Sebastian Mildiner Moraga
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sebastian Mildiner Moraga has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Emmeke Aarts
Department of Methodology and Statistics, Utrecht University, Utrecht, Netherlands
7 shared publications - Fionneke Marijke Bos
Department of Psychiatry, Rob Giel Research Center, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
2 shared publications Gino Coudé
Institut des Sciences Cognitives Marc Jeannerod CNRS UMR 5229 Bron France
2 shared publications- James John Bonaiuto
Decision, Action, and Neural Computation (DANC) team, Institut des Sciences Cognitives Marc Jeannerod, Lyon, France
2 shared publications - Marco Bimbi
Institut des Sciences Cognitives Marc Jeannerod CNRS UMR 5229 Bron France
2 shared publications - Pier Francesco Ferrari
Department of Medicine and Surgery, University of Parma
2 shared publications
Latest Publications
- Open Access
- 7 July 2026
- Published by Oxford University Press (OUP) in JAMIA Open
- Vol. 9 (4)
Real-time prediction of atrial fibrillation in intensive care unit: a meta-learning approach
Objective: Atrial fibrillation (AF) is a common arrhythmia affecting a large fraction of patients in intensive care units (ICUs). Predicting patients at risk of AF in the ICU is a challenging task and is not commonly practiced but could have clinical implications considering that AF is a proxy for poorer outcomes. Our goal is to develop a real-time AF prediction model using ICU numerical data to improve alarm quality, helping clinicians to identify at-risk patients and intervene before AF onset, thereby potentially improving clinical outcomes. Methods: We employed AmsterdamUMCdb, Europe’s first openly accessible ICU dataset. The dataset includes static features, including demographics, as well as dynamic bedside monitoring data, like blood pressure and respiratory rate, along with detailed records of medication and fluid administration. To enhance generalizability across diverse ICU patients, we trained a long short-term memory (LSTM) model combined with a Model-Agnostic Meta-Learning (MAML) approach. Model performance was tested on an imbalanced test set, reflective of the real-world ratio of AF to non-AF patients. Direct external validation was performed using the MIMIC-IV database to test generalizability across different clinical settings. Results: The LSTM-MAML model achieved an AUC of 0.92, accuracy of 0.89, and precision of 0.29 on the internal validation set. In external validation with MIMIC-IV, it showed near-equivalent performance with an AUC of 0.89, accuracy of 0.85, and precision of 0.18. Conclusions: The real-time prediction model demonstrated predictive value for AF and has potential for future clinical benefits. However, for clinical implementation, further refinement is necessary to improve its performance in identifying patients at risk for AF.
- 7 July 2026
- Published by Oxford University Press (OUP) in JAMIA Open
- Vol. 9 (4)
Open AccessReal-time prediction of atrial fibrillation in intensive care unit: a meta-learning approach
Objective: Atrial fibrillation (AF) is a common arrhythmia affecting a large fraction of patients in intensive care units (ICUs). Predicting patients at risk of AF in the ICU is a challenging task and is not commonly practiced but could have clinical implications considering that AF is a proxy for poorer outcomes. Our goal is to develop a real-time AF prediction model using ICU numerical data to improve alarm quality, helping clinicians to identify at-risk patients and intervene before AF onset, thereby potentially improving clinical outcomes. Methods: We employed AmsterdamUMCdb, Europe’s first openly accessible ICU dataset. The dataset includes static features, including demographics, as well as dynamic bedside monitoring data, like blood pressure and respiratory rate, along with detailed records of medication and fluid administration. To enhance generalizability across diverse ICU patients, we trained a long short-term memory (LSTM) model combined with a Model-Agnostic Meta-Learning (MAML) approach. Model performance was tested on an imbalanced test set, reflective of the real-world ratio of AF to non-AF patients. Direct external validation was performed using the MIMIC-IV database to test generalizability across different clinical settings. Results: The LSTM-MAML model achieved an AUC of 0.92, accuracy of 0.89, and precision of 0.29 on the internal validation set. In external validation with MIMIC-IV, it showed near-equivalent performance with an AUC of 0.89, accuracy of 0.85, and precision of 0.18. Conclusions: The real-time prediction model demonstrated predictive value for AF and has potential for future clinical benefits. However, for clinical implementation, further refinement is necessary to improve its performance in identifying patients at risk for AF.
- 1 August 2024
- Published by American Psychological Association (APA) in Journal of Psychopathology and Clinical Science
- Vol. 133 (6) , 456-468
Evidence for mood instability in patients with bipolar disorder: Applying multilevel hidden Markov modeling to intensive longitudinal ecological momentary assessment data.
Bipolar disorder (BD) is a chronic psychiatric condition characterized by large episodic changes in mood and energy. Recently, BD has been proposed to be conceptualized as chronic cyclical mood instability, as opposed to the traditional view of alternating discrete episodes with stable periods in-between. Recognizing this mood instability may improve care and call for high-frequency measures coupled with advanced statistical models. To uncover empirically derived mood states, a multilevel hidden Markov model (HMM) was applied to 4-month ecological momentary assessment data in 20 patients with BD, yielding ∼9,820 assessments in total. Ecological momentary assessment data comprised self-report questionnaires (5 × daily) measuring manic and depressive constructs. Manic and depressive symptoms were also assessed weekly using the Altman Self-Rating Mania Scale and the Quick Inventory for Depressive Symptomatology Self-Report. Alignment between HMM-uncovered momentary mood states and weekly questionnaires was assessed with a multilevel linear model. HMM uncovered four mood states: neutral, elevated, mixed, and lowered, which aligned with weekly symptom scores. On average, patients remained < 25 hr in one state. In almost half of the patients, mood instability was observed. Switching between mood states, three patterns were identified: patients switching predominantly between (a) neutral and lowered states, (b) neutral and elevated states, and (c) mixed, elevated, and lowered states. In all, elevated and lowered mood states were interspersed by mixed states. The results indicate that chronic mood instability is a key feature of BD, even in "relatively" euthymic periods. This should be considered in theoretical and clinical conceptualizations of the disorder. (PsycInfo Database Record (c) 2024 APA, all rights reserved).
- 1 August 2024
- Published by American Psychological Association (APA) in Journal of Psychopathology and Clinical Science
- Vol. 133 (6) , 456-468
Evidence for mood instability in patients with bipolar disorder: Applying multilevel hidden Markov modeling to intensive longitudinal ecological momentary assessment data.
Bipolar disorder (BD) is a chronic psychiatric condition characterized by large episodic changes in mood and energy. Recently, BD has been proposed to be conceptualized as chronic cyclical mood instability, as opposed to the traditional view of alternating discrete episodes with stable periods in-between. Recognizing this mood instability may improve care and call for high-frequency measures coupled with advanced statistical models. To uncover empirically derived mood states, a multilevel hidden Markov model (HMM) was applied to 4-month ecological momentary assessment data in 20 patients with BD, yielding ∼9,820 assessments in total. Ecological momentary assessment data comprised self-report questionnaires (5 × daily) measuring manic and depressive constructs. Manic and depressive symptoms were also assessed weekly using the Altman Self-Rating Mania Scale and the Quick Inventory for Depressive Symptomatology Self-Report. Alignment between HMM-uncovered momentary mood states and weekly questionnaires was assessed with a multilevel linear model. HMM uncovered four mood states: neutral, elevated, mixed, and lowered, which aligned with weekly symptom scores. On average, patients remained < 25 hr in one state. In almost half of the patients, mood instability was observed. Switching between mood states, three patterns were identified: patients switching predominantly between (a) neutral and lowered states, (b) neutral and elevated states, and (c) mixed, elevated, and lowered states. In all, elevated and lowered mood states were interspersed by mixed states. The results indicate that chronic mood instability is a key feature of BD, even in "relatively" euthymic periods. This should be considered in theoretical and clinical conceptualizations of the disorder. (PsycInfo Database Record (c) 2024 APA, all rights reserved).
- Open Access
- 29 June 2023
- Published by Wiley in European Journal of Neuroscience
- Vol. 58 (3) , 2787-2806
Bayesian multilevel hidden Markov models identify stable state dynamics in longitudinal recordings from macaque primary motor cortex
Neural populations, rather than single neurons, may be the fundamental unit of cortical computation. Analysing chronically recorded neural population activity is challenging not only because of the high dimensionality of activity but also because of changes in the signal that may or may not be due to neural plasticity. Hidden Markov models (HMMs) are a promising technique for analysing such data in terms of discrete latent states, but previous approaches have not considered the statistical properties of neural spiking data, have not been adaptable to longitudinal data, or have not modelled condition‐specific differences. We present a multilevel Bayesian HMM addresses these shortcomings by incorporating multivariate Poisson log‐normal emission probability distributions, multilevel parameter estimation and trial‐specific condition covariates. We applied this framework to multi‐unit neural spiking data recorded using chronically implanted multi‐electrode arrays from macaque primary motor cortex during a cued reaching, grasping and placing task. We show that, in line with previous work, the model identifies latent neural population states which are tightly linked to behavioural events, despite the model being trained without any information about event timing. The association between these states and corresponding behaviour is consistent across multiple days of recording. Notably, this consistency is not observed in the case of a single‐level HMM, which fails to generalise across distinct recording sessions. The utility and stability of this approach is demonstrated using a previously learned task, but this multilevel Bayesian HMM framework would be especially suited for future studies of long‐term plasticity in neural populations.
- 29 June 2023
- Published by Wiley in European Journal of Neuroscience
- Vol. 58 (3) , 2787-2806
Open AccessBayesian multilevel hidden Markov models identify stable state dynamics in longitudinal recordings from macaque primary motor cortex
Neural populations, rather than single neurons, may be the fundamental unit of cortical computation. Analysing chronically recorded neural population activity is challenging not only because of the high dimensionality of activity but also because of changes in the signal that may or may not be due to neural plasticity. Hidden Markov models (HMMs) are a promising technique for analysing such data in terms of discrete latent states, but previous approaches have not considered the statistical properties of neural spiking data, have not been adaptable to longitudinal data, or have not modelled condition‐specific differences. We present a multilevel Bayesian HMM addresses these shortcomings by incorporating multivariate Poisson log‐normal emission probability distributions, multilevel parameter estimation and trial‐specific condition covariates. We applied this framework to multi‐unit neural spiking data recorded using chronically implanted multi‐electrode arrays from macaque primary motor cortex during a cued reaching, grasping and placing task. We show that, in line with previous work, the model identifies latent neural population states which are tightly linked to behavioural events, despite the model being trained without any information about event timing. The association between these states and corresponding behaviour is consistent across multiple days of recording. Notably, this consistency is not observed in the case of a single‐level HMM, which fails to generalise across distinct recording sessions. The utility and stability of this approach is demonstrated using a previously learned task, but this multilevel Bayesian HMM framework would be especially suited for future studies of long‐term plasticity in neural populations.
- Open Access
- 17 May 2023
- Published by Taylor & Francis in Multivariate Behavioral Research
- Vol. 59 (1) , 17-45
Go Multivariate: Recommendations on Bayesian Multilevel Hidden Markov Models with Categorical Data
The multilevel hidden Markov model (MHMM) is a promising method to investigate intense longitudinal data obtained within the social and behavioral sciences. The MHMM quantifies information on the latent dynamics of behavior over time. In addition, heterogeneity between individuals is accommodated with the inclusion of individual-specific random effects, facilitating the study of individual differences in dynamics. However, the performance of the MHMM has not been sufficiently explored. We performed an extensive simulation to assess the effect of the number of dependent variables (1-8), number of individuals (5-90), and number of observations per individual (100-1600) on the estimation performance of a Bayesian MHMM with categorical data including various levels of state distinctiveness and separation. We found that using multivariate data generally alleviates the sample size needed and improves the stability of the results. Moreover, including variables only consisting of random noise was generally not detrimental to model performance. Regarding the estimation of group-level parameters, the number of individuals and observations largely compensate for each other. However, only the former drives the estimation of between-individual variability. We conclude with guidelines on the sample size necessary based on the level of state distinctiveness and separation and study objectives of the researcher.
- 17 May 2023
- Published by Taylor & Francis in Multivariate Behavioral Research
- Vol. 59 (1) , 17-45
Open AccessGo Multivariate: Recommendations on Bayesian Multilevel Hidden Markov Models with Categorical Data
The multilevel hidden Markov model (MHMM) is a promising method to investigate intense longitudinal data obtained within the social and behavioral sciences. The MHMM quantifies information on the latent dynamics of behavior over time. In addition, heterogeneity between individuals is accommodated with the inclusion of individual-specific random effects, facilitating the study of individual differences in dynamics. However, the performance of the MHMM has not been sufficiently explored. We performed an extensive simulation to assess the effect of the number of dependent variables (1-8), number of individuals (5-90), and number of observations per individual (100-1600) on the estimation performance of a Bayesian MHMM with categorical data including various levels of state distinctiveness and separation. We found that using multivariate data generally alleviates the sample size needed and improves the stability of the results. Moreover, including variables only consisting of random noise was generally not detrimental to model performance. Regarding the estimation of group-level parameters, the number of individuals and observations largely compensate for each other. However, only the former drives the estimation of between-individual variability. We conclude with guidelines on the sample size necessary based on the level of state distinctiveness and separation and study objectives of the researcher.
- Open Access
- 31 January 2023
- Published by Center for Open Science in PsyArXiv
Evidence for mood instability in patients with bipolar disorder: Applying multilevel hidden Markov modelling to intensive longitudinal ecological momentary assessment data
Background. Bipolar disorder (BD) is a chronic psychiatric condition characterized by large episodic changes in mood and energy. Recently, BD has been proposed to be conceptualized as chronic cyclical mood instability, as opposed to the traditional view of alternating discrete episodes with stable periods in-between. Recognizing this mood instability may improve care and calls for high-frequency measures coupled with advanced statistical models. Methods. To uncover empirically derived mood states, a multilevel hidden Markov model (HMM) was applied to 4-month ecological momentary assessment (EMA) data in twenty patients with BD, yielding ~9.820 assessments in total. EMA-data comprised self-report questionnaires (5x daily) measuring manic and depressive constructs. Manic and depressive symptoms were also assessed weekly using the Altman Self-Rating Mania Scale and the Quick Inventory for Depressive Symptomatology Self-Report. Alignment between HMM-uncovered momentary mood states and weekly questionnaires was assessed with a multilevel linear model.Results. HMM uncovered four mood states: neutral, elevated, mixed, and lowered, which aligned with weekly symptom scores. On average, patients remained <25h in one state. In almost half of the patients, mood instability was observed. Switching between mood states, three patterns were identified: patients switching predominantly between 1) neutral and lowered states, 2) neutral and elevated states, 3) mixed, elevated, and lowered states. In all, elevated and lowered mood states were interspersed by mixed states.Conclusions. The results indicate that chronic mood instability is a key feature of BD, even in “relatively” euthymic periods. This should be considered in theoretical and clinical conceptualizations of the disorder.
- 31 January 2023
- Published by Center for Open Science in PsyArXiv
Open AccessEvidence for mood instability in patients with bipolar disorder: Applying multilevel hidden Markov modelling to intensive longitudinal ecological momentary assessment data
Background. Bipolar disorder (BD) is a chronic psychiatric condition characterized by large episodic changes in mood and energy. Recently, BD has been proposed to be conceptualized as chronic cyclical mood instability, as opposed to the traditional view of alternating discrete episodes with stable periods in-between. Recognizing this mood instability may improve care and calls for high-frequency measures coupled with advanced statistical models. Methods. To uncover empirically derived mood states, a multilevel hidden Markov model (HMM) was applied to 4-month ecological momentary assessment (EMA) data in twenty patients with BD, yielding ~9.820 assessments in total. EMA-data comprised self-report questionnaires (5x daily) measuring manic and depressive constructs. Manic and depressive symptoms were also assessed weekly using the Altman Self-Rating Mania Scale and the Quick Inventory for Depressive Symptomatology Self-Report. Alignment between HMM-uncovered momentary mood states and weekly questionnaires was assessed with a multilevel linear model.Results. HMM uncovered four mood states: neutral, elevated, mixed, and lowered, which aligned with weekly symptom scores. On average, patients remained <25h in one state. In almost half of the patients, mood instability was observed. Switching between mood states, three patterns were identified: patients switching predominantly between 1) neutral and lowered states, 2) neutral and elevated states, 3) mixed, elevated, and lowered states. In all, elevated and lowered mood states were interspersed by mixed states.Conclusions. The results indicate that chronic mood instability is a key feature of BD, even in “relatively” euthymic periods. This should be considered in theoretical and clinical conceptualizations of the disorder.
- Open Access
Bayesian multilevel hidden Markov models identify stable state dynamics in longitudinal recordings from macaque primary motor cortex
Neural populations, rather than single neurons, may be the fundamental unit of cortical computation. Analyzing chronically recorded neural population activity is challenging not only because of the high dimensionality of activity in many neurons, but also because of changes in the recorded signal that may or may not be due to neural plasticity. Hidden Markov models (HMMs) are a promising technique for analyzing such data in terms of discrete, latent states, but previous approaches have either not considered the statistical properties of neural spiking data, have not been adaptable to longitudinal data, or have not modeled condition specific differences. We present a multilevel Bayesian HMM which addresses these shortcomings by incorporating multivariate Poisson log-normal emission probability distributions, multilevel parameter estimation, and trial-specific condition covariates. We applied this framework to multi-unit neural spiking data recorded using chronically implanted multi-electrode arrays from macaque primary motor cortex during a cued reaching, grasping, and placing task. We show that the model identifies latent neural population states which are tightly linked to behavioral events, despite the model being trained without any information about event timing. We show that these events represent specific spatiotemporal patterns of neural population activity and that their relationship to behavior is consistent over days of recording. The utility and stability of this approach is demonstrated using a previously learned task, but this multilevel Bayesian HMM framework would be especially suited for future studies of long-term plasticity in neural populations.
Open AccessBayesian multilevel hidden Markov models identify stable state dynamics in longitudinal recordings from macaque primary motor cortex
Neural populations, rather than single neurons, may be the fundamental unit of cortical computation. Analyzing chronically recorded neural population activity is challenging not only because of the high dimensionality of activity in many neurons, but also because of changes in the recorded signal that may or may not be due to neural plasticity. Hidden Markov models (HMMs) are a promising technique for analyzing such data in terms of discrete, latent states, but previous approaches have either not considered the statistical properties of neural spiking data, have not been adaptable to longitudinal data, or have not modeled condition specific differences. We present a multilevel Bayesian HMM which addresses these shortcomings by incorporating multivariate Poisson log-normal emission probability distributions, multilevel parameter estimation, and trial-specific condition covariates. We applied this framework to multi-unit neural spiking data recorded using chronically implanted multi-electrode arrays from macaque primary motor cortex during a cued reaching, grasping, and placing task. We show that the model identifies latent neural population states which are tightly linked to behavioral events, despite the model being trained without any information about event timing. We show that these events represent specific spatiotemporal patterns of neural population activity and that their relationship to behavior is consistent over days of recording. The utility and stability of this approach is demonstrated using a previously learned task, but this multilevel Bayesian HMM framework would be especially suited for future studies of long-term plasticity in neural populations.
- Open Access
Sample Size Considerations for Bayesian Multilevel Hidden Markov Models: A Simulation Study on Multivariate Continuous Data with highly overlapping Component Distributions based on Sleep Data
Spurred in part by the ever-growing number of sensors and web-based methods of collecting data, the use of Intensive Longitudinal Data (ILD) is becoming more common in the social and behavioural sciences. The ILD collected in this field are often hypothesised to be the result of latent states (e.g. behaviour, emotions), and the promise of ILD lies in its ability to capture the dynamics of these states as they unfold in time. In particular, by collecting data for multiple subjects, researchers can observe how such dynamics differ between subjects. The Bayesian Multilevel Hidden Markov Model (mHMM) is a relatively novel model that is suited to model the ILD of this kind while taking into account heterogeneity between subjects. While the mHMM has been applied in a variety of settings, large-scale studies that examine the required sample size for this model are lacking. In this paper, we address this research gap by conducting a simulation study to evaluate the effect of changing (1) the number of subjects, (2) the number of occasions, and (3) the between subjects variability on parameter estimates obtained by the mHMM. We frame this simulation study in the context of sleep research, which consists of multivariate continuous data that displays considerable overlap in the state dependent component distributions. In addition, we generate a set of baseline scenarios with more general data properties. Overall, the number of subjects has the largest effect on model performance. However, the number of occasions is important to adequately model latent state transitions. We discuss how the characteristics of the data influence parameter estimation and provide recommendations to researchers seeking to apply the mHMM to their own data.
Open AccessSample Size Considerations for Bayesian Multilevel Hidden Markov Models: A Simulation Study on Multivariate Continuous Data with highly overlapping Component Distributions based on Sleep Data
Spurred in part by the ever-growing number of sensors and web-based methods of collecting data, the use of Intensive Longitudinal Data (ILD) is becoming more common in the social and behavioural sciences. The ILD collected in this field are often hypothesised to be the result of latent states (e.g. behaviour, emotions), and the promise of ILD lies in its ability to capture the dynamics of these states as they unfold in time. In particular, by collecting data for multiple subjects, researchers can observe how such dynamics differ between subjects. The Bayesian Multilevel Hidden Markov Model (mHMM) is a relatively novel model that is suited to model the ILD of this kind while taking into account heterogeneity between subjects. While the mHMM has been applied in a variety of settings, large-scale studies that examine the required sample size for this model are lacking. In this paper, we address this research gap by conducting a simulation study to evaluate the effect of changing (1) the number of subjects, (2) the number of occasions, and (3) the between subjects variability on parameter estimates obtained by the mHMM. We frame this simulation study in the context of sleep research, which consists of multivariate continuous data that displays considerable overlap in the state dependent component distributions. In addition, we generate a set of baseline scenarios with more general data properties. Overall, the number of subjects has the largest effect on model performance. However, the number of occasions is important to adequately model latent state transitions. We discuss how the characteristics of the data influence parameter estimation and provide recommendations to researchers seeking to apply the mHMM to their own data.