Social and Environmental” and “Psychological and Mental Health.” Ranked lists of risk factors within domains and heat maps showing the salience of risk factors across life course stages were generated. Discussion: The study integrated multidisciplinary expert perspectives and prioritized health equity throughout the framework’s development. The ranked risk factor lists and life stage heat maps support the targeted inclusion of risk factors across developmental stages in prediction models. Conclusion: This theoretical framework provides a roadmap of important risk factors for inclusion in early identification models to enhance the predictive accuracy of childhood mental health problems. It offers a useful theoretical reference point to support model building for those without domain expertise.
- 3 November 2025
- Published by Oxford University Press (OUP) in JAMIA Open
- Vol. 8 (6)
Open AccessDevelopment of a risk factor framework to inform machine learning prediction of young people’s mental health problems: a Delphi study
Objectives: To create a theoretical framework of mental health risk factors to inform the development of prediction models for young people’s mental health problems. Materials and Methods: We created an initial prototype theoretical framework using a rapid literature search and stakeholder discussion. A snowball sampling approach identified experts for the Delphi study. Round 1 sought consensus on the overall approach, framework domains, and life course stages. Round 2 aimed to establish the points in the life course where exposure to specific risk factors would be most influential. Round 3 ranked risk factors within domains by their predictive importance for young people’s mental health problems. Results: The final framework reached consensus after 3 rounds and included 287 risk factors across 8 domains and 5 life course stages. Twenty-five experts completed round 3. Domains ranked as most important were “Social and Environmental” and “Psychological and Mental Health.” Ranked lists of risk factors within domains and heat maps showing the salience of risk factors across life course stages were generated. Discussion: The study integrated multidisciplinary expert perspectives and prioritized health equity throughout the framework’s development. The ranked risk factor lists and life stage heat maps support the targeted inclusion of risk factors across developmental stages in prediction models. Conclusion: This theoretical framework provides a roadmap of important risk factors for inclusion in early identification models to enhance the predictive accuracy of childhood mental health problems. It offers a useful theoretical reference point to support model building for those without domain expertise.
- Open Access
- 11 April 2025
- Published by Royal College of Psychiatrists in BJPsych Open
- Vol. 11 (3) , e86
Machine learning for prediction of childhood mental health problems in social care
Background: Rates of childhood mental health problems are increasing in the UK. Early identification of childhood mental health problems is challenging but critical to children’s future psychosocial development. This is particularly important for children with social care contact because earlier identification can facilitate earlier intervention. Clinical prediction tools could improve these early intervention efforts. Aims: Characterise a novel cohort consisting of children in social care and develop effective machine learning models for prediction of childhood mental health problems. Method: We used linked, de-identified data from the Secure Anonymised Information Linkage Databank to create a cohort of 26 820 children in Wales, UK, receiving social care services. Integrating health, social care and education data, we developed several machine learning models aimed at predicting childhood mental health problems. We assessed the performance, interpretability and fairness of these models. Results: Risk factors strongly associated with childhood mental health problems included age, substance misuse and being a looked after child. The best-performing model, a gradient boosting classifier, achieved an area under the receiver operating characteristic curve of 0.75 (95% CI 0.73–0.78). Assessments of algorithmic fairness showed potential biases within these models. Conclusions: Machine learning performance on this prediction task was promising. Predictive performance in social care settings can be bolstered by linking diverse routinely collected data-sets, making available a range of heterogenous risk factors relating to clinical, social and environmental exposures.
- 11 April 2025
- Published by Royal College of Psychiatrists in BJPsych Open
- Vol. 11 (3) , e86
Open AccessMachine learning for prediction of childhood mental health problems in social care
Background: Rates of childhood mental health problems are increasing in the UK. Early identification of childhood mental health problems is challenging but critical to children’s future psychosocial development. This is particularly important for children with social care contact because earlier identification can facilitate earlier intervention. Clinical prediction tools could improve these early intervention efforts. Aims: Characterise a novel cohort consisting of children in social care and develop effective machine learning models for prediction of childhood mental health problems. Method: We used linked, de-identified data from the Secure Anonymised Information Linkage Databank to create a cohort of 26 820 children in Wales, UK, receiving social care services. Integrating health, social care and education data, we developed several machine learning models aimed at predicting childhood mental health problems. We assessed the performance, interpretability and fairness of these models. Results: Risk factors strongly associated with childhood mental health problems included age, substance misuse and being a looked after child. The best-performing model, a gradient boosting classifier, achieved an area under the receiver operating characteristic curve of 0.75 (95% CI 0.73–0.78). Assessments of algorithmic fairness showed potential biases within these models. Conclusions: Machine learning performance on this prediction task was promising. Predictive performance in social care settings can be bolstered by linking diverse routinely collected data-sets, making available a range of heterogenous risk factors relating to clinical, social and environmental exposures.
- Open Access
- 13 January 2022
- Published by Cambridge University Press (CUP) in Psychological Medicine
- Vol. 53 (7) , 2936-2945
Clozapine-related obsessive–compulsive symptoms and their impact on wellbeing: a naturalistic longitudinal study
Background: Obsessive–compulsive symptoms (OCS) are commonly associated with clozapine treatment but are frequently overlooked by clinicians despite their potential impact on patients' quality of life. In this study, we explored whether OCS severity impacted subjective wellbeing and general functioning, independently of depressive and psychotic symptoms.Methods: We used anonymised electronic healthcare records from a large cohort of patients who were treated with clozapine and assessed annually for OCS, wellbeing, general functioning, and psychopathology using standardised scales as part of routine clinical practice. We used statistical mixed linear model techniques to evaluate the longitudinal influence of OCS severity on wellbeing and general functioning.Results: A total of 184 patients were included, with 527 face-to-face assessments and 64.7% evaluated three or more times. Different linear mixed models demonstrated that OCS in patients treated with clozapine were associated with significantly worse wellbeing scores, independently of depression and psychotic symptoms, but OCS did not impair general functioning. Obsessional thinking and hoarding behaviour, but not compulsions, were significantly associated with the impact on wellbeing, which may be attributable to the ego-syntonic nature of the compulsions.Conclusions: Given the frequent occurrence of OCS and their negative impact on wellbeing, we encourage clinicians to routinely assess and treat OCS in patients who are taking clozapine.
- 13 January 2022
- Published by Cambridge University Press (CUP) in Psychological Medicine
- Vol. 53 (7) , 2936-2945
Open AccessClozapine-related obsessive–compulsive symptoms and their impact on wellbeing: a naturalistic longitudinal study
Background: Obsessive–compulsive symptoms (OCS) are commonly associated with clozapine treatment but are frequently overlooked by clinicians despite their potential impact on patients' quality of life. In this study, we explored whether OCS severity impacted subjective wellbeing and general functioning, independently of depressive and psychotic symptoms.Methods: We used anonymised electronic healthcare records from a large cohort of patients who were treated with clozapine and assessed annually for OCS, wellbeing, general functioning, and psychopathology using standardised scales as part of routine clinical practice. We used statistical mixed linear model techniques to evaluate the longitudinal influence of OCS severity on wellbeing and general functioning.Results: A total of 184 patients were included, with 527 face-to-face assessments and 64.7% evaluated three or more times. Different linear mixed models demonstrated that OCS in patients treated with clozapine were associated with significantly worse wellbeing scores, independently of depression and psychotic symptoms, but OCS did not impair general functioning. Obsessional thinking and hoarding behaviour, but not compulsions, were significantly associated with the impact on wellbeing, which may be attributable to the ego-syntonic nature of the compulsions.Conclusions: Given the frequent occurrence of OCS and their negative impact on wellbeing, we encourage clinicians to routinely assess and treat OCS in patients who are taking clozapine.