MGMaria Gilles

Maria Gilles

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Maria Gilles has a total of 271 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Momentary Depression Severity Prediction in Patients With Acute Depression Who Undergo Sleep Deprivation Therapy: Speech-Based Machine Learning Approach

    by Lisa-Marie Hartnagel, Daniel Emden, Jerome C Foo, Fabian Streit, Stephanie H Witt, Josef Frank, Matthias F Limberger, Sara E Schmitz, Maria Gilles, Marcella Rietschel, et al.

    Background: Mobile devices for remote monitoring are inevitable tools to support treatment and patient care, especially in recurrent diseases such as major depressive disorder. The aim of this study was to learn if machine learning (ML) models based on longitudinal speech data are helpful in predicting momentary depression severity. Data analyses were based on a dataset including 30 inpatients during an acute depressive episode receiving sleep deprivation therapy in stationary care, an intervention inducing a rapid change in depressive symptoms in a relatively short period of time. Using an ambulatory assessment approach, we captured speech samples and assessed concomitant depression severity via self-report questionnaire over the course of 3 weeks (before, during, and after therapy). We extracted 89 speech features from the speech samples using the Extended Geneva Minimalistic Acoustic Parameter Set from the Open-Source Speech and Music Interpretation by Large-Space Extraction (audEERING) toolkit and the additional parameter speech rate. Objective: We aimed to understand if a multiparameter ML approach would significantly improve the prediction compared to previous statistical analyses, and, in addition, which mechanism for splitting training and test data was most successful, especially focusing on the idea of personalized prediction. Methods: To do so, we trained and evaluated a set of >500 ML pipelines including random forest, linear regression, support vector regression, and Extreme Gradient Boosting regression models and tested them on 5 different train-test split scenarios: a group 5-fold nested cross-validation at the subject level, a leave-one-subject-out approach, a chronological split, an odd-even split, and a random split. Results: In the 5-fold cross-validation, the leave-one-subject-out, and the chronological split approaches, none of the models were statistically different from random chance. The other two approaches produced significant results for at least one of the models tested, with similar performance. In total, the superior model was an Extreme Gradient Boosting in the odd-even split approach (R²=0.339, mean absolute error=0.38; both P<.001), indicating that 33.9% of the variance in depression severity could be predicted by the speech features. Conclusions: Overall, our analyses highlight that ML fails to predict depression scores of unseen patients, but prediction performance increased strongly compared to our previous analyses with multilevel models. We conclude that future personalized ML models might improve prediction performance even more, leading to better patient management and care.


  • Open Access

    Genome-wide association study of borderline personality disorder identifies 11 loci and highlights shared risk with mental and somatic disorders

    by Fabian Streit, Swapnil Awasthi, Alisha Sm Hall, Alice Braun, Maria Niarchou, Eirini Marouli, Oladapo Babajide, Josef Frank, Lea Zillich, Carolin M Callies, et al.

    We conducted the largest genome-wide meta-analysis of borderline personality disorder (BPD) to date, with a discovery sample of 12,339 cases and 1,041,717 controls, and a replication study of 685 cases and 107,750 controls (all participants of European ancestry). We identified 11 independent associated genomic loci, and nine risk genes in the gene-based analysis. We observed a single-nucleotide polymorphism (SNP) heritability of 17.3% and derived polygenic scores (PGS) predicted 4.6% of the phenotypic variance in BPD on the liability scale. BPD showed the strongest positive genetic correlations with GWAS of posttraumatic stress disorder, depression, attention deficit hyperactivity disorder, antisocial behavior, and measures of suicide and self-harm. Phenome-wide association analyses using BPD-PGS confirmed these associations and additionally revealed associations with general medical conditions including obstructive pulmonary disease and diabetes. The present analyses highlight BPD as a polygenic disorder, with the genetic risk showing substantial overlap with psychiatric and physical health conditions.


  • Open Access

    Stress in pregnancy - Implications for fetal BDNF in amniotic fluid at birth

    by Eva Kathrin Lamadé, Bruno Pedraz-Petrozzi, Ole Lindner, Pascal Meininger, Antonia Pisters, Maria Gilles, Stephanie H. Witt, Marcella Rietschel, Helene Dukal, Fabian Schunk, et al.


  • Open Access

    Lithium treatment for affective disorders: Exploring the potential of salivary therapeutic monitoring

    by Maja P. Völker, Lea Sirignano, Helene Dukal, Alexander Schwesinger, Peter Findeisen, Fabian Schummer, Nils Hummel, Juliana Bresele, Michael Schneider, Joachim Behr, et al.


  • Stress during pregnancy and fetal serum BDNF in cord blood at birth

    by Eva Kathrin Lamadé, Bruno Pedraz-Petrozzi, Ole Lindner, Pascal Meininger, Michaela Coenen, Stephanie H. Witt, Marcella Rietschel, Helene Dukal, Maria Gilles, Stefan A. Wudy, et al.


  • Open Access

    Speech Features as Predictors of Momentary Depression Severity in Patients With Depressive Disorder Undergoing Sleep Deprivation Therapy: Ambulatory Assessment Pilot Study

    by Lisa-Marie Wadle, Ulrich W Ebner-Priemer, Jerome C Foo, Yoshiharu Yamamoto, Fabian Streit, Stephanie H Witt, Josef Frank, Lea Zillich, Matthias F Limberger, Ayimnisagul Ablimit, et al.

    Background: The use of mobile devices to continuously monitor objectively extracted parameters of depressive symptomatology is seen as an important step in the understanding and prevention of upcoming depressive episodes. Speech features such as pitch variability, speech pauses, and speech rate are promising indicators, but empirical evidence is limited, given the variability of study designs. Objective: Previous research studies have found different speech patterns when comparing single speech recordings between patients and healthy controls, but only a few studies have used repeated assessments to compare depressive and nondepressive episodes within the same patient. To our knowledge, no study has used a series of measurements within patients with depression (eg, intensive longitudinal data) to model the dynamic ebb and flow of subjectively reported depression and concomitant speech samples. However, such data are indispensable for detecting and ultimately preventing upcoming episodes. Methods: In this study, we captured voice samples and momentary affect ratings over the course of 3 weeks in a sample of patients (N=30) with an acute depressive episode receiving stationary care. Patients underwent sleep deprivation therapy, a chronotherapeutic intervention that can rapidly improve depression symptomatology. We hypothesized that within-person variability in depressive and affective momentary states would be reflected in the following 3 speech features: pitch variability, speech pauses, and speech rate. We parametrized them using the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) from open-source Speech and Music Interpretation by Large-Space Extraction (openSMILE; audEERING GmbH) and extracted them from a transcript. We analyzed the speech features along with self-reported momentary affect ratings, using multilevel linear regression analysis. We analyzed an average of 32 (SD 19.83) assessments per patient. Results: Analyses revealed that pitch variability, speech pauses, and speech rate were associated with depression severity, positive affect, valence, and energetic arousal; furthermore, speech pauses and speech rate were associated with negative affect, and speech pauses were additionally associated with calmness. Specifically, pitch variability was negatively associated with improved momentary states (ie, lower pitch variability was linked to lower depression severity as well as higher positive affect, valence, and energetic arousal). Speech pauses were negatively associated with improved momentary states, whereas speech rate was positively associated with improved momentary states. Conclusions: Pitch variability, speech pauses, and speech rate are promising features for the development of clinical prediction technologies to improve patient care as well as timely diagnosis and monitoring of treatment response. Our research is a step forward on the path to developing an automated depression monitoring system, facilitating individually tailored treatments and increased patient empowerment.


  • Open Access

    Speech Features as Predictors of Momentary Depression Severity in Patients With Depressive Disorder Undergoing Sleep Deprivation Therapy: Ambulatory Assessment Pilot Study (Preprint)

    by Lisa-Marie Wadle, Ulrich W Ebner-Priemer, Jerome C Foo, Yoshiharu Yamamoto, Fabian Streit, Stephanie H Witt, Josef Frank, Lea Zillich, Matthias F Limberger, Ayimnisagul Ablimit, et al.

    BACKGROUND The use of mobile devices to continuously monitor objectively extracted parameters of depressive symptomatology is seen as an important step in the understanding and prevention of upcoming depressive episodes. Speech features such as pitch variability, speech pauses, and speech rate are promising indicators, but empirical evidence is limited, given the variability of study designs. OBJECTIVE Previous research studies have found different speech patterns when comparing single speech recordings between patients and healthy controls, but only a few studies have used repeated assessments to compare depressive and nondepressive episodes within the same patient. To our knowledge, no study has used a series of measurements within patients with depression (eg, intensive longitudinal data) to model the dynamic ebb and flow of subjectively reported depression and concomitant speech samples. However, such data are indispensable for detecting and ultimately preventing upcoming episodes. METHODS In this study, we captured voice samples and momentary affect ratings over the course of 3 weeks in a sample of patients (N=30) with an acute depressive episode receiving stationary care. Patients underwent sleep deprivation therapy, a chronotherapeutic intervention that can rapidly improve depression symptomatology. We hypothesized that within-person variability in depressive and affective momentary states would be reflected in the following 3 speech features: pitch variability, speech pauses, and speech rate. We parametrized them using the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) from open-source Speech and Music Interpretation by Large-Space Extraction (openSMILE; audEERING GmbH) and extracted them from a transcript. We analyzed the speech features along with self-reported momentary affect ratings, using multilevel linear regression analysis. We analyzed an average of 32 (SD 19.83) assessments per patient. RESULTS Analyses revealed that pitch variability, speech pauses, and speech rate were associated with depression severity, positive affect, valence, and energetic arousal; furthermore, speech pauses and speech rate were associated with negative affect, and speech pauses were additionally associated with calmness. Specifically, pitch variability was negatively associated with improved momentary states (ie, lower pitch variability was linked to lower depression severity as well as higher positive affect, valence, and energetic arousal). Speech pauses were negatively associated with improved momentary states, whereas speech rate was positively associated with improved momentary states. CONCLUSIONS Pitch variability, speech pauses, and speech rate are promising features for the development of clinical prediction technologies to improve patient care as well as timely diagnosis and monitoring of treatment response. Our research is a step forward on the path to developing an automated depression monitoring system, facilitating individually tailored treatments and increased patient empowerment.

  • Open Access

    Effects of left anodal transcranial direct current stimulation on hypothalamic–pituitary–adrenal axis activity in depression: a randomized controlled pilot trial

    by Bruno Pedraz-Petrozzi, Helena Sardinha, Maria Gilles, Michael Deuschle

    The main objective of this study was to evaluate the effect of left anodal transcranial direct current stimulation (tDCS) on hypothalamic–pituitary–adrenal axis (HPAA) activity in individuals with depression. We conducted a 3-week, randomized, triple-blind pilot trial with 47 participants (dropout rate: 14.89%) randomly assigned to either the tDCS or control group (sham stimulation). Salivary cortisol was used as an HPAA activity marker since cortisol is the effector hormone of the HPAA. The primary outcome was the effect of tDCS on the diurnal cortisol pattern (DCP and area under the curve with respect to ground -AUCg-). Secondary outcomes included tDCS effects on cortisol awakening response (CAR) and cortisol decline (CD), as well as the variation of cortisol concentrations between the initiation of tDCS and 2 weeks later. Intention-to-treat and per-protocol analyses were conducted. Our primary outcome showed an absent effect of tDCS on DCP and AUCg. Additionally, tDCS had an absent effect on CAR, CD, and cortisol concentration variation before-after stimulation. Our pilot study suggests that anodal tDCS showed an absent effect on HPAA activity in individuals with depression. More studies are needed to confirm these findings.


  • Open Access

    Effect of left anodal transcranial direct current stimulation on hypothalamic-pituitary-adrenal axis (HPAA) activity in patients with depressive episodes: a randomized, triple-blind, pilot trial

    by Bruno Pedraz-Petrozzi, Helena Sardinha, Maria Gilles, Michael Deuschle

    Background This study's main aim was to evaluate the effect of left anodal transcranial direct current stimulation (tDCS) on hypothalamic-pituitary-adrenal axis (HPAA) activity in participants with depression. As an additional exploratory objective, we aimed to find any relationship between baseline morning cortisol concentrations, family history of depression, and somatic symptoms. Materials and Methods A 3-week, randomized, triple-blind, pilot trial was carried out. Participants (n = 47, drop-out: 14.89%) were allocated randomly to one of two groups: tDCS and control group (sham stimulation). Since the effector hormone of the HPAA is cortisol, salivary cortisol was used as an HPAA activity marker. The primary outcome was the effect of tDCS on the diurnal cortisol pattern (DCP). Secondary outcomes were tDCS effects on cortisol awakening response (CAR) and maximal cortisol decline (MCD), as well as the variation of cortisol concentrations between the initiation of tDCS and 2 weeks later. Intention-to-treat and per-protocol analyses were carried out. Results Regarding our primary outcome, we found no significant effectof tDCS on the interaction group * time * daytime. Concerning our secondary outcomes, tDCS had no significant effects on CAR, MCD or cortisol concentration variation between the initiation of tDCS and 2 weeks later in the tDCS group when compared with the sham stimulation group. Finally, an exploratory analysis found a significant relationship between morning cortisol, family history of depression, and somatic symptoms. Conclusions Our main results indicate that anodal tDCS did not affect HPAA activity in depression. More studies are needed to confirm these findings.

  • W32. INVESTIGATING ANTIDEPRESSANT RESPONSE: COMPREHENSIVE PHENOTYPING IN PATIENTS UNDERGOING SLEEP DEPRIVATION THERAPY

    by Lara Fetscher, Lea Sirignano, Hiroki Takeuchi, Jinhyuk Kim, Stephanie Witt, Fabian Streit, Josef Frank, Lea Zillich, Ulrich Ebner-Priemer, Yoshiharu Yamamoto, et al.