Health Assistant Wearable-Based Data Science System Model: A Pilot Study

Budiarto, Arif; Febriana, Trisna; Suparyanto, Teddy; Caraka, Rezzy Eko; Pardamean, Bens

doi:10.1109/icimtech.2018.8528102

Cited by 8 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Commercial wearables that have their algorithmic method for tracking ambulatory sleep have advantages such as affordable prices, high availability in the market, and high capabilities for their system integration with various health-oriented platforms. However, evaluating commercial sleep tracking data problems compared with polysomnograms as the gold standard for measuring ambulatory sleep cannot be utilized for medical approval in certain clinical research cases (7,8). The algorithm has implemented in this commercial wearable is a company secret and is rarely published for research from the production side, which causes clinical evaluation problems.…”

Section: Introductionmentioning

confidence: 99%

Sleep Stage Classification For Medical Purposes: Machine Learning Evaluation For Imbalanced Data

Pardamean

Budiarto

Mahesworo

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Sleep is commonly associated with physical and mental health status. Sleep quality can be determined from the dynamic of sleep stages during the night. Data from the wearable device can potentially be used as predictors to classify the sleep stage. Robust Machine Learning (ML) model is needed to learn the pattern within wearable data to be associated with the sleep-wake classification, especially to handle the imbalanced proportion between wake and sleep stages. In this study, we incorporated a publicy available dataset consists of three features captured from a consumer wearable device and the labelled sleep stages from a polysomnogram. We implemented Random Forest, Support Vector Machine , Extreme Gradiet Boosting Tree, Densed Neural Network (DNN), and Long Short-Term Memory (LSTM), complemented by three strategies to handle the imbalanced data problem. Results: In total, we included more than 24,815 rows of preprocessed data from 31 samples. The proportion of minority-majority data is 1:10. In classifying this extreme imbalanced data, the DNN model was found to have the best performance compared to the previous best model, which is based on basic Multi-Layer Perceptron. Our best model successfully achieved a 12% higher specificity score (prediction score for minority class) and 1% improvement on the sensitivity score (prediction score for majority class) by including all features in the model. This achievement was affected by the implementation of custom class weight and oversampling strategy. In contrast, when we only used two features, XGB achieved a specificity improvement only by 1%, while keeping the sensitivity at the same level.Conclusions: The non-linear operation within the DNN model could successfully learn the hidden pattern from the combination of three features. Additionally, the class weight parameter avoided the model ignoring the minority class by giving more weight for this class in the loss function. The feature engineering process seemed to obscure the time-series characteristics within the data. This is why LSTM, as one of the best methods for time-series data, failed to perform well in this classification task.

show abstract

Section: Introductionmentioning

confidence: 99%

Sleep Stage Classification For Medical Purposes: Machine Learning Evaluation For Imbalanced Data

Pardamean

Budiarto

Mahesworo

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hypertension referred to as a silent disease is the main factor causing heart disease and stroke. In an uncontrolled condition, this silent disease will cause damage to other organs such as the brain, kidneys, eyes, and movement organs (Budiarto et al, 2018;Caraka et al, 2021). Hypertension is often occurred in both developed and developing countries, the symptoms are not felt and according to CDC, hypertension is characterized by an increase in systolic blood pressure exceeding 140 mmHg and diastolic pressure exceeding 90 mmHg.…”

Section: Introductionmentioning

confidence: 99%

The Potency of Bovine Bone Gelatin as Antihypertensive Agent: A Review

Khikmawati

Rahayu

Amieni

et al. 2021

JITEK

View full text Add to dashboard Cite

This review was purposed to understand the effectiveness of bovine bone gelatin as an antihypertensive agent. This review concerning the effectiveness of bovine bone gelatin as an antihypertensive agent. Hypertension, also called as a silent disease, has become the main cause of coronary heart disease and stroke that contributes to the malfunction of human organs. Changes of lifestyle alongside with science enhancement, provides new inventions regarding methods of hypertension therapy by minimizing the use of synthetic drugs. Collagen tissue of bovine bone gelatin is known to contain angiotensin converting enzyme (ACE) inhibitor, an active peptide that plays a role in lowering blood pressure supporting with the large amount of Gly (27%), Pro (17.6%), and Hyp (14.4%) and repeating pattern of Gly-X-Y. A study was carried out in vivo using injected spontaneously hypertensive rats (SHR) with 30 mg/kg and was able to reduce blood pressure by 15 mmHg. Antihypertensive test with SHR tail-cuff at 30 mg/kg bovine gelatin hydrolysate RGL-(Hyp)-GL and RGM-(Hyp)-GF were 31.3 mmHg and 38.6 mmHg respectively. A study conducted using bovine and porcine gelatin with 30–50 kDa (permeate P1) and 1–2 kDa (permeate P3) was able to reduce blood pressure by 22 mmHg and 21.33 mmHg. In addition, it is still possible conducting research to find out other peptides of bovine bone gelatin that can be used as a future alternative antihypertensive agent.

show abstract