Clinical Questions and Psychological Change: How Can Artificial Intelligence Support Mental Health Practitioners?
Abstract
:1. Introduction
Theoretical–Methodological References and Scope
- Generative DRs promote or keep pressure towards the management of critical situations and the creation of new realities of sense;
- Stabilization DRs concur to keep unchanged the ways that outline the ongoing reality of sense;
- Hybrid DRs develop in both a generative or stabilization orientation based on the DR they link with.
- Description: they pursue the objective of detecting the discursive configuration, gathering what is brought by the patient;
- Evaluation: they pursue the objective of deepening the text offered by the patient, bringing in other elements and specifying them;
- Generating change: they pursue the objective of shifting the discursive configuration of the patient toward healthier scenarios and intervening following that direction;
- Maintenance: they pursue the goal of consolidating what has been built and developed during the clinical intervention with the patient up until that specific moment.
2. Materials and Methods
- Precision: the number of correctly labeled items out of all items that were labeled (correctly or not with that class of DR);
- Recall: the number of correctly labeled items compared to the total number of items that belong to that DR class;
- F1-score: the harmonic mean between precision and recall;
- Accuracy: the number of correct predictions out of all predictions made.
- Encode question and answer in the input;
- Use what has already been administered in the training phase of the ML algorithm to encode the argumentative ‘joints’ (the part(s) of text that could represent the DR) defined by the question (and/or its DR), vocabulary, position of graphic forms, presence of particles and, more generally, relevant features in congruence with what has been administered;
- Denominate the most plausible DR for the response text, based on the coding obtained.
- By changing the question, the trajectory of the discursive configuration changes and, in turn, the possibilities of psychological change increase;
- Some DRs may be more likely to occur than others;
- With description questions, a wider range of DRs may be more likely to occur;
- With evaluation questions, a shorter range toward hybrid DRs may be more likely to occur.
3. Results
3.1. Experimental Case 1: No Question vs. Question String
3.2. Experimental Case 2: Adding Information About the Question
4. Discussion and Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Gelo, O.C.G.; Lagetto, G.; Dinoi, C.; Belfiore, E.; Lombi, E.; Blasi, S.; Aria, M.; Ciavolino, E. Which Methodological Practice (s) for Psychotherapy Science? A Systematic Review and a Proposal. Integr. Psychol. Behav. Sci. 2020, 54, 215–248. [Google Scholar] [CrossRef] [PubMed]
- Salvatore, S.; Cordella, B. Foundations of the Psychological Intervention: A Unifying Theoretical and Methodological Framework; Routledge: London, UK, 2024; ISBN 978-1-00-344936-2. [Google Scholar]
- Kim, N.S.; Ahn, W. Clinical Psychologists’ Theory-Based Representations of Mental Disorders Predict Their Diagnostic Reasoning and Memory. J. Exp. Psychol. Gen. 2002, 131, 451–476. [Google Scholar] [CrossRef] [PubMed]
- Fried, E.I.; Flake, J.K.; Robinaugh, D.J. Revisiting the Theoretical and Methodological Foundations of Depression Measurement. Nat. Rev. Psychol. 2022, 1, 358–368. [Google Scholar] [CrossRef] [PubMed]
- Neal, T.M.S.; MacLean, N.; Morgan, R.D.; Murrie, D.C. Confirmatory Information Seeking Is Robust in Psychologists’ Diagnostic Reasoning. Law Hum. Behav. 2024. [Google Scholar] [CrossRef]
- Iudici, A.; Colombo, L.; Caravita, S.C.S.; Cottone, P.; Neri, J. The Invisible Discrimination: Biases in the Clinical Approach Regarding Migrants: A Study to Help Ethnopsychology Services and Clinicians. Behav. Sci. 2024, 14, 155. [Google Scholar] [CrossRef]
- Klatte, R.; Strauss, B.; Flückiger, C.; Rosendahl, J. Adverse Effects of Psychotherapy: Protocol for a Systematic Review and Meta-Analysis. Syst. Rev. 2018, 7, 135. [Google Scholar] [CrossRef]
- Curran, J.; Parry, G.D.; Hardy, G.E.; Darling, J.; Mason, A.-M.; Chambers, E. How Does Therapy Harm? A Model of Adverse Process Using Task Analysis in the Meta-Synthesis of Service Users’ Experience. Front. Psychol. 2019, 10, 347. [Google Scholar] [CrossRef]
- Saxon, D.; Barkham, M.; Foster, A.; Parry, G. The Contribution of Therapist Effects to Patient Dropout and Deterioration in the Psychological Therapies. Clin. Psychol. Psychother. 2017, 24, 575–588. [Google Scholar] [CrossRef]
- Flemotomos, N.; Martinez, V.R.; Chen, Z.; Singla, K.; Ardulov, V.; Peri, R.; Caperton, D.D.; Gibson, J.; Tanana, M.J.; Georgiou, P.; et al. Automated Evaluation of Psychotherapy Skills Using Speech and Language Technologies. Behav. Res. Methods 2022, 54, 690–711. [Google Scholar] [CrossRef]
- Aafjes-van Doorn, K.; Kamsteeg, C.; Bate, J.; Aafjes, M. A Scoping Review of Machine Learning in Psychotherapy Research. Psychother. Res. 2021, 31, 92–116. [Google Scholar] [CrossRef]
- Orrù, L.; Taccini, F.; Mannarini, S. Worry about the Future in the Climate Change Emergency: A Mediation Analysis of the Role of Eco-Anxiety and Emotion Regulation. Behav. Sci. 2024, 14, 255. [Google Scholar] [CrossRef]
- World Health Organization. Constitution of the World ‘Health’ Organization, 45th ed.; WHO: Geneva, Switzerland, 2006. [Google Scholar]
- Turchi, G.P.; Orrù, L.; Iudici, A.; Pinto, E. A Contribution towards Health. J. Eval. Clin. Pract. 2022, 28, 717–720. [Google Scholar] [CrossRef] [PubMed]
- Wittgenstein, L. Tractatus Logico-Philosophicus; Routledge & Kegan Paul: London, UK, 1922. [Google Scholar]
- Choosing Prediction Over Explanation in Psychology: Lessons from Machine Learning-Tal Yarkoni, Jacob Westfall. 2017. Available online: https://journals.sagepub.com/doi/10.1177/1745691617693393 (accessed on 22 July 2024).
- Dwyer, D.B.; Falkai, P.; Koutsouleris, N. Machine Learning Approaches for Clinical Psychology and Psychiatry. Annu. Rev. Clin. Psychol. 2018, 14, 91–118. [Google Scholar] [CrossRef]
- Singla, K.; Chen, Z.; Flemotomos, N.; Gibson, J.; Can, D.; Atkins, D.; Narayanan, S. Using Prosodic and Lexical Information for Learning Utterance-Level Behaviors in Psychotherapy. Interspeech 2018, 2018, 3413–3417. [Google Scholar] [PubMed]
- Black, M.P.; Katsamanis, A.; Baucom, B.R.; Lee, C.-C.; Lammert, A.C.; Christensen, A.; Georgiou, P.G.; Narayanan, S.S. Toward Automating a Human Behavioral Coding System for Married Couples’ Interactions Using Speech Acoustic Features. Speech Commun. 2013, 55, 1–21. [Google Scholar] [CrossRef]
- Xiao, B.; Bone, D.; Segbroeck, M.V.; Imel, Z.E.; Atkins, D.C.; Georgiou, P.G.; Narayanan, S.S. Modeling Therapist Empathy through Prosody in Drug Addiction Counseling. In Proceedings of the Interspeech 2014, ISCA, Singapore, 14 September 2014; pp. 213–217. [Google Scholar]
- Rubel, J.A.; Zilcha-Mano, S.; Giesemann, J.; Prinz, J.; Lutz, W. Predicting Personalized Process-Outcome Associations in Psychotherapy Using Machine Learning Approaches—A Demonstration. Psychother. Res. 2020, 30, 300–309. [Google Scholar] [CrossRef]
- Shatte, A.B.R.; Hutchinson, D.M.; Teague, S.J. Machine Learning in Mental Health: A Scoping Review of Methods and Applications. Psychol. Med. 2019, 49, 1426–1448. [Google Scholar] [CrossRef]
- Mikolov, T.; Sutskever, I.; Chen, K.; Corrado, G.; Dean, J. Distributed Representations of Words and Phrases and Their Compositionality. arXiv 2013, arXiv:1310.4546. [Google Scholar]
- Alshahrani, S.; Kapetanios, E. Are Deep Learning Approaches Suitable for Natural Language Processing? In Natural Language Processing and Information Systems; Lecture Notes in Computer Science; Métais, E., Meziane, F., Saraee, M., Sugumaran, V., Vadera, S., Eds.; Springer International Publishing: Cham, Switzerland, 2016; Volume 9612, pp. 343–349. ISBN 978-3-319-41753-0. [Google Scholar]
- Maitra, S.; Eshrak, S.; Bari, A.; Al-Sakin, A.; Munia, R.H.; Akter, N.; Haque, Z. Prediction of Academic Performance Applying NNs: A Focus on Statistical Feature-Shedding and Lifestyle. Int. J. Adv. Comput. Sci. Appl. 2019, 10, 561–570. [Google Scholar] [CrossRef]
- Cook, B.L.; Progovac, A.M.; Chen, P.; Mullin, B.; Hou, S.; Baca-Garcia, E. Novel Use of Natural Language Processing (NLP) to Predict Suicidal Ideation and Psychiatric Symptoms in a Text-Based Mental Health Intervention in Madrid. Comput. Math. Methods Med. 2016, 2016, 8708434. [Google Scholar] [CrossRef]
- Harikumar, H.; Nguyen, T.; Gupta, S.; Rana, S.; Kaimal, R.; Venkatesh, S. Understanding Behavioral Differences Between Short and Long-Term Drinking Abstainers from Social Media. In Proceedings of the Advanced Data Mining and Applications: 12th International Conference, ADMA 2016, Gold Coast, QLD, Australia, 12–15 December 2016; Springer: Berlin/Heidelberg, Germany, 2016; pp. 520–533. [Google Scholar]
- Song, I.; Dillon, D.; Goh, T.J.; Sung, M. A Health Social Network Recommender System. In Proceedings of the Agents in Principle, Agents in Practice; Kinny, D., Hsu, J.Y., Governatori, G., Ghose, A.K., Eds.; Springer: Berlin/Heidelberg, Germany, 2011; pp. 361–372. [Google Scholar]
- Orrù, L.; Neri, J.; Cuccarini, M.; Iudici, A.; Turchi, G.P. Biographical Change and Machine Learning with MADIT: A Predictive Model Proposal for Data and Intervention Analysis. In Proceedings of the 16th International Conference on Statistical Analysis of Textual Data, Naples, Italy, 6–8 July 2022; pp. 644–650. [Google Scholar]
- Kazdin, A.E. Understanding How and Why Psychotherapy Leads to Change. Psychother. Res. J. Soc. Psychother. Res. 2009, 19, 418–428. [Google Scholar] [CrossRef] [PubMed]
- Carey, T.A. Exposure and Reorganization: The What and How of Effective Psychotherapy. Clin. Psychol. Rev. 2011, 31, 236–248. [Google Scholar] [CrossRef] [PubMed]
- Goldfried, M.R. What Should We Expect from Psychotherapy? Clin. Psychol. Rev. 2013, 33, 862–869. [Google Scholar] [CrossRef] [PubMed]
- Wittgenstein, L. Philosophical Investigations; Basil Blackwell Ltd.: Oxford, UK, 1953. [Google Scholar]
- Turchi, G.P.; Dalla Riva, M.S.; Ciloni, C.; Moro, C.; Orrù, L. The Interactive Management of the SARS-CoV-2 Virus: The Social Cohesion Index, a Methodological-Operational Proposal. Front. Psychol. 2021, 12, 559842. [Google Scholar] [CrossRef] [PubMed]
- Turchi, G.P.; Dalla Riva, M.S.; Orrù, L.; Pinto, E. How to Intervene in the Health Management of the Oncological Patient and of Their Caregiver? A Narrative Review in the Psycho-Oncology Field. Behav. Sci. 2021, 11, 99. [Google Scholar] [CrossRef]
- Pinto, E.; Alfieri, R.; Orrù, L.; Dalla Riva, M.S.; Turchi, G.P. Forward to a Methodological Proposal to Support Cancer Patients: The Dialogics’ Contribution for the Precision Care. Med. Oncol. 2022, 39, 75. [Google Scholar] [CrossRef]
- Brady, H.E. The Challenge of Big Data and Data Science. Annu. Rev. Polit. Sci. 2019, 22, 297–323. [Google Scholar] [CrossRef]
- Lazer, D.; Radford, J. Data Ex Machina: Introduction to Big Data. Annu. Rev. Sociol. 2017, 43, 19–39. [Google Scholar] [CrossRef]
- Van Atteveldt, W.; van der Velden, M.A.C.G.; Boukes, M. The Validity of Sentiment Analysis: Comparing Manual Annotation, Crowd-Coding, Dictionary Approaches, and Machine Learning Algorithms. Commun. Methods Meas. 2021, 15, 121–140. [Google Scholar] [CrossRef]
- Turchi, G.P.; Moro, C.; Neri, J.; Orrù, L. Dialogic Process Analysis in Natural Language Processing: An Attempt to Describe the Sense of Reality and Meaning of Textdata. In New Frontiers in Textual Data Analysis; Studies in Classification, Data Analysis, and Knowledge Organization; Giordano, G., Misuraca, M., Eds.; Springer: Cham, Switzerland, 2024. [Google Scholar]
- Turchi, G.P.; Bassi, D.; Agnoletti, C.; Riva, M.S.D.; Iudici, A.; Orrù, L. What Are They Gonna Think About Me? An Innovative Text Analysis on Social Anxiety and Taijin Kyofusho Through MADIT Methodology. Hum. Arenas 2023, 1–15. [Google Scholar] [CrossRef]
- Turchi, G.P.; Orrù, L.; Trovò, A.; Moro, C.; Iudici, A.; Navarin, N. Introducing Dialogic Process Analysis in Natural Language Processing. In Proceedings of the 16th International Conference on Statistical Analysis of Textual Data, Naples, Italy, 6–8 July 2022; pp. 636–643. [Google Scholar]
- Luxton, D.D. Artificial Intelligence in Psychological Practice: Current and Future Applications and Implications. Prof. Psychol. Res. Pract. 2014, 45, 332–339. [Google Scholar] [CrossRef]
- Orrù, L.; Moro, C.; Cuccarini, M.; Paita, M.; Dalla Riva, M.S.; Bassi, D.; Da San Martino, G.; Navarin, N.; Turchi, G.P. Machine Learning and MADIT Methodology for the Fake News Identification: The Persuasion Index. In Proceedings of the 4th International Conference on Advanced Research Methods and Analytics (CARMA 2022), València, Spain, 29 June 2022. [Google Scholar]
- Iudici, A.; Verzelloni, C.; Bonato, D.; Neri, J.; Faccio, E. Relocation into Italian Residential Care Homes: A Qualitative Analysis of Decision and Choice: Psychological Implications and Consideration on Health. Collabra Psychol. 2022, 8, 31755. [Google Scholar] [CrossRef]
Model | Pretrained Weights | Batch Size | Learning Rate | Freeze To |
---|---|---|---|---|
BertClfier | bert-base-italian-xxl-uncased | 16 | 1e -05 | 1 |
AdamW Eps | Max Epochs | Patience Epochs | Embed Dim | Activation Function |
0.0001 | 200 | 20 | 768 | ReLU |
Discursive Repertoires | PrecA | PrecB | RecA | RecB | F1A | F1B |
---|---|---|---|---|---|---|
Anticipation | 0.06 | 0.07 | 0.13 | 0.07 | 0.08 | 0.07 |
Cause of Action | 0.40 | 0.32 | 0.48 | 0.44 | 0.43 | 0.37 |
Comment | 0.26 | 0.20 | 0.22 | 0.20 | 0.23 | 0.20 |
Confirmation | 0.25 | 0.27 | 0.35 | 0.31 | 0.29 | 0.29 |
Consideration | 0.09 | 0.00 | 0.31 | 0.00 | 0.14 | 0.00 |
Contraposition | 0.48 | 0.43 | 0.64 | 0.63 | 0.55 | 0.51 |
Description | 0.68 | 0.64 | 0.46 | 0.45 | 0.55 | 0.53 |
Declaration of Aims | 0.30 | 0.26 | 0.60 | 0.53 | 0.40 | 0.35 |
Generalization | 0.23 | 0.16 | 0.17 | 0.11 | 0.19 | 0.13 |
Judgment | 0.63 | 0.56 | 0.52 | 0.52 | 0.57 | 0.54 |
Justification | 0.27 | 0.28 | 0.42 | 0.36 | 0.33 | 0.31 |
Implications | 0.31 | 0.30 | 0.41 | 0.34 | 0.35 | 0.32 |
Non Answer | 0.42 | 0.38 | 0.62 | 0.61 | 0.71 | 0.47 |
Opinion | 0.52 | 0.46 | 0.67 | 0.67 | 0.59 | 0.54 |
Possibility | 0.40 | 0.40 | 0.43 | 0.39 | 0.42 | 0.39 |
Prescription | 0.37 | 0.37 | 0.74 | 0.67 | 0.49 | 0.48 |
Prevision | 0.26 | 0.24 | 0.52 | 0.40 | 0.34 | 0.30 |
Proposal | 0.28 | 0.23 | 0.52 | 0.58 | 0.36 | 0.14 |
Reshaping | 0.31 | 0.06 | 0.57 | 0.14 | 0.40 | 0.08 |
Targeting | 0.37 | 0.29 | 0.51 | 0.57 | 0.43 | 0.39 |
Certify Reality | 0.55 | 0.50 | 0.25 | 0.16 | 0.34 | 0.24 |
Specification | 0.33 | 0.30 | 0.39 | 0.32 | 0.36 | 0.31 |
Evaluation | 0.29 | 0.30 | 0.34 | 0.34 | 0.31 | 0.32 |
Accuracy | - | - | - | - | 0.43 | 0.39 |
Macro avg | 0.35 | 0.30 | 0.45 | 0.39 | 0.38 | 0.32 |
Weighted avg | 0.47 | 0.43 | 0.43 | 0.39 | 0.43 | 0.38 |
RDs–Description Question | n° of Occurrences | % Probability | DRs—Evaluation Question | n° of Occurrence | % Probability |
---|---|---|---|---|---|
Certify Reality | 2213 | 0.17 | |||
Judgment | 2173 | 0.17 | |||
Description | 1885 | 0.15 | Certify Reality | 75 | 0.2 |
Opinion | 687 | 0.05 | Judgment | 69 | 0.18 |
Comment | 606 | 0.05 | Description | 52 | 0.14 |
Evaluation | 579 | 0.05 | Opinion | 44 | 0.12 |
Specification | 538 | 0.04 | Comment | 31 | 0.08 |
Generalization | 504 | 0.04 | Specification | 16 | 0.04 |
Contraposition | 406 | 0.03 | Evaluation | 13 | 0.03 |
Implications | 391 | 0.03 | Generalization | 12 | 0.03 |
Justification | 343 | 0.03 | Contraposition | 11 | 0.03 |
Cause of Action | 315 | 0.02 | Prescription | 11 | 0.03 |
Prevision | 278 | 0.02 | Possibility | 7 | 0.02 |
Possibility | 269 | 0.02 | Proposal | 6 | 0.02 |
Declaration of Aims | 267 | 0.02 | Justification | 5 | 0.01 |
Non Answer | 251 | 0.02 | Cause of Action | 4 | 0.01 |
Prescription | 208 | 0.02 | Prevision | 4 | 0.01 |
Confirmation | 186 | 0.01 | Implications | 3 | 0.01 |
Targeting | 173 | 0.01 | Non Answer | 3 | 0.01 |
Proposal | 96 | 0.01 | Consideration | 2 | 0.01 |
Anticipation | 47 | 0.003 | Declaration of Aims | 2 | 0.01 |
Consideration | 41 | 0.002 | Targeting | 2 | 0.01 |
Reshaping | 2 | 0.0001 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Orrù, L.; Cuccarini, M.; Moro, C.; Turchi, G.P. Clinical Questions and Psychological Change: How Can Artificial Intelligence Support Mental Health Practitioners? Behav. Sci. 2024, 14, 1225. https://doi.org/10.3390/bs14121225
Orrù L, Cuccarini M, Moro C, Turchi GP. Clinical Questions and Psychological Change: How Can Artificial Intelligence Support Mental Health Practitioners? Behavioral Sciences. 2024; 14(12):1225. https://doi.org/10.3390/bs14121225
Chicago/Turabian StyleOrrù, Luisa, Marco Cuccarini, Christian Moro, and Gian Piero Turchi. 2024. "Clinical Questions and Psychological Change: How Can Artificial Intelligence Support Mental Health Practitioners?" Behavioral Sciences 14, no. 12: 1225. https://doi.org/10.3390/bs14121225
APA StyleOrrù, L., Cuccarini, M., Moro, C., & Turchi, G. P. (2024). Clinical Questions and Psychological Change: How Can Artificial Intelligence Support Mental Health Practitioners? Behavioral Sciences, 14(12), 1225. https://doi.org/10.3390/bs14121225