データサイエンスを使用してメカニズムの発見において患者の視点を中心にする (CPP)
データサイエンスを使用して心理メカニズムの発見と介入開発において患者の視点を中心にする
Including patient perspectives when developing new therapy interventions is crucial because it can help to understand response heterogeneity and promote engagement. Yet, analyzing patient interview data is difficult and time-consuming. This study aims to explore the potential for natural language processing and deep learning to analyze patient interviews and identify potential ways in which therapy leads to psychological change. This study will recruit participants from an existing clinical service that offers a 16-week online group therapy model (and adjunct individual therapy sessions) called Program for Alleviating and Resolving Trauma and Stress (PARTS) based on a therapy called Internal Family Systems (IFS). The investigators will use a mixed methods approach, applying natural language processing and deep learning to develop models that identify potential mechanisms of change. These models will be based on patient perspectives of psychological change, as expressed in interviews, and be compared to models based on clinical measures.
調査の概要
状態
詳細な説明
Demand for cost-effective, novel, scalable trauma-focused interventions is high. Prevalence rates of posttraumatic stress disorder (PTSD) and Complex PTSD in US community mental health clinics are estimated to be as high as 50%. Yet response heterogeneity to PTSD interventions remains high, with non-response rates reaching 50-60% and dropout rates for traditional interventions (i.e., cognitive behavioral, exposure therapies) at 30-40%. Moreover, research populations in typical stepwise, efficacy-driven clinical research trials are often characterized by strict exclusion criteria and low representation from underrepresented communities. The homogeneous nature of efficacy-based research populations creates an incomplete picture, especially in public sector and community-based mental health facilities. Studies have suggested not only does this homogeneity limit effectiveness across diverse populations, but may contribute to exacerbating health disparities.
Engaging patient perspectives is crucial to research because it can provide insight into response heterogeneity and engagement, ultimately leading to an understanding of mechanisms and creating more patient-centered interventions. One way to center the patient's voice and increase the potential of identifying unique mechanisms of change for a novel therapy, is to use qualitative interviews because it directly accesses the lived experience and its context. Despite the potential benefits of utilizing qualitative data in stepwise randomized control trials, several obstacles persist, including resource constraints, the inability to quantify interactive elements, and concerns regarding the practical value of the gathered information. Innovative methods that reliably and rapidly extract value-laden, relevant themes, and discern non-verbal conversational elements may facilitate the integration of patient experience and inclusion of their perspectives in clinical intervention trials.
This single-arm study aims to evaluate the feasibility of using natural language processing (NLP) and deep learning to identify potential mechanisms of PTSD symptom change from patient interviews. The study will utilize ongoing cohorts from a clinical service that offers a 16-week, live-online group therapy model (and adjunct individual therapy sessions) called Program For Alleviating And Resolving Trauma and Stress (PARTS) that uses the IFS model. The investigators will use a convergent mixed methods approach applying machine learning and natural language processing to develop models that identify potential mechanisms of change.
Analysis: The investigators will use several different methods to develop our models including Latent Dirichlet Allocation, pre-trained language models, transfer learning (recurrent neural networks, generative adversarial network), and penalized regression-based models. These models will use data derived from patient perspectives of psychological change, as expressed in interviews, and will be compared to models derived from clinical measures. The study will use standard performance metrics and cross-validation scores to evaluate comparative performance of the models. As an exploratory aim, the study will evaluate the feasibility of using features derived from language processing models and clinical measures to predict individual therapy visits post-intervention. The exploratory data will also include structured clinical data, social determinants of health, and therapy-based utilization (dates, provider type, length).
Anticipated results: The development of two validated models: one derived from patient interview data and the other based on clinical measures to comprehensively identify mechanisms of change from group-based therapy models of IFS for PTSD.
研究の種類
入学 (実際)
連絡先と場所
研究場所
-
-
Massachusetts
-
Malden、Massachusetts、アメリカ、02148
- Cambridge Health Alliance
-
-
参加基準
適格基準
就学可能な年齢
健康ボランティアの受け入れ
受講資格のある性別
サンプリング方法
調査対象母集団
Participants will be recruited from a community-based clinical service called Program For Alleviating and Resolving Trauma and Stress (PARTS) service within Cambridge Health Alliance (CHA) that offers a 16-week, live-online group therapy model based on Internal Family Systems.
説明
Inclusion Criteria:
Must be enrolled in the clinical service offering online PARTS group and approved and confirmed to start by the clinical team.
Have sufficient English fluency and literacy skills to understand the consent process, procedures and questionnaires and have the ability to provide written informed consent.
Have access to the internet and an electronic device with adequate data capacity; to complete questionnaires online and participate in two online video interviews.
Must be willing to complete online computerized assessments both at baseline and post-intervention; and participate in two, one-hour videotaped interviews one at baseline and one 2-4 weeks post-intervention.
Exclusion Criteria:
Inability to complete an informed consent assessment AND/OR inability to complete baseline study assessment procedures (due to cognitive deficit, non-proficiency in English literacy, or any other reason).
Expected medical hospitalization in 24 weeks from the date of enrollment.
Expected incarceration in 24 weeks from the date of enrollment.
Individuals who are pregnant with a due date within 24 weeks after study consent.
Insufficient internet connection to conduct online interviews or computerized assessments.
研究計画
研究はどのように設計されていますか?
デザインの詳細
- 観測モデル:COHORT
- 時間の展望:PROSPECTIVE
この研究は何を測定していますか?
主要な結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Similarity of topics and mechanism identification
時間枠:24 weeks
|
Similarity of topics obtained from interview data using language processing tools to those classified by human coders and identification of mechanisms from predictive models with language processing derived features. |
24 weeks
|
二次結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Comparable mechanism identification and performance
時間枠:24 weeks
|
Models using features derived from interview data will find comparable mechanisms to ones using clinical survey data and exhibit moderate predictive power. |
24 weeks
|
その他の成果指標
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
PTSD Symptom Severity Changes
時間枠:20 weeks
|
The PTSD Checklist for DSM-5 (PCL-5) is a 20-item self-report measure designed to assess PTSD symptom severity (scores above 30-31 indicate more severe symptoms). |
20 weeks
|
|
PTSD and Complex PTSD Symptom Severity Changes
時間枠:20 weeks
|
The 18-item International Trauma Questionnaire (ITQ) captures PTSD symptom severity, disturbances in self-organization (DSO) (characteristic of Complex PTSD), and impact on functioning. For the ITQ, PTSD and DSO scores range from 0 to 24, while Complex PTSD scores range from 0 to 48. |
20 weeks
|
協力者と研究者
捜査官
- 主任研究者:Zev Schuman-Olivier, MD、Center for Mindfulness and Compassion, Cambridge Health Alliance
- 主任研究者:Dilara Ally, PhD、Center for Mindfulness and Compassion, Cambridge Health Alliance
出版物と役立つリンク
一般刊行物
- Schottenbauer MA, Glass CR, Arnkoff DB, Tendick V, Gray SH. Nonresponse and dropout rates in outcome studies on PTSD: review and methodological considerations. Psychiatry. 2008 Summer;71(2):134-68. doi: 10.1521/psyc.2008.71.2.134.
- Spoont MR, Murdoch M, Hodges J, Nugent S. Treatment receipt by veterans after a PTSD diagnosis in PTSD, mental health, or general medical clinics. Psychiatr Serv. 2010 Jan;61(1):58-63. doi: 10.1176/ps.2010.61.1.58.
- Adams-Campbell LL, Ahaghotu C, Gaskins M, Dawkins FW, Smoot D, Polk OD, Gooding R, DeWitty RL. Enrollment of African Americans onto clinical treatment trials: study design barriers. J Clin Oncol. 2004 Feb 15;22(4):730-4. doi: 10.1200/JCO.2004.03.160.
- Erves JC, Mayo-Gamble TL, Malin-Fair A, Boyer A, Joosten Y, Vaughn YC, Sherden L, Luther P, Miller S, Wilkins CH. Needs, Priorities, and Recommendations for Engaging Underrepresented Populations in Clinical Research: A Community Perspective. J Community Health. 2017 Jun;42(3):472-480. doi: 10.1007/s10900-016-0279-2.
研究記録日
主要日程の研究
研究開始 (実際)
一次修了 (実際)
研究の完了 (推定)
試験登録日
最初に提出
QC基準を満たした最初の提出物
最初の投稿 (実際)
学習記録の更新
投稿された最後の更新 (実際)
QC基準を満たした最後の更新が送信されました
最終確認日
詳しくは
本研究に関する用語
追加の関連 MeSH 用語
その他の研究ID番号
- 13664
個々の参加者データ (IPD) の計画
個々の参加者データ (IPD) を共有する予定はありますか?
IPD プランの説明
Not planning to share IPD with other researchers
医薬品およびデバイス情報、研究文書
米国FDA規制医薬品の研究
米国FDA規制機器製品の研究
この情報は、Web サイト clinicaltrials.gov から変更なしで直接取得したものです。研究の詳細を変更、削除、または更新するリクエストがある場合は、register@clinicaltrials.gov。 までご連絡ください。 clinicaltrials.gov に変更が加えられるとすぐに、ウェブサイトでも自動的に更新されます。