1
|
Solsky I, Haynes AB. Beyond the physical: Digital phenotyping and the complexity of surgical recovery. Surgery 2024; 176:519-520. [PMID: 38749794 DOI: 10.1016/j.surg.2024.04.021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2024] [Revised: 04/11/2024] [Accepted: 04/17/2024] [Indexed: 07/16/2024]
Abstract
Digital phenotyping, the moment-by-moment quantification of human behavior in situ using data from personal digital devices, is a potentially powerful tool for increasing understanding of recovery from surgery. While physical metrics are often emphasized, measures of emotional, cognitive, and psychosocial function are important aspects for the surgeon, a better understanding of which can lead to improved preoperative counseling and optimization, shared decision-making, and monitoring of recovery after surgery. A growing number of studies have begun to characterize these techniques. Ultimately, this tool may provide rich data about the perioperative period that will help surgeons and patients alike.
Collapse
Affiliation(s)
| | - Alex B Haynes
- University of Texas, Austin. https://twitter.com/masstransitalex
| |
Collapse
|
2
|
Ciharova M, Amarti K, van Breda W, Peng X, Lorente-Català R, Funk B, Hoogendoorn M, Koutsouleris N, Fusar-Poli P, Karyotaki E, Cuijpers P, Riper H. Use of Machine Learning Algorithms Based on Text, Audio, and Video Data in the Prediction of Anxiety and Posttraumatic Stress in General and Clinical Populations: A Systematic Review. Biol Psychiatry 2024:S0006-3223(24)01362-3. [PMID: 38866173 DOI: 10.1016/j.biopsych.2024.06.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/27/2023] [Revised: 05/24/2024] [Accepted: 06/04/2024] [Indexed: 06/14/2024]
Abstract
Research in machine learning (ML) algorithms using natural behavior (i.e., text, audio, and video data) suggests that these techniques could contribute to personalization in psychology and psychiatry. However, a systematic review of the current state of the art is missing. Moreover, individual studies often target ML experts who may overlook potential clinical implications of their findings. In a narrative accessible to mental health professionals, we present a systematic review conducted in 5 psychology and 2 computer science databases. We included 128 studies that assessed the predictive power of ML algorithms using text, audio, and/or video data in the prediction of anxiety and posttraumatic stress disorder. Most studies (n = 87) were aimed at predicting anxiety, while the remainder (n = 41) focused on posttraumatic stress disorder. They were mostly published since 2019 in computer science journals and tested algorithms using text (n = 72) as opposed to audio or video. Studies focused mainly on general populations (n = 92) and less on laboratory experiments (n = 23) or clinical populations (n = 13). Methodological quality varied, as did reported metrics of the predictive power, hampering comparison across studies. Two-thirds of studies, which focused on both disorders, reported acceptable to very good predictive power (including high-quality studies only). The results of 33 studies were uninterpretable, mainly due to missing information. Research into ML algorithms using natural behavior is in its infancy but shows potential to contribute to diagnostics of mental disorders, such as anxiety and posttraumatic stress disorder, in the future if standardization of methods, reporting of results, and research in clinical populations are improved.
Collapse
Affiliation(s)
- Marketa Ciharova
- Department of Clinical, Neuro, and Developmental Psychology, Amsterdam Public Health Research Institute, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands; Black Dog Institute, University of New South Wales, Sydney, New South Wales, Australia.
| | - Khadicha Amarti
- Department of Clinical, Neuro, and Developmental Psychology, Amsterdam Public Health Research Institute, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
| | - Ward van Breda
- Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
| | - Xianhua Peng
- Department of Clinical, Neuro, and Developmental Psychology, Amsterdam Public Health Research Institute, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands; Department of Methodology and Statistics, Tilburg School of Social and Behavioral Sciences, Tilburg University, Tilburg, the Netherlands
| | - Rosa Lorente-Català
- Department of Basic and Clinical Psychology and Psychobiology, Universitat Jaume I, Castellon, Spain
| | - Burkhardt Funk
- Institute of Information Systems, Leuphana University, Lüneburg, Germany
| | - Mark Hoogendoorn
- Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
| | - Nikolaos Koutsouleris
- Artificial Intelligence in Mental Health Group, Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom; Precision Psychiatry Group, Max Planck Institute, Munich, Germany; Section for Precision Psychiatry, Department of Psychiatry and Psychotherapy, University Medical Center, Ludwig-Maximilians-University Munich, Munich, Germany
| | - Paolo Fusar-Poli
- Section for Precision Psychiatry, Department of Psychiatry and Psychotherapy, University Medical Center, Ludwig-Maximilians-University Munich, Munich, Germany; Early Psychosis: Interventions and Clinical-Detection (EPIC) Lab, Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom; Department of Brain and Behavioural Sciences, University of Pavia, Pavia, Italy; OASIS Service, South London and the Maudsley National Health Service Foundation Trust, London, United Kingdom
| | - Eirini Karyotaki
- Department of Clinical, Neuro, and Developmental Psychology, Amsterdam Public Health Research Institute, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands; WHO Collaborating Center for Research and Dissemination of Psychological Interventions, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
| | - Pim Cuijpers
- Department of Clinical, Neuro, and Developmental Psychology, Amsterdam Public Health Research Institute, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands; WHO Collaborating Center for Research and Dissemination of Psychological Interventions, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands; Babeș-Bolyai University, International Institute for Psychotherapy, Cluj-Napoca, Romania
| | - Heleen Riper
- Department of Clinical, Neuro, and Developmental Psychology, Amsterdam Public Health Research Institute, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands; Department of Psychiatry, Amsterdam Public Health Research Institute, Amsterdam University Medical Centre, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
| |
Collapse
|
3
|
Schoeller F, Christov-Moore L, Lynch C, Diot T, Reggente N. Predicting individual differences in peak emotional response. PNAS NEXUS 2024; 3:pgae066. [PMID: 38444601 PMCID: PMC10914375 DOI: 10.1093/pnasnexus/pgae066] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/19/2023] [Accepted: 01/24/2024] [Indexed: 03/07/2024]
Abstract
Why does the same experience elicit strong emotional responses in some individuals while leaving others largely indifferent? Is the variance influenced by who people are (personality traits), how they feel (emotional state), where they come from (demographics), or a unique combination of these? In this 2,900+ participants study, we disentangle the factors that underlie individual variations in the universal experience of aesthetic chills, the feeling of cold and shivers down the spine during peak experiences. Here, we unravel the interplay of psychological and sociocultural dynamics influencing self-reported chills reactions. A novel technique harnessing mass data mining of social media platforms curates the first large database of ecologically sourced chills-evoking stimuli. A combination of machine learning techniques (LASSO and SVM) and multilevel modeling analysis elucidates the interacting roles of demographics, traits, and states factors in the experience of aesthetic chills. These findings highlight a tractable set of features predicting the occurrence and intensity of chills-age, sex, pre-exposure arousal, predisposition to Kama Muta (KAMF), and absorption (modified tellegen absorption scale [MODTAS]), with 73.5% accuracy in predicting the occurrence of chills and accounting for 48% of the variance in chills intensity. While traditional methods typically suffer from a lack of control over the stimuli and their effects, this approach allows for the assignment of stimuli tailored to individual biopsychosocial profiles, thereby, increasing experimental control and decreasing unexplained variability. Further, they elucidate how hidden sociocultural factors, psychological traits, and contextual states shape seemingly "subjective" phenomena.
Collapse
Affiliation(s)
- Felix Schoeller
- Institute for Advanced Consciousness Studies, Santa Monica, CA 90403, USA
- Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
| | | | - Caitlin Lynch
- Institute for Advanced Consciousness Studies, Santa Monica, CA 90403, USA
| | - Thomas Diot
- Department of Psychiatry, GHU Paris Psychiatrie et Neurosciences, Paris 75010, France
| | - Nicco Reggente
- Institute for Advanced Consciousness Studies, Santa Monica, CA 90403, USA
| |
Collapse
|