Predicting PTSD with machine learning: Forecasting refugees’ trauma and tailored intervention
Bibliographic record
Abstract
Post-Traumatic Stress Disorder (PTSD) is a mental health condition triggered by experiencing or witnessing traumatic events. Symptoms of PTSD include intrusive thoughts, avoidance behaviors, negative alterations in cognition and mood, and heightened arousal and reactivity. These symptoms can severely impact an individual's daily functioning and quality of life. Refugees, who often face extreme stress and traumatic experiences, are particularly susceptible to PTSD. The high prevalence of PTSD among refugee populations demands effective screening and early intervention to mitigate long-term mental health consequences. Therefore, the primary objective of this study is to leverage machine learning algorithms to predict PTSD in individuals using data derived from the PTSD Checklist for DSM-5 (PCL-5) and sociodemographic information. By developing a predictive model, in R and using the Python and random forests, we aim to identify individuals at high risk of developing PTSD, according to specific factors interacting in the context, as well allowing for timely and targeted interventions. Sociodemographic variables and symptoms (features) were collected in 77 survivors with refugee status admitted in Portugal, through sociodemographic questionnaire and the PCL-5, respectively. The predictive model based in each set of factors indicated area under the curve (Receiver Operating Characteristics) with moderate to high values (between >50 and <93) for validations trials with pool sensitivity variation between 33% and 70%. Specificity showed unbalanced scoring (false positives approx. 80%) for some clusters from PCL-5 considering certain variables introduced in model as potential predictors. Intrusive memories and cognitive and mood alterations were the clusters with highest predictive value to determine the ML model by integrating the following sociodemographic factors: date of entry in host country, academic background, household and monthly income. This model may inform and discern future interventions in refugees following trauma exposure with different features.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".