02 / 2022 – 08 / 2022
A good mental health state and suitable psychological treatment are related to better recovery from physiological problems . This is particularly relevant in palliative care, where improving the overall quality of life is the key aim . The assessment of the current mental health state, especially anxiety and depression, is an important aspect of care. Data-driven prediction models could help anticipate psychologic problems, enable more accurate monitoring, avoid the need for related questionnaires, and thus provide better care.
Existing research in predicting anxiety focus on conventional machine learning methods such as KNN, Random Forest, regression models or SVM [3, 6]. Research using Neural Networks and Deep Learning predict anxiety from explicit anxiety questionnaire data rather then other health data [6, 7]. In the area of Palliative care, machine learning methods are currently mainly used for predicting the patients’ need for palliative therapy [8, 9]. Hofmann et al. used palliative routine data to create a regression model for anxiety prediction, but did not explore machine learning techniques .
The aim of this thesis is to investigate various machine learning algorithms and applications on predicting axiety and other parameters.
 Gholam Reza Nikrahan, Johannes A. C. Laferton, Karim Asgari, Mehrdad Kalantari, Mohammad Reza Abedi, Ali Etesampour, Abbas Rezaei, Laura Suarez, and Jeff C. Huffman. Effects of Positive Psychology Interventions on Risk Biomarkers in Coronary Patients: A Randomized, Wait-List Controlled Pilot Trial. Psychosomatics, 57(4):359-368, July 2016.
 Robin B Rome, Hillary H Luminais, Deborah A Bourgeois, and Christopher M Blais. The role of palliative care at the end of life. Ochsner J., 11(4):348-352, 2011.
 Margret Olafsdottir, Per-Olow Sjoden, and Bengt Westling. Prevalence and prediction of chemotherapy-related anxiety, nausea and vomiting in cancer patients. Behaviour Research and Therapy, 24(1):59-66, January 1986.
 Kevin Yi-Lwern Yap, Xiu Hui Low, Wai Keung Chui, Alexandre Chan, and for the Onco-Informatics Group. Computational Prediction of State Anxiety in Asian Patients With Cancer Susceptible to Chemotherapy-Induced Nausea and Vomiting. Journal of Clinical Psychopharmacology, 32(2):207-217, April 2012.
 Markus W. Haun, Laura Simon, Halina Sklenarova, Verena Zimmermann-Schlegel, Hans-Christoph Friederich, and Mechthild Hartmann. Predicting anxiety in cancer survivors presenting to primary care A machine learning approach accounting for physical comorbidity. Cancer Medicine, 10(14):5001-5016, 2021. _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/cam4.4048.
 Anu Priya, Shruti Garg, and Neha Prerna Tigga. Predicting Anxiety, Depression and Stress in Modern Life using Machine Learning Algorithms. Procedia Computer Science, 167:1258-1267, January 2020.
 Prince Kumar, Shruti Garg, and Ashwani Garg. Assessment of Anxiety, Depression and Stress using Machine Learning Models. Procedia Computer Science, 171:1989-1998, January 2020.
 Anand Avati, Kenneth Jung, Stephanie Harman, Lance Downing, Andrew Ng, and Nigam H. Shah. Improving palliative care with deep learning. BMC Medical Informatics and Decision Making, 18(4):122, December 2018.
 Aixia Guo, Randi Foraker, Patrick White, Corey Chivers, Katherine Courtright, and Nathan Moore. Using Electronic Health Records and Claims Data to Identify High-risk Patients Likely to Benefit From Palliative Care. American Journal of Managed Care, 27(1):e7-e15, January 2021. Place: Cranbury, New Jersey Publisher: MJH Life Sciences.
 Sonja Hofmann, Stephanie Hess, Carsten Klein, Gabriele Lindena, Lukas Radbruch, and Christoph Ostgathe. Patients in palliative care: Development of a predictive model for anxiety using routine data. PLOS ONE, 12(8):e0179415, August 2017. Publisher: Public Library of Science.