ABSTRACT
Poor sleep quality in Autism Spectrum Disorder (ASD) individuals is linked to severe daytime behaviors. This study explores the relationship between a prior night's sleep structure and its predictive power for next-day behavior in ASD individuals. The motion was extracted using a low-cost near-infrared camera in a privacy-preserving way. Over two years, we recorded overnight data from 14 individuals, spanning over 2,000 nights, and tracked challenging daytime behaviors, including aggression, self-injury, and disruption. We developed an ensemble machine learning algorithm to predict next-day behavior in the morning and the afternoon. Our findings indicate that sleep quality is a more reliable predictor of morning behavior than afternoon behavior the next day. The proposed model attained an accuracy of 74% and a F1 score of 0.74 in target-sensitive tasks and 67% accuracy and 0.69 F1 score in target-insensitive tasks. For 7 of the 14, betterthan-chance balanced accuracy was obtained (p-value<0.05), with 3 showing significant trends (p-value<0.1). These results suggest off-body, privacy-preserving sleep monitoring as a viable method for predicting next-day adverse behavior in ASD individuals, with the potential for behavioral intervention and enhanced care in social and learning settings.
ABSTRACT
Objective.Cardiovascular diseases are a major cause of mortality globally, and electrocardiograms (ECGs) are crucial for diagnosing them. Traditionally, ECGs are stored in printed formats. However, these printouts, even when scanned, are incompatible with advanced ECG diagnosis software that require time-series data. Digitizing ECG images is vital for training machine learning models in ECG diagnosis, leveraging the extensive global archives collected over decades. Deep learning models for image processing are promising in this regard, although the lack of clinical ECG archives with reference time-series data is challenging. Data augmentation techniques using realistic generative data models provide a solution.Approach.We introduceECG-Image-Kit, an open-source toolbox for generating synthetic multi-lead ECG images with realistic artifacts from time-series data, aimed at automating the conversion of scanned ECG images to ECG data points. The tool synthesizes ECG images from real time-series data, applying distortions like text artifacts, wrinkles, and creases on a standard ECG paper background.Main results.As a case study, we used ECG-Image-Kit to create a dataset of 21 801 ECG images from the PhysioNet QT database. We developed and trained a combination of a traditional computer vision and deep neural network model on this dataset to convert synthetic images into time-series data for evaluation. We assessed digitization quality by calculating the signal-to-noise ratio and compared clinical parameters like QRS width, RR, and QT intervals recovered from this pipeline, with the ground truth extracted from ECG time-series. The results show that this deep learning pipeline accurately digitizes paper ECGs, maintaining clinical parameters, and highlights a generative approach to digitization.Significance.The toolbox has broad applications, including model development for ECG image digitization and classification. The toolbox currently supports data augmentation for the 2024 PhysioNet Challenge, focusing on digitizing and classifying paper ECG images.
Subject(s)
Deep Learning , Electrocardiography , Image Processing, Computer-Assisted , Image Processing, Computer-Assisted/methods , Humans , Signal Processing, Computer-Assisted , Artifacts , SoftwareABSTRACT
Research on automated mental health assessment tools has been growing in recent years, often aiming to address the subjectivity and bias that existed in the current clinical practice of the psychiatric evaluation process. Despite the substantial health and economic ramifications, the potential unfairness of those automated tools was understudied and required more attention. In this work, we systematically evaluated the fairness level in a multimodal remote mental health dataset and an assessment system, where we compared the fairness level in race, gender, education level, and age. Demographic parity ratio (DPR) and equalized odds ratio (EOR) of classifiers using different modalities were compared, along with the F1 scores in different demographic groups. Post-training classifier threshold optimization was employed to mitigate the unfairness. No statistically significant unfairness was found in the composition of the dataset. Varying degrees of unfairness were identified among modalities, with no single modality consistently demonstrating better fairness across all demographic variables. Post-training mitigation effectively improved both DPR and EOR metrics at the expense of a decrease in F1 scores. Addressing and mitigating unfairness in these automated tools are essential steps in fostering trust among clinicians, gaining deeper insights into their use cases, and facilitating their appropriate utilization.
ABSTRACT
BACKGROUND: Atrial fibrillation (AF) is often asymptomatic and thus under-observed. Given the high risks of stroke and heart failure among patients with AF, early prediction and effective management are crucial. Given the prevalence of obstructive sleep apnea among AF patients, electrocardiogram (ECG) analysis from polysomnography (PSG) offers a unique opportunity for early AF prediction. Our aim is to identify individuals at high risk of AF development from singlelead ECGs during standard PSG. METHODS: We analyzed 18,782 singlelead ECG recordings from 13,609 subjects undergoing PSG at the Massachusetts General Hospital sleep laboratory. AF presence was identified using ICD-9/10 codes. The dataset included 15,913 recordings without AF history and 2054 recordings from patients diagnosed with AF between one month to fifteen years post-PSG. Data were partitioned into training, validation, and test cohorts ensuring that individual patients remained exclusive to each cohort. The test set was held out during the training process. We employed two different methods for feature extraction to build a final model for AF prediction: Extraction of hand-crafted ECG features and a deep learning method. For extraction of ECG-hand-crafted features, recordings were split into 30-s windows, and those with a signal quality index (SQI) below 0.95 were discarded. From each remaining window, 150 features were extracted from the time, frequency, time-frequency domains, and phase-space reconstructions of the ECG. A compilation of 12 statistical features summarized these window-specific features per recording, resulting in 1800 features (12 × 150). A pre-trained deep neural network from the PhysioNet Challenge 2021 was updated using transfer learning to discriminate recordings with and without AF. The model processed PSG ECGs in 16-s windows to generate AF probabilities, from which 13 statistical features were extracted. Combining 1800 features from feature extraction with 13 from the deep learning model, we performed a feature selection and subsequently trained a shallow neural network to predict future AF and evaluated its performance on the test cohort. RESULTS: On the test set, our model exhibited sensitivity, specificity, and precision of 0.67, 0.81, and 0.3, respectively, for AF prediction. Survival analysis revealed a hazard ratio of 8.36 (p-value: 1.93 × 10-52) for AF outcomes using the log-rank test. CONCLUSIONS: Our proposed ECG analysis method, utilizing overnight PSG data, shows promise in AF prediction despite modest precision, suggesting false positives. This approach could enable low-cost screening and proactive treatment for high-risk patients. Refinements, including additional physiological parameters, may reduce false positives, enhancing clinical utility and accuracy.
ABSTRACT
Importance: Research on resilience after trauma has often focused on individual-level factors (eg, ability to cope with adversity) and overlooked influential neighborhood-level factors that may help mitigate the development of posttraumatic stress disorder (PTSD). Objective: To investigate whether an interaction between residential greenspace and self-reported individual resources was associated with a resilient PTSD trajectory (ie, low/no symptoms) and to test if the association between greenspace and PTSD trajectory was mediated by neural reactivity to reward. Design, Setting, and Participants: As part of a longitudinal cohort study, trauma survivors were recruited from emergency departments across the US. Two weeks after trauma, a subset of participants underwent functional magnetic resonance imaging during a monetary reward task. Study data were analyzed from January to November 2023. Exposures: Residential greenspace within a 100-m buffer of each participant's home address was derived from satellite imagery and quantified using the Normalized Difference Vegetation Index and perceived individual resources measured by the Connor-Davidson Resilience Scale (CD-RISC). Main Outcome and Measures: PTSD symptom severity measured at 2 weeks, 8 weeks, 3 months, and 6 months after trauma. Neural responses to monetary reward in reward-related regions (ie, amygdala, nucleus accumbens, orbitofrontal cortex) was a secondary outcome. Covariates included both geocoded (eg, area deprivation index) and self-reported characteristics (eg, childhood maltreatment, income). Results: In 2597 trauma survivors (mean [SD] age, 36.5 [13.4] years; 1637 female [63%]; 1304 non-Hispanic Black [50.2%], 289 Hispanic [11.1%], 901 non-Hispanic White [34.7%], 93 non-Hispanic other race [3.6%], and 10 missing/unreported [0.4%]), 6 PTSD trajectories (resilient, nonremitting high, nonremitting moderate, slow recovery, rapid recovery, delayed) were identified through latent-class mixed-effect modeling. Multinominal logistic regressions revealed that for individuals with higher CD-RISC scores, greenspace was associated with a greater likelihood of assignment in a resilient trajectory compared with nonremitting high (Wald z test = -3.92; P < .001), nonremitting moderate (Wald z test = -2.24; P = .03), or slow recovery (Wald z test = -2.27; P = .02) classes. Greenspace was also associated with greater neural reactivity to reward in the amygdala (n = 288; t277 = 2.83; adjusted P value = 0.02); however, reward reactivity did not differ by PTSD trajectory. Conclusions and Relevance: In this cohort study, greenspace and self-reported individual resources were significantly associated with PTSD trajectories. These findings suggest that factors at multiple ecological levels may contribute to the likelihood of resiliency to PTSD after trauma.
ABSTRACT
The neurocardiac circuit is integral to physiological regulation of threat and trauma-related responses. However, few direct investigations of brain-behavior associations with replicable physiological markers of PTSD have been conducted. The current study probed the neurocardiac circuit by examining associations among its core regions in the brain (e.g., insula, hypothalamus) and the periphery (heart rate [HR], high frequency heart rate variability [HF-HRV], and blood pressure [BP]). We sought to characterize these associations and to determine whether there were differences by PTSD status. Participants were N = 315 (64.1 % female) trauma-exposed adults enrolled from emergency departments as part of the prospective AURORA study. Participants completed a deep phenotyping session (e.g., fear conditioning, magnetic resonance imaging) two weeks after emergency department admission. Voxelwise analyses revealed several significant interactions between PTSD severity 8-weeks posttrauma and psychophysiological recordings on hypothalamic connectivity to the prefrontal cortex (PFC), insula, superior temporal sulcus, and temporoparietaloccipital junction. Among those with PTSD, diastolic BP was directly correlated with right insula-hypothalamic connectivity, whereas the reverse was found for those without PTSD. PTSD status moderated the association between systolic BP, HR, and HF-HRV and hypothalamic connectivity in the same direction. While preliminary, our findings may suggest that individuals with higher PTSD severity exhibit compensatory neural mechanisms to down-regulate autonomic imbalance. Additional study is warranted to determine how underlying mechanisms (e.g., inflammation) may disrupt the neurocardiac circuit and increase cardiometabolic disease risk in PTSD.
Subject(s)
Blood Pressure , Heart Rate , Magnetic Resonance Imaging , Stress Disorders, Post-Traumatic , Humans , Stress Disorders, Post-Traumatic/physiopathology , Stress Disorders, Post-Traumatic/diagnostic imaging , Female , Male , Adult , Heart Rate/physiology , Blood Pressure/physiology , Hypothalamus/physiopathology , Hypothalamus/diagnostic imaging , Middle Aged , Young Adult , Cerebral Cortex/diagnostic imaging , Cerebral Cortex/physiopathology , Psychological Trauma/physiopathology , Psychological Trauma/diagnostic imagingABSTRACT
Background: Atrial fibrillation (AF) is often asymptomatic and thus under-observed. Given the high risks of stroke and heart failure among patients with AF, early prediction and effective management are crucial. Importantly, obstructive sleep apnea is highly prevalent among AF patients (60-90%); therefore, electrocardiogram (ECG) analysis from polysomnography (PSG), a standard diagnostic tool for subjects with suspected sleep apnea, presents a unique opportunity for the early prediction of AF. Our goal is to identify individuals at a high risk of developing AF in the future from a single-lead ECG recorded during standard PSGs. Methods: We analyzed 18,782 single-lead ECG recordings from 13,609 subjects at Massachusetts General Hospital, identifying AF presence using ICD-9/10 codes in medical records. Our dataset comprises 15,913 recordings without a medical record for AF and 2,056 recordings from patients who were first diagnosed with AF between 1 day to 15 years after the PSG recording. The PSG data were partitioned into training, validation, and test cohorts. In the first phase, a signal quality index (SQI) was calculated in 30-second windows and those with SQI < 0.95 were removed. From each remaining window, 150 hand-crafted features were extracted from time, frequency, time-frequency domains, and phase-space reconstructions of the ECG. A compilation of 12 statistical features summarized these window-specific features per recording, resulting in 1,800 features. We then updated a pre-trained deep neural network and data from the PhysioNet Challenge 2021 using transfer-learning to discriminate between recordings with and without AF using the same Challenge data. The model was applied to the PSG ECGs in 16-second windows to generate the probability of AF for each window. From the resultant probability sequence, 13 statistical features were extracted. Subsequently, we trained a shallow neural network to predict future AF using the extracted ECG and probability features. Results: On the test set, our model demonstrated a sensitivity of 0.67, specificity of 0.81, and precision of 0.3 for predicting AF. Further, survival analysis for AF outcomes, using the log-rank test, revealed a hazard ratio of 8.36 (p-value of 1.93 × 10 -52 ). Conclusions: Our proposed ECG analysis method, utilizing overnight PSG data, shows promise in AF prediction despite a modest precision indicating the presence of false positive cases. This approach could potentially enable low-cost screening and proactive treatment for high-risk patients. Ongoing refinement, such as integrating additional physiological parameters could significantly reduce false positives, enhancing its clinical utility and accuracy.
ABSTRACT
Importance: Obstructive sleep apnea (OSA) is a common condition in older adult (aged >65 years) populations, but more mechanistic research is needed to individualize treatments. Previous evidence has suggested an association between OSA and posttraumatic stress disorder (PTSD) but is limited by possible selection bias. High-quality research on this association with a careful evaluation of possible confounders may yield important mechanistic insight into both conditions and improve treatment efforts. Objective: To investigate the association of current PTSD symptoms and PTSD diagnosis with OSA. Design, Setting, and Participants: This cross-sectional study of twin pairs discordant for PTSD, which allows for adjustment for familial factors, was conducted using in-laboratory polysomnography from March 20, 2017, to June 3, 2019. The study sample comprised male veteran twins recruited from the Vietnam Era Twin Registry. The data analysis was performed between June 11, 2022, and January 30, 2023. Exposure: Symptoms of PTSD in twins who served in the Vietnam War. Diagnosis of PTSD was a secondary exposure. Main Outcomes and Measures: Obstructive sleep apnea was assessed using the apnea-hypopnea index (AHI) (≥4% oxygen saturation criterion as measured by events per hour) with overnight polysomnography. Symptoms of PTSD were assessed using the PTSD Checklist (PCL) and structured clinical interview for PTSD diagnosis. Results: A total of 181 male twins (mean [SD] age, 68.4 [2.0] years) including 66 pairs discordant for PTSD symptoms and 15 pairs discordant for a current PTSD diagnosis were evaluated. In models examining the PCL and OSA within pairs and adjusted for body mass index (BMI) and other sociodemographic, cardiovascular, and psychiatric risk factors (including depression), each 15-point increase in PCL was associated with a 4.6 (95% CI, 0.1-9.1) events-per-hour higher AHI. Current PTSD diagnosis was associated with an adjusted 10.5 (95% CI, 5.7-15.3) events-per-hour higher AHI per sleep-hour. Comparable standardized estimates of the association of PTSD symptoms and BMI with AHI per SD increase (1.9 events per hour; 95% CI, 0.5-3.3 events per hour) were found. Conclusions and Relevance: This cross-sectional study found an association between PTSD and sleep-disordered breathing. The findings have important public health implications and may also enhance understanding of the many factors that potentially affect OSA pathophysiology.
Subject(s)
Sleep Apnea, Obstructive , Stress Disorders, Post-Traumatic , Veterans , Humans , Stress Disorders, Post-Traumatic/epidemiology , Male , Sleep Apnea, Obstructive/epidemiology , Cross-Sectional Studies , Aged , Veterans/statistics & numerical data , Veterans/psychology , Middle Aged , Vietnam Conflict , Polysomnography , Diseases in Twins/epidemiology , TwinsABSTRACT
There are significant challenges to identifying which individuals require intervention following exposure to trauma, and a need for strategies to identify and provide individuals at risk for developing PTSD with timely interventions. The present study seeks to identify a minimal set of trauma-related symptoms, assessed during the weeks following traumatic exposure, that can accurately predict PTSD. Participants were 2185 adults (Mean age=36.4 years; 64% women; 50% Black) presenting for emergency care following traumatic exposure. Participants received a 'flash survey' with 6-8 varying symptoms (from a pool of 26 trauma symptoms) several times per week for eight weeks following the trauma exposure (each symptom assessed â¼6 times). Features (mean, sd, last, worst, peak-end scores) from the repeatedly assessed symptoms were included as candidate variables in a CART machine learning analysis to develop a pragmatic predictive algorithm. PTSD (PCL-5 ≥38) was present for 669 (31%) participants at the 8-week follow-up. A classification tree with three splits, based on mean scores of nervousness, rehashing, and fatigue, predicted PTSD with an Area Under the Curve of 0.836. Findings suggest feasibility for a 3-item assessment protocol, delivered once per week, following traumatic exposure to assess and potentially facilitate follow-up care for those at risk.
Subject(s)
Machine Learning , Stress Disorders, Post-Traumatic , Humans , Stress Disorders, Post-Traumatic/diagnosis , Stress Disorders, Post-Traumatic/psychology , Female , Male , Adult , Longitudinal Studies , Middle AgedABSTRACT
Individuals with Autism Spectrum Disorder may display interfering behaviors that limit their inclusion in educational and community settings, negatively impacting their quality of life. These behaviors may also signal potential medical conditions or indicate upcoming high-risk behaviors. This study explores behavior patterns that precede high-risk, challenging behaviors or seizures the following day. We analyzed an existing dataset of behavior and seizure data from 331 children with profound ASD over nine years. We developed a deep learning-based algorithm designed to predict the likelihood of aggression, elopement, and self-injurious behavior (SIB) as three high-risk behavioral events, as well as seizure episodes as a high-risk medical event occurring the next day. The proposed model attained accuracies of 78.4%, 80.68%, 85.43%, and 69.95% for predicting the next-day occurrence of aggression, SIB, elopement, and seizure episodes, respectively. The results were proven significant for more than 95% of the population for all high-risk event predictions using permutation-based statistical tests. Our findings emphasize the potential of leveraging historical behavior data for the early detection of high-risk behavioral and medical events, paving the way for behavioral interventions and improved support in both social and educational environments.
ABSTRACT
BACKGROUND: Knowledge of sex differences in risk factors for posttraumatic stress disorder (PTSD) can contribute to the development of refined preventive interventions. Therefore, the aim of this study was to examine if women and men differ in their vulnerability to risk factors for PTSD. METHODS: As part of the longitudinal AURORA study, 2924 patients seeking emergency department (ED) treatment in the acute aftermath of trauma provided self-report assessments of pre- peri- and post-traumatic risk factors, as well as 3-month PTSD severity. We systematically examined sex-dependent effects of 16 risk factors that have previously been hypothesized to show different associations with PTSD severity in women and men. RESULTS: Women reported higher PTSD severity at 3-months post-trauma. Z-score comparisons indicated that for five of the 16 examined risk factors the association with 3-month PTSD severity was stronger in men than in women. In multivariable models, interaction effects with sex were observed for pre-traumatic anxiety symptoms, and acute dissociative symptoms; both showed stronger associations with PTSD in men than in women. Subgroup analyses suggested trauma type-conditional effects. CONCLUSIONS: Our findings indicate mechanisms to which men might be particularly vulnerable, demonstrating that known PTSD risk factors might behave differently in women and men. Analyses did not identify any risk factors to which women were more vulnerable than men, pointing toward further mechanisms to explain women's higher PTSD risk. Our study illustrates the need for a more systematic examination of sex differences in contributors to PTSD severity after trauma, which may inform refined preventive interventions.
ABSTRACT
Objective.The EPHNOGRAM project aimed to develop a low-cost, low-power device for simultaneous electrocardiogram (ECG) and phonocardiogram (PCG) recording, with additional channels for environmental audio to enhance PCG through active noise cancellation. The objective was to study multimodal electro-mechanical activities of the heart, offering insights into the differences and synergies between these modalities during various cardiac activity levels.Approach.We developed and tested several hardware prototypes of a simultaneous ECG-PCG acquisition device. Using this technology, we collected simultaneous ECG and PCG data from 24 healthy adults during different physical activities, including resting, walking, running, and stationary biking, in an indoor fitness center. The data were annotated using a robust software that we developed for detecting ECG R-peaks and PCG S1 and S2 components, and overseen by a human expert. We also developed machine learning models using ECG-based, PCG-based, and joint ECG-PCG features, like R-R and S1-S2 intervals, to classify physical activities and analyze electro-mechanical dynamics.Main results.The results show a significant coupling between ECG and PCG components, especially during high-intensity exercise. Notable micro-variations in S2-based heart rate show differences in the heart's electrical and mechanical functions. The Lomb-Scargle periodogram and approximate entropy analyses confirm the higher volatility of S2-based heart rate compared to ECG-based heart rate. Correlation analysis shows stronger coupling between R-R and R-S1 intervals during high-intensity activities. Hybrid ECG-PCG features, like the R-S2 interval, were identified as more informative for physical activity classification through mRMR feature selection and SHAP value analysis.Significance.The EPHNOGRAM database, is available on PhysioNet. The database enhances our understanding of cardiac function, enabling future studies on the heart's mechanical and electrical interrelationships. The results of this study can contribute to improved cardiac condition diagnoses. Additionally, the designed hardware has the potential for integration into wearable devices and the development of multimodal stress test technologies.
Subject(s)
Electrocardiography , Signal Processing, Computer-Assisted , Humans , Electrocardiography/instrumentation , Electrocardiography/methods , Phonocardiography/instrumentation , Male , Adult , Databases, Factual , Female , Time Factors , Young Adult , Machine Learning , Heart Rate/physiologyABSTRACT
BACKGROUND: Autonomic function can be measured noninvasively using heart rate variability (HRV), which indexes overall sympathovagal balance. Deceleration capacity (DC) of heart rate is a more specific metric of vagal modulation. Higher values of these measures have been associated with reduced mortality risk primarily in patients with cardiovascular disease, but their significance in community samples is less clear. METHODS AND RESULTS: This prospective twin study followed 501 members from the VET (Vietnam Era Twin) registry. At baseline, frequency domain HRV and DC were measured from 24-hour Holter ECGs. During an average 12-year follow-up, all-cause death was assessed via the National Death Index. Multivariable Cox frailty models with random effect for twin pair were used to examine the hazard ratios of death per 1-SD increase in log-transformed autonomic metrics. Both in the overall sample and comparing twins within pairs, higher values of low-frequency HRV and DC were significantly associated with lower hazards of all-cause death. In within-pair analysis, after adjusting for baseline factors, there was a 22% and 27% lower hazard of death per 1-SD increment in low-frequency HRV and DC, respectively. Higher low-frequency HRV and DC, measured during both daytime and nighttime, were associated with decreased hazard of death, but daytime measures showed numerically stronger associations. Results did not substantially vary by zygosity. CONCLUSIONS: Autonomic inflexibility, and especially vagal withdrawal, are important mechanistic pathways of general mortality risk, independent of familial and genetic factors.
Subject(s)
Veterans , Humans , Bradycardia , Deceleration , Electrocardiography, Ambulatory , Heart Rate/physiology , Prospective StudiesABSTRACT
BACKGROUND: Females are more likely to develop posttraumatic stress disorder (PTSD) than males. Impaired inhibition has been identified as a mechanism for PTSD development, but studies on potential sex differences in this neurobiological mechanism and how it relates to PTSD severity and progression are relatively rare. Here, we examined sex differences in neural activation during response inhibition and PTSD following recent trauma. METHODS: Participants (n = 205, 138 female sex assigned at birth) were recruited from emergency departments within 72 hours of a traumatic event. PTSD symptoms were assessed 2 weeks and 6 months posttrauma. A Go/NoGo task was performed 2 weeks posttrauma in a 3T magnetic resonance imaging scanner to measure neural activity during response inhibition in the ventromedial prefrontal cortex, right inferior frontal gyrus, and bilateral hippocampus. General linear models were used to examine the interaction effect of sex on the relationship between our regions of interest and the whole brain, PTSD symptoms at 6 months, and symptom progression between 2 weeks and 6 months. RESULTS: Lower response inhibition-related ventromedial prefrontal cortex activation 2 weeks posttrauma predicted more PTSD symptoms at 6 months in females but not in males, while greater response inhibition-related right inferior frontal gyrus activation predicted lower PTSD symptom progression in males but not females. Whole-brain interaction effects were observed in the medial temporal gyrus and left precentral gyrus. CONCLUSIONS: There are sex differences in the relationship between inhibition-related brain activation and PTSD symptom severity and progression. These findings suggest that sex differences should be assessed in future PTSD studies and reveal potential targets for sex-specific interventions.
Subject(s)
Inhibition, Psychological , Magnetic Resonance Imaging , Sex Characteristics , Stress Disorders, Post-Traumatic , Humans , Stress Disorders, Post-Traumatic/physiopathology , Stress Disorders, Post-Traumatic/diagnostic imaging , Female , Male , Adult , Prefrontal Cortex/physiopathology , Prefrontal Cortex/diagnostic imaging , Young Adult , Brain/physiopathology , Brain/diagnostic imaging , Hippocampus/physiopathology , Hippocampus/diagnostic imagingABSTRACT
This study examines the association between brain dynamic functional network connectivity (dFNC) and current/future posttraumatic stress (PTS) symptom severity, and the impact of sex on this relationship. By analyzing 275 participants' dFNC data obtained ~2 weeks after trauma exposure, we noted that brain dynamics of an inter-network brain state link negatively with current (r=-0.179, pcorrected= 0.021) and future (r=-0.166, pcorrected= 0.029) PTS symptom severity. Also, dynamics of an intra-network brain state correlated with future symptom intensity (r = 0.192, pcorrected = 0.021). We additionally observed that the association between the network dynamics of the inter-network brain state with symptom severity is more pronounced in females (r=-0.244, pcorrected = 0.014). Our findings highlight a potential link between brain network dynamics in the aftermath of trauma with current and future PTSD outcomes, with a stronger protective effect of inter-network brain states against symptom severity in females, underscoring the importance of sex differences.
ABSTRACT
Regular blood pressure (BP) monitoring in clinical and ambulatory settings plays a crucial role in the prevention, diagnosis, treatment, and management of cardiovascular diseases. Recently, the widespread adoption of ambulatory BP measurement devices has been predominantly driven by the increased prevalence of hypertension and its associated risks and clinical conditions. Recent guidelines advocate for regular BP monitoring as part of regular clinical visits or even at home. This increased utilization of BP measurement technologies has raised significant concerns regarding the accuracy of reported BP values across settings. In this survey, which focuses mainly on cuff-based BP monitoring technologies, we highlight how BP measurements can demonstrate substantial biases and variances due to factors such as measurement and device errors, demographics, and body habitus. With these inherent biases, the development of a new generation of cuff-based BP devices that use artificial intelligence (AI) has significant potential. We present future avenues where AI-assisted technologies can leverage the extensive clinical literature on BP-related studies together with the large collections of BP records available in electronic health records. These resources can be combined with machine learning approaches, including deep learning and Bayesian inference, to remove BP measurement biases and provide individualized BP-related cardiovascular risk indexes.
Subject(s)
Artificial Intelligence , Hypertension , Humans , Blood Pressure/physiology , Bayes Theorem , Blood Pressure Determination , Hypertension/diagnosisABSTRACT
Background: Post-traumatic stress disorder (PTSD) and substance use (tobacco, alcohol, and cannabis) are highly comorbid. Many factors affect this relationship, including sociodemographic and psychosocial characteristics, other prior traumas, and physical health. However, few prior studies have investigated this prospectively, examining new substance use and the extent to which a wide range of factors may modify the relationship to PTSD. Methods: The Advancing Understanding of RecOvery afteR traumA (AURORA) study is a prospective cohort of adults presenting at emergency departments (N = 2,943). Participants self-reported PTSD symptoms and the frequency and quantity of tobacco, alcohol, and cannabis use at six total timepoints. We assessed the associations of PTSD and future substance use, lagged by one timepoint, using the Poisson generalized estimating equations. We also stratified by incident and prevalent substance use and generated causal forests to identify the most important effect modifiers of this relationship out of 128 potential variables. Results: At baseline, 37.3% (N = 1,099) of participants reported likely PTSD. PTSD was associated with tobacco frequency (incidence rate ratio (IRR): 1.003, 95% CI: 1.00, 1.01, p = 0.02) and quantity (IRR: 1.01, 95% CI: 1.001, 1.01, p = 0.01), and alcohol frequency (IRR: 1.002, 95% CI: 1.00, 1.004, p = 0.03) and quantity (IRR: 1.003, 95% CI: 1.001, 1.01, p = 0.001), but not with cannabis use. There were slight differences in incident compared to prevalent tobacco frequency and quantity of use; prevalent tobacco frequency and quantity were associated with PTSD symptoms, while incident tobacco frequency and quantity were not. Using causal forests, lifetime worst use of cigarettes, overall self-rated physical health, and prior childhood trauma were major moderators of the relationship between PTSD symptoms and the three substances investigated. Conclusion: PTSD symptoms were highly associated with tobacco and alcohol use, while the association with prospective cannabis use is not clear. Findings suggest that understanding the different risk stratification that occurs can aid in tailoring interventions to populations at greatest risk to best mitigate the comorbidity between PTSD symptoms and future substance use outcomes. We demonstrate that this is particularly salient for tobacco use and, to some extent, alcohol use, while cannabis is less likely to be impacted by PTSD symptoms across the strata.
ABSTRACT
Poor sleep quality in Autism Spectrum Disorder (ASD) individuals is linked to severe daytime behaviors. This study explores the relationship between a prior night's sleep structure and its predictive power for next-day behavior in ASD individuals. The motion was extracted using a low-cost near-infrared camera in a privacy-preserving way. Over two years, we recorded overnight data from 14 individuals, spanning over 2,000 nights, and tracked challenging daytime behaviors, including aggression, self-injury, and disruption. We developed an ensemble machine learning algorithm to predict next-day behavior in the morning and the afternoon. Our findings indicate that sleep quality is a more reliable predictor of morning behavior than afternoon behavior the next day. The proposed model attained an accuracy of 74% and a F1 score of 0.74 in target-sensitive tasks and 67% accuracy and 0.69 F1 score in target-insensitive tasks. For 7 of the 14, better-than-chance balanced accuracy was obtained (p-value<0.05), with 3 showing significant trends (p-value<0.1). These results suggest off-body, privacy-preserving sleep monitoring as a viable method for predicting next-day adverse behavior in ASD individuals, with the potential for behavioral intervention and enhanced care in social and learning settings.
ABSTRACT
Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices with photoplethysmography (PPG) sensors and deep neural networks has demonstrated some success using proprietary algorithms in commercial solutions. However, to improve continuous AF detection in ambulatory settings towards a population-wide screening use case, we face several challenges, one of which is the lack of large-scale labeled training data. To address this challenge, we propose to leverage AF alarms from bedside patient monitors to label concurrent PPG signals, resulting in the largest PPG-AF dataset so far (8.5 M 30-second records from 24,100 patients) and demonstrating a practical approach to build large labeled PPG datasets. Furthermore, we recognize that the AF labels thus obtained contain errors because of false AF alarms generated from imperfect built-in algorithms from bedside monitors. Dealing with label noise with unknown distribution characteristics in this case requires advanced algorithms. We, therefore, introduce and open-source a novel loss design, the cluster membership consistency (CMC) loss, to mitigate label errors. By comparing CMC with state-of-the-art methods selected from a noisy label competition, we demonstrate its superiority in handling label noise in PPG data, resilience to poor-quality signals, and computational efficiency.
Subject(s)
Algorithms , Atrial Fibrillation , Photoplethysmography , Signal Processing, Computer-Assisted , Humans , Photoplethysmography/methods , Atrial Fibrillation/physiopathology , Atrial Fibrillation/diagnosis , Clinical Alarms , Machine Learning , Wearable Electronic DevicesABSTRACT
Social interaction behaviors change as a result of both physical and psychiatric problems, and it is important to identify subtle changes in group activity engagements for monitoring the mental health of patients in clinics. This work proposes a system to identify when and where group formations occur in an approximately 1700 m2 therapeutic built environment using a distributed edge-computing camera network. The proposed method can localize group formations when provided with noisy positions and orientations of individuals, estimated from sparsely distributed multiview cameras, which run a lightweight multiperson 2-D pose detection model. Our group identification method demonstrated an F1 score of up to 90% with a mean absolute error of 1.25 m for group localization on our benchmark dataset. The dataset consisted of seven subjects walking, sitting, and conversing for 35 min in groups of various sizes ranging from 2 to 7 subjects. The proposed system is low-cost and scalable to any ordinary building to transform the indoor space into a smart environment using edge computing systems. We expect the proposed system to enhance existing therapeutic units for passively monitoring the social behaviors of patients when implementing real-time interventions.