Exploring the Possibility of Photoplethysmography-Based Human Activity Recognition Using Convolutional Neural Networks.

Various sensing modalities, including external and internal sensors, have been employed in research on human activity recognition (HAR). Among these, internal sensors, particularly wearable technologies, hold significant promise due to their lightweight nature and simplicity. Recently, HAR techniques leveraging wearable biometric signals, such as electrocardiography (ECG) and photoplethysmography (PPG), have been proposed using publicly available datasets. However, to facilitate broader practical applications, a more extensive analysis based on larger databases with cross-subject validation is required. In pursuit of this objective, we initially gathered PPG signals from 40 participants engaged in five common daily activities. Subsequently, we evaluated the feasibility of classifying these activities using deep learning architecture. The model's performance was assessed in terms of accuracy, precision, recall, and F-1 measure via cross-subject cross-validation (CV). The proposed method successfully distinguished the five activities considered, with an average test accuracy of 95.14%. Furthermore, we recommend an optimal window size based on a comprehensive evaluation of performance relative to the input signal length. These findings confirm the potential for practical HAR applications based on PPG and indicate its prospective extension to various domains, such as healthcare or fitness applications, by concurrently analyzing behavioral and health data through a single biometric signal.

Distinct effect of exercise modes on mood-related behavior in mice.

Exercise can afford several benefits to combat mood disorders in both rodents and humans. Engagement in various physical activities upregulates levels of neurotrophic factors in several brain regions and improves mental health. However, the type of exercise that regulates mood and the underlying mechanisms in the brain remain elusive. Herein, we performed two distinct types of exercise and RNA sequencing analyses to investigate the effect of exercise on mood-related behaviors and explain the distinct patterns of gene expression. Specifically, resistance exercise exhibited reduced immobility time in the forced swim test when compared with both no exercise and treadmill exercise (in the aerobic training [AT] group). Interestingly, anxiety-like behaviors in the open field and nest-building tests were ameliorated in the AT group when compared with those in the control group; however, this was not observed in the RT group. To elucidate the mechanism underlying these different behavioral changes caused by distinct exercise types, we examined the shift in the gene expression pattern in the hippocampus, a brain region that plays a critical role in regulating mood. We discovered that 38 and 40 genes were altered in the AT and RT groups, respectively, compared with the control group. Both exercises regulated 16 common genes. Compared with the control group, mitogen-activated protein kinase (MAPK) was enriched in the AT group and phosphatidylinositol-3-kinase (PI3K)/AKT and neurotrophin signaling pathways were enriched in the RT group, as determined by bioinformatics pathway analysis. PCR results revealed that Cebpß expression was increased in AT group, and Dcx expression was upregulated in both groups. Our findings indicate that different exercise types may exert substantially distinct effects on mood-like behaviors. Accordingly, appropriate types of exercise can be undertaken based on the mood disorder to be regulated.

A Holistic Strategy for Classification of Sleep Stages with EEG.

Manual sleep stage scoring is usually implemented with the help of sleep specialists by means of visual inspection of the neurophysiological signals of the patient. As it is a very hectic task to perform, automated sleep stage classification systems were developed in the past, and advancements are being made consistently by researchers. The various stages of sleep are identified by these automated sleep stage classification systems, and it is quite an important step to assist doctors for the diagnosis of sleep-related disorders. In this work, a holistic strategy named as clustering and dimensionality reduction with feature extraction cum selection for classification along with deep learning (CDFCD) is proposed for the classification of sleep stages with EEG signals. Though the methodology follows a similar structural flow as proposed in the past works, many advanced and novel techniques are proposed under each category in this work flow. Initially, clustering is applied with the help of hierarchical clustering, spectral clustering, and the proposed principal component analysis (PCA)-based subspace clustering. Then the dimensionality of it is reduced with the help of the proposed singular value decomposition (SVD)-based spectral algorithm and the standard variational Bayesian matrix factorization (VBMF) technique. Then the features are extracted and selected with the two novel proposed techniques, such as the sparse group lasso technique with dual-level implementation (SGL-DLI) and the ridge regression technique with limiting weight scheme (RR-LWS). Finally, the classification happens with the less explored multiclass Gaussian process classification (MGC), the proposed random arbitrary collective classification (RACC), and the deep learning technique using long short-term memory (LSTM) along with other conventional machine learning techniques. This methodology is validated on the sleep EDF database, and the results obtained with this methodology have surpassed the results of the previous studies in terms of the obtained classification accuracy reporting a high accuracy of 93.51% even for the six-classes classification problem.

Using a Real-Time Location System for Assessment of Patient Ambulation in a Hospital Setting.

OBJECTIVE: To assess the feasibility of using an infrared-based Real-Time Location System (RTLS) for measuring patient ambulation in a 2-minute walk test (2MWT) by comparing the distance walked and the Johns Hopkins Highest Level of Mobility (JH-HLM) score to clinician observation as a criterion standard. DESIGN: Criterion standard validation study. SETTING: Inpatient, university hospital. PARTICIPANTS: Patients (N=25) in an adult neuroscience/brain rescue unit. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: RTLS and clinician-reported ambulation distance in feet, and JH-HLM score on an 8-point ordinal scale. RESULTS: The RTLS ambulation distance for the 25 patients in the 2MWT was between 68 and 516ft. The mean difference between clinician-reported and RTLS ambulation distance was 8.4±11.7ft (2.7%±4.6%). The correlation between clinician-reported and RTLS ambulation distance was 97.9% (P<.01). The clinician-reported ambulation distance for 2 patients was +100ft and -99ft compared with the RTLS distance, implying clinician error in counting the number of laps (98ft). The correlation between the RTLS distance and clinician-reported distance excluding these 2 patients is 99.8% (P<.01). The accuracy of the RTLS for assessment of JH-HLM score for all 25 patients was 96%. The average patient speed obtained from RTLS data varied between 0.4 and 3.0mph. CONCLUSIONS: The RTLS is able to accurately measure patient ambulation and calculate JH-HLM for a 2MWT when compared with clinician observation as the criterion standard.

Introducing Contactless Blood Pressure Assessment Using a High Speed Video Camera.

Recent studies demonstrated that blood pressure (BP) can be estimated using pulse transit time (PTT). For PTT calculation, photoplethysmogram (PPG) is usually used to detect a time lag in pulse wave propagation which is correlated with BP. Until now, PTT and PPG were registered using a set of body-worn sensors. In this study a new methodology is introduced allowing contactless registration of PTT and PPG using high speed camera resulting in corresponding image-based PTT (iPTT) and image-based PPG (iPPG) generation. The iPTT value can be potentially utilized for blood pressure estimation however extent of correlation between iPTT and BP is unknown. The goal of this preliminary feasibility study was to introduce the methodology for contactless generation of iPPG and iPTT and to make initial estimation of the extent of correlation between iPTT and BP "in vivo." A short cycling exercise was used to generate BP changes in healthy adult volunteers in three consecutive visits. BP was measured by a verified BP monitor simultaneously with iPTT registration at three exercise points: rest, exercise peak, and recovery. iPPG was simultaneously registered at two body locations during the exercise using high speed camera at 420 frames per second. iPTT was calculated as a time lag between pulse waves obtained as two iPPG's registered from simultaneous recoding of head and palm areas. The average inter-person correlation between PTT and iPTT was 0.85 ± 0.08. The range of inter-person correlations between PTT and iPTT was from 0.70 to 0.95 (p < 0.05). The average inter-person coefficient of correlation between SBP and iPTT was -0.80 ± 0.12. The range of correlations between systolic BP and iPTT was from 0.632 to 0.960 with p < 0.05 for most of the participants. Preliminary data indicated that a high speed camera can be potentially utilized for unobtrusive contactless monitoring of abrupt blood pressure changes in a variety of settings. The initial prototype system was able to successfully generate approximation of pulse transit time and showed high intra-individual correlation between iPTT and BP. Further investigation of the proposed approach is warranted.

Development and evaluation of an improved technique for pulmonary function testing using electrical impedance pneumography intended for the diagnosis of chronic obstructive pulmonary disease patients.

Spirometry is regarded as the only effective method for detecting pulmonary function test (PFT) indices. In this study, a novel impedance pulmonary function measurement system (IPFS) is developed for directly assessing PFT indices. IPFS can obtain high resolution values and remove motion artifacts through real-time base impedance feedback. Feedback enables the detection of PFT indices using only both hands for convenience. IPFS showed no differences in the sitting, supine, and standing postures during the measurements, indicating that patient posture has no effect on IPFS. Mean distance analysis showed good agreement between the volume and flow signal of IPFS (p < 0.05). PFT indices were detected in subjects to differentiate a chronic obstructive pulmonary disease (COPD) patient group from a normal group. The forced vital capacity (FVC), forced expiratory volume in the first second (FEV1), FEV1/FVC, and peak expiratory flow (PEF) in the COPD group were lower than those in the normal group by IPFS (p < 0.05). IPFS is therefore suitable for evaluating pulmonary function in normal and COPD patients. Moreover, IPFS could be useful for periodic monitoring of existing patients diagnosed with obstructive lung disease.

The effect of voluntary exercise on light cycle stress-induced metabolic resistance.

PURPOSE: Disruption of circadian genes affects metabolic homeostasis. Regular exercise programs prevent metabolic dysfunction and alter circadian gene expression In this study, we investigated whether exercise affects light stress-induced circadian rhythm derangement and metabolic resistance. METHODS: A circadian rhythm derangement mouse model was designed by extending the light exposure by two hours (14 L/10 D) for three weeks. Nine-weekold male mice were single-caged and divided into four groups: sedentary groups with or without light stress, and voluntary wheel-trained groups with or without light stress. In addition, differentiated myotubes were cultured in the presence of dexamethasone with or without 5-aminoimidazole-4-carboxamide-1-beta-4-ribofuranoside (AICAR). The comprehensive laboratory animal monitoring system was used to analyze the metabolic changes in mice. Moreover, reverse transcription-polymerase chain reaction (RT-PCR) was used to quantify the mRNA expression levels of circadian genes in animal and cell culture models. RESULTS: Three weeks of light stress reduced the running distance and increased the weight of mice. In addition, VO2 consumption and heat production were increased during the night cycle under non-stress conditions but not under stress conditions. PCR analysis revealed that exercise and stress altered the expression levels of circadian genes in the hypothalamus and quadriceps muscles. mRNA expression levels of period circadian regulator 1 were downregulated in the quadriceps muscles of the stressed sedentary group compared to that in muscles of the non-stressed sedentary group. Furthermore, differentiated myotube cells cultured in the presence of dexamethasone, with or without AICAR, showed distinct oscillation patterns at various time points. CONCLUSION: Our study demonstrates that exercise partially prevents metabolic disruption by regulating the circadian gene expression in skeletal muscles.

A Dual Level Analysis with Evolutionary Computing and Swarm Models for Classification of Leukemia.

One of the major reasons of mortality in human beings is cancer, and there is an absolute necessity for doctors to identify and treat a person suffering from it. Leukemia is a group of blood cancers that usually originates in the bone marrow and results in very high number of abnormal cells. For the diagnosis of cancer, microarray data serves as an important clinical application and serves as a great aid to the entire medical community. The dimensionality of the microarray data is too high, and so selection of suitable genes is quite an important step for the improvement of data classification. Therefore, for the prediction and diagnosis of cancer, there is an utmost necessity to select the most informative genes. In this work, Minimum Redundancy Maximum Relevance (MRMR), Signal to Noise Ratio (SNR), Multivariate Error Weight Uncorrelated Shrunken Centroid (EWUSC), and multivariate correlation-based feature selection (CFS) are chosen as initial feature selection techniques. Then, to select the most informative genes, five different kinds of evolutionary optimization techniques too are incorporated here such as African Buffalo Optimization (ABO), Artificial Bee Colony Optimization (ABCO), Cockroach Swarm Optimization (CSO), Imperialist Competitive Optimization (ICO), and Social Spider Optimization (SSO). Finally, the optimized values are fed through classification process and the best results are obtained when multivariate CFS with SSO is utilized and classified with Probabilistic Neural Network (PNN), and a high classification accuracy of 95.70% is obtained.

iApp: An Autonomous Inspection, Auscultation, Percussion, and Palpation Platform.

Disease symptoms often contain features that are not routinely recognized by patients but can be identified through indirect inspection or diagnosis by medical professionals. Telemedicine requires sufficient information for aiding doctors' diagnosis, and it has been primarily achieved by clinical decision support systems (CDSSs) utilizing visual information. However, additional medical diagnostic tools are needed for improving CDSSs. Moreover, since the COVID-19 pandemic, telemedicine has garnered increasing attention, and basic diagnostic tools (e.g., classical examination) have become the most important components of a comprehensive framework. This study proposes a conceptual system, iApp, that can collect and analyze quantified data based on an automatically performed inspection, auscultation, percussion, and palpation. The proposed iApp system consists of an auscultation sensor, camera for inspection, and custom-built hardware for automatic percussion and palpation. Experiments were designed to categorize the eight abdominal divisions of healthy subjects based on the system multi-modal data. A deep multi-modal learning model, yielding a single prediction from multi-modal inputs, was designed for learning distinctive features in eight abdominal divisions. The model's performance was evaluated in terms of the classification accuracy, sensitivity, positive predictive value, and F-measure, using epoch-wise and subject-wise methods. The results demonstrate that the iApp system can successfully categorize abdominal divisions, with the test accuracy of 89.46%. Through an automatic examination of the iApp system, this proof-of-concept study demonstrates a sophisticated classification by extracting distinct features of different abdominal divisions where different organs are located. In the future, we intend to capture the distinct features between normal and abnormal tissues while securing patient data and demonstrate the feasibility of a fully telediagnostic system that can support abnormality diagnosis.

Physical Telerehabilitation Improves Quality of Life in Patients with Multiple Sclerosis.

The purpose of this study was to investigate the effect of physical telerehabilitation on the quality of life (QOL) in patients with multiple sclerosis (PwMS) in a randomized controlled trial. PwMS in both groups received home-based individualized exercise plan based on their physical therapy exam. PwMS in the intervention group were guided by a telerehabilitation system in following their exercise program on a daily basis whereas PwMS in the control group received periodic newsletters. Disease-specific QOL was assessed by MSQOL-54 survey at the baseline and the end of 3-month rehabilitation program. Among the MSQOL sub-scales, the mean sub-score values for pain and cognitive function in control and intervention groups were significantly different as demonstrated by one-way ANOVA (pain: F = 4.301, p = 0.044, cognitive function: F = 5.053, p = 0.030). Our results demonstrated positive effects of physical telerehabilitation on MS symptoms and QOL. Development of further approaches promoting continuous participation in telerehabilitation in PwMS is warranted.

Association Between System Usage Pattern and Impact of Web-Based Telerehabilitation in Patients with Multiple Sclerosis.

Patients with multiple sclerosis (PwMS) increasingly use online services for managing their healthcare. The objective of this study was to investigate web log data (weblogs) generated by PwMS in the process of web-based telerehabilitation and correlate them with rehabilitation progress. The weblogs from 17 patients (female: 15, male 2; mean age: 60.1±11.4 years) were tracked for an average period of 153.6±38.3 days with the total number of log events and page visit records of 1,457 and 37,030, respectively. The time and frequency of patients' web visits were investigated as well as their adherence to prescribed exercise regimen. Rehabilitation progress was gauged by changes in quality of life, mobility, and sleep ascertained by measuring MSQOL, 2MWT and PSQI respectively. The changes in these metrics were correlated with system usage patterns. On average, PwMS visited 30 pages a day for 26.5 minutes, with a single login amounting for 27 pages in duration of 22.0 minutes. The average exercise program comprised 6.9 sets and 29.1 repetitions with average set and repetition completion rates of 46.5% and 72.6% respectively. A statistically significant association has been found between time spent in the online exercise mode and clinical improvements. The results of the study demonstrate that the patients had more pronounced outcome improvements when they increased the time of using the telerehabilitation system for home-based exercise. The results of this study could contribute to the development of more efficient home-based telerehabilitation systems.

Relationship Between Exercise Duration in Multimodal Telerehabilitation and Quality of Sleep in Patients with Multiple Sclerosis.

The purpose of this study was to investigate the effect of a telerehabilitation system on the quality of sleep in patients with multiple sclerosis (PwMS). Fifteen females and two males (60.1 ± 11.4 years) who used the system for three months completed the Pittsburg Sleep Quality Index (PSQI) at the baseline and end of follow-up. Total System Usage (TSU) and Total Exercise Time (TET) were elucidated from the system web logs for each PwMS. A significant association (p<0.05) was found between PSQI sleep efficiency (SE) and TSU (0.76) and between SE and TET (0.81). The association between PSQI total score (TS) and TSU and between TS and TET were -0.507 and -0.702 respectively (p<0.05). Our results uncovered an association between amount of exercise time spent by PwMS and positive effects on both the efficiency and quality of sleep. Thus, further development of approaches promoting continuous participation of PwMS in telerehabilitation is warranted.

Usability of Remote Assessment of Exercise Capacity for Pulmonary Telerehabilitation Program.

Pulmonary rehabilitation [PR] has been successfully carried out via telemedicine however initial patient assessment has been traditionally conducted in PR centers. The first step in PR is assessment of patient's exercise capacity which allows individualized prescription of safe and effective exercise program. With COVID-19 pandemics assessment of patients in PR centers has been limited resulting in significant reduction of patients undergoing life-saving PR. The goal of this pilot study was to introduce approaches for remote assessment of exercise capacity using videoconferencing platforms and provide initial usability assessment of this approach by conducing cognitive walkthrough testing. We developed a remote assessment system that supports comprehensive physical therapy assessment necessary for prescription of a personalized exercise program tailored to individual fitness level and limitations in gait and balance of the patient under evaluation. Usability was assessed by conducting cognitive walkthrough and system usability surveys. The usability inspection of the remote exercise assessment demonstrated overall high acceptance by all study participants. Our next steps in developing user-centered interface should include usability evaluation in different subgroups of patients with varying socio-economic background, different age groups, computer skills, literacy and numeracy.

Towards a Highly Usable, Mobile Electronic Platform for Patient Recruitment and Consent Management.

This study seeks to assess usability and acceptance of E-Consent on mobile devices such as tablet computers for collecting universal biobank consents. Usability inspection occurred via cognitive walkthroughs and heuristics evaluations, supplemented by surveys to capture health literacy, patient engagement, and other metrics. 17 patients of varied ages, backgrounds, and occupations participated in the study. The System Usability Scale (SUS) provided a standardized reference for usability and satisfaction, and the mean result of 84.4 placed this mobile iteration in the top 10th percentile. A semi-structured qualitative interview provided copious actionable feedback, which will inform the next iteration of this project. Overall, this implementation of the E-Consent framework on mobile devices was considered easy-to-use, satisfying, and engaging, allowing users to progress through the consent materials at their own pace. The platform has once again demonstrated high usability and high levels of user acceptance, this time in a novel setting.

Assessment of Patient Ambulation Profiles to Predict Hospital Readmission, Discharge Location, and Length of Stay in a Cardiac Surgery Progressive Care Unit.

Importance: Promoting patient mobility during hospitalization is associated with improved outcomes and reduced risk of hospitalization-associated functional decline. Therefore, accurate measurement of mobility with high-information content data may be key to improved risk prediction models, identification of at-risk patients, and the development of interventions to improve outcomes. Remote monitoring enables measurement of multiple ambulation metrics incorporating both distance and speed. Objective: To evaluate novel ambulation metrics in predicting 30-day readmission rates, discharge location, and length of stay using a real-time location system to continuously monitor the voluntary ambulations of postoperative cardiac surgery patients. Design, Setting, and Participants: This prognostic cohort study of the mobility of 100 patients after cardiac surgery in a progressive care unit at Johns Hopkins Hospital was performed using a real-time location system. Enrollment occurred between August 29, 2016, and April 4, 2018. Data analysis was performed from June 2018 to December 2019. Main Outcomes and Measures: Outcome measures included 30-day readmission, discharge location, and length of stay. Digital records of all voluntary ambulations were created where each ambulation consisted of multiple segments defined by distance and speed. Ambulation profiles consisted of 19 parameters derived from the digital ambulation records. Results: A total of 100 patients (81 men [81%]; mean [SD] age, 63.1 [11.6] years) were evaluated. Distance and speed were recorded for more than 14 000 segments in 840 voluntary ambulations, corresponding to a total of 127.8 km (79.4 miles) using a real-time location system. Patient ambulation profiles were predictive of 30-day readmission (sensitivity, 86.7%; specificity, 88.2%; C statistic, 0.925 [95% CI, 0.836-1.000]), discharge to acute rehabilitation (sensitivity, 84.6%; specificity, 86.4%; C statistic, 0.930 [95% CI, 0.855-1.000]), and length of stay (correlation coefficient, 0.927). Conclusions and Relevance: Remote monitoring provides a high-information content description of mobility, incorporating elements of step count (ambulation distance and related parameters), gait speed (ambulation speed and related parameters), frequency of ambulation, and changes in parameters on successive ambulations. Ambulation profiles incorporating multiple aspects of mobility enables accurate prediction of clinically relevant outcomes.

Factors Affecting Adherence with Telerehabilitation in Patients with Multiple Sclerosis.

The goal of this study was to identify predictors of telerehabilitation adherence in patients with multiple sclerosis (MS). An adherence prediction model was based on baseline patient characteristics. Such a model may be useful for identifying patients who require higher levels of engagements in the early stages of home telerehabilitation programs. The resulting set of predictive features included education, patient satisfaction with the program, and psychological domain of the MS Impact Scale. Resulting prediction of high and low adherence had overall 80.0% accuracy, 81.8% sensitivity, and 77.8% specificity. We concluded that the baseline patient information may be instrumental in personalizing levels of support and training necessary for active patient participation in telerehabilitation.

Mining Electronic Dental Records to Identify Dry Socket Risk Factors.

The goal of this study was to investigate risk factors for developing dry sockets in patients after dental extractions. Data were collected directly from electronic dental records (EDR) and were utilized for selecting dry socket cases and controls to conduct a nested case-control study. Case-control matching was based on sex, age range, maxilla-mandible location, and anterior-posterior location. From 83 self-reported health survey questions, 7 questions were found to have predictive potential based on a significant chi-squared test. Stepwise conditional logistic regression showed a statistically significant association between the development of dry socket and a history of serious illness (OR=1.4; 95% CI:1.02-1.95), cancer (OR=2.6; 95% CI:1.13-5.83), and frequent mouth sores (OR=1.9; 95% CI:1.09-3.33). These results corroborated previous reports on potential involvement of impaired immune response in dry socket development. EDR may be an important source for uncovering predictive factors that play a role in prevention and management of oral health.

Wearable Devices for Precision Medicine and Health State Monitoring.

Wearable technologies will play an important role in advancing precision medicine by enabling measurement of clinically-relevant parameters describing an individual's health state. The lifestyle and fitness markets have provided the driving force for the development of a broad range of wearable technologies that can be adapted for use in healthcare. Here we review existing technologies currently used for measurement of the four primary vital signs: temperature, heart rate, respiration rate, and blood pressure, along with physical activity, sweat, and emotion. We review the relevant physiology that defines the measurement needs and evaluate the different methods of signal transduction and measurement modalities for the use of wearables in healthcare.

Implant Failure Prediction Using Discriminant Analysis.

Electronic dental records (EDR) provide access to a vast repository of clinical information which may be used for analyzing dental care delivery. The goal of this study was identification of determinants of implant survival and development of implant failure prediction model using large data set of intact and failed implant parameters extracted from EDR. A retrospective analysis of 19 variables reflecting patient, surgeon and dental treatment characteristics of 800 dental implants was performed using discriminant analysis to develop a predictive model identifying potential implant failure based on characteristics routinely available in a clinical care setting. The intact and failed implant characteristics were compared using the Goodman and Kruskal's lambda test, the point-biserial test, the chi-square test, and ANOVA test. A stepwise discriminant analysis reduced model dimensionality from 19 to 4 features. The final discriminant analysis model included the following variables: non-temporary implant, pre-op antibiotics, immunocompromised status, and gender. Overall, 72% of implant failure cases and 62% of intact implants were correctly identified by the resulting discriminant function. As the final predictive feature set is readily available in EDR, the resulting algorithm may be implemented as a clinical decision support module embedded into EDR to promote personalized approach in dental implant patients.

Using Big Data to Uncover Patient Determinants of Care Utilization Compliance in a Student Dental Clinic.

This study aims at assessing the relationship between social determinants of health (SDH) and dental care utilization compliance in a student dental clinic. Electronic dental records (EDR) were queried based on visit codes and evaluated using descriptive and inferential statistics, and binary logistic regression. Overall, characteristics of 16,474 visits were analyzed to identify potential predictors of appointment compliance. Factors affecting compliance with treatment plans prescribed at comprehensive care visits were identified in a cohort of 6,105 patients. Determinants of compliance with a comprehensive care visit following triage visits were analyzed in a cohort of 5491 patients. Results indicated that certain patient characteristics were associated with either increased or decreased compliance with dental care utilization. We concluded that EDR can be instrumental in identifying patterns of care utilization and determinants of patient compliance based on SDH.