Dataset Information

Machine learning methods to predict child posttraumatic stress: a proof of concept study.

ABSTRACT:

Background

The care of traumatized children would benefit significantly from accurate predictive models for Posttraumatic Stress Disorder (PTSD), using information available around the time of trauma. Machine Learning (ML) computational methods have yielded strong results in recent applications across many diseases and data types, yet they have not been previously applied to childhood PTSD. Since these methods have not been applied to this complex and debilitating disorder, there is a great deal that remains to be learned about their application. The first step is to prove the concept: Can ML methods - as applied in other fields - produce predictive classification models for childhood PTSD? Additionally, we seek to determine if specific variables can be identified - from the aforementioned predictive classification models - with putative causal relations to PTSD.

Methods

ML predictive classification methods - with causal discovery feature selection - were applied to a data set of 163 children hospitalized with an injury and PTSD was determined three months after hospital discharge. At the time of hospitalization, 105 risk factor variables were collected spanning a range of biopsychosocial domains.

Results

Seven percent of subjects had a high level of PTSD symptoms. A predictive classification model was discovered with significant predictive accuracy. A predictive model constructed based on subsets of potentially causally relevant features achieves similar predictivity compared to the best predictive model constructed with all variables. Causal Discovery feature selection methods identified 58 variables of which 10 were identified as most stable.

Conclusions

In this first proof-of-concept application of ML methods to predict childhood Posttraumatic Stress we were able to determine both predictive classification models for childhood PTSD and identify several causal variables. This set of techniques has great potential for enhancing the methodological toolkit in the field and future studies should seek to replicate, refine, and extend the results produced in this study.

SUBMITTER: Saxe GN

PROVIDER: S-EPMC5502325 | biostudies-literature | 2017 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning methods to predict child posttraumatic stress: a proof of concept study.

Saxe Glenn N GN Ma Sisi S Ren Jiwen J Aliferis Constantin C

BMC psychiatry 20170710 1

<h4>Background</h4>The care of traumatized children would benefit significantly from accurate predictive models for Posttraumatic Stress Disorder (PTSD), using information available around the time of trauma. Machine Learning (ML) computational methods have yielded strong results in recent applications across many diseases and data types, yet they have not been previously applied to childhood PTSD. Since these methods have not been applied to this complex and debilitating disorder, there is a gr ...[more]

PMID: 28689495

Similar Datasets

Project description:OBJECTIVE:We have previously found that acute psychological stress may affect mitochondria and trigger an increase in serum mitochondrial DNA, known as circulating cell-free mtDNA (ccf-mtDNA). Similar to other stress reactivity measures, there are substantial unexplained inter-individual differences in the magnitude of ccf-mtDNA reactivity, as well as within-person differences across different occasions of testing. Here, we sought to identify psychological and physiological predictors of ccf-mtDNA reactivity using machine learning-based multivariate classifiers. METHOD:We used data from serum ccf-mtDNA concentration measured pre- and post-stress in 46 healthy midlife adults tested on two separate occasions. To identify variables predicting the magnitude of ccf-mtDNA reactivity, two multivariate classification models, partial least-squares discriminant analysis (PLS-DA) and random forest (RF), were trained to discriminate between high and low ccf-mtDNA responders. Potential predictors used in the models included state variables such as physiological measures and affective states, and trait variables such as sex and personality measures. Variables identified across both models were considered to be predictors of ccf-mtDNA reactivity and selected for downstream analyses. RESULTS:Identified predictors were significantly enriched for state over trait measures (X2?=?7.03; p?=?0.008) and for physiological over psychological measures (X2?=?4.36; p?=?0.04). High responders were more likely to be male (X2?=?26.95; p?<?0.001) and differed from low-responders on baseline cardiovascular and autonomic measures, and on stress-induced reduction in fatigue (Cohen's d?=?0.38-0.73). These group-level findings also accurately accounted for within-person differences in 90% of cases. CONCLUSION:These results suggest that acute cardiovascular and psychological indices, rather than stable individual traits, predict stress-induced ccf-mtDNA reactivity. This work provides a proof-of-concept that machine learning approaches can be used to explore determinants of inter-individual and within-person differences in stress psychophysiology.

Project description:IntroductionDifficulty swallowing (dysphagia) occurs frequently in patients with neurological disorders and can lead to aspiration, choking, and malnutrition. Dysphagia is typically diagnosed using costly, invasive imaging procedures or subjective, qualitative bedside examinations. Wearable sensors are a promising alternative to noninvasively and objectively measure physiological signals relevant to swallowing. An ongoing challenge with this approach is consolidating these complex signals into sensitive, clinically meaningful metrics of swallowing performance. To address this gap, we propose 2 novel, digital monitoring tools to evaluate swallows using wearable sensor data and machine learning.MethodsBiometric swallowing and respiration signals from wearable, mechano-acoustic sensors were compared between patients with poststroke dysphagia and nondysphagic controls while swallowing foods and liquids of different consistencies, in accordance with the Mann Assessment of Swallowing Ability (MASA). Two machine learning approaches were developed to (1) classify the severity of impairment for each swallow, with model confidence ratings for transparent clinical decision support, and (2) compute a similarity measure of each swallow to nondysphagic performance. Task-specific models were trained using swallow kinematics and respiratory features from 505 swallows (321 from patients and 184 from controls).ResultsThese models provide sensitive metrics to gauge impairment on a per-swallow basis. Both approaches demonstrate intrasubject swallow variability and patient-specific changes which were not captured by the MASA alone. Sensor measures encoding respiratory-swallow coordination were important features relating to dysphagia presence and severity. Puree swallows exhibited greater differences from controls than saliva swallows or liquid sips (p < 0.037).DiscussionDeveloping interpretable tools is critical to optimize the clinical utility of novel, sensor-based measurement techniques. The proof-of-concept models proposed here provide concrete, communicable evidence to track dysphagia recovery over time. With refined training schemes and real-world validation, these tools can be deployed to automatically measure and monitor swallowing in the clinic and community for patients across the impairment spectrum.

Project description:BackgroundDepression during the postnatal year is prevalent in mothers (17%) and fathers (9%), and suicide is the leading cause of maternal death in this period. Lifelong costs and consequences of untreated postnatal depression (PND) are high due to impacts on infants as well as parents. We aimed to improve access to PND treatment using digital screening. We developed a smartphone app (ClinTouch DAWN-P) that allows parents to monitor their mood daily with the Edinburgh Postnatal Depression Scale (EPDS), uploading responses in real-time to a secure server. We evaluated the app's feasibility, acceptability, validity and safety in a proof-of-concept study.MethodsPregnant women (≥ 36 weeks gestation) and partners were recruited from antenatal services and invited to complete daily EPDS assessments via the ClinTouch DAWN-P app until 6 weeks postpartum. Participants completed standard paper-based EPDS at two time points for validity comparisons. We examined app acceptability and usability at 6 weeks postpartum with qualitative interviews, examined using framework analysis, and the abridged Mobile App Rating Scale (convergent mixed methods design).ResultsMost (96%) eligible pregnant women approached were keen to try the app. Participating mothers (n = 15) and partners/fathers (n = 8) found the app easy to use, and 91% continued to use it for the full study period. Overall, 67% of daily app-based assessments were completed, with a history of depression predicting lower app usage. Participants suggested modifications to the app and its deployment to improve usability (e.g., extending the response window and including feedback and parenting advice). The validity of app-based responses was confirmed by high agreement with standard EPDS. App-based and paper-based ratings showed perfect agreement in identifying cases of likely PND. There were no serious adverse events relating to app use.ConclusionsDigital PND screening appears feasible, acceptable, valid and safe. It also benefits from being remotely delivered: we enrolled all participants remotely during the first COVID-19 lockdown. Use of digital screening could address known shortcomings of conventional health visitor-delivered screening such as limited staff time, parental unwillingness to disclose difficulties to a professional, lack of partner/father screening, and language barriers.Trial registrationThe study was prospectively registered (Clinicaltrials.gov: NCT04279093 ).

Dataset Information

Machine learning methods to predict child posttraumatic stress: a proof of concept study.

Background

Methods

Results

Conclusions

Publications

Machine learning methods to predict child posttraumatic stress: a proof of concept study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets