Vorapun Senanarong

Dr. Vorapun Senanarong


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 May 2021 in Frontiers in Neurology
Verified
Journal Article
Open access
PDF file
YVYudthaphon Vichianin
Yudthaphon Vichianin
AKAnutr Khummongkol
Anutr Khummongkol
PCPipat Chiewvit
Pipat Chiewvit
ARAtthapon Raksthaput
Atthapon Raksthaput
SCSunisa Chaichanettee
Sunisa Chaichanettee
VSVorapun Senanarong
Vorapun Senanarong
Background: The determination of brain volumes using visual ratings is associated with an inherently low accuracy for the diagnosis of Alzheimer's disease (AD). A support-vector machine (SVM) is one of the machine learning techniques, which may be utilized as a classifier for various classification problems. This study exploratorily investigated the accuracy of SVM classification models for AD subjects using brain volume and various clinical data as features.Methods: The study was designed as a retrospective chart review. A total of 201 eligible subjects were recruited from the Memory Clinic at Siriraj Hospital, Thailand. Eighteen cases were excluded due to incomplete MRI data. Subjects were randomly assigned to a training group (AD = 46, normal = 46) and testing group (AD = 45, normal = 46) for SVM modeling and validation, respectively. The results in terms of accuracy and a receiver operating characteristic curve analysis are reported.Results: The highest accuracy for brain volumetry (62.64%) was found using the hippocampus as a single feature. A combination of clinical parameters as features provided accuracy ranging between 83 and 90%. However, a combination of brain volumetry and clinical parameters as features to the SVM models did not improve the accuracy of the result.Conclusions: In our study, the use of brain volumetry as SVM features provided low classification accuracy with the highest accuracy of 62.64% using the hippocampus volume alone. In contrast, the use of clinical parameters [Thai mental state examination score, controlled oral word association tests (animals; and letters K, S, and P), learning memory, clock-drawing test, and construction-praxis] as features for SVM models provided good accuracy between 83 and 90%.

23 September 2022 in BMC Geriatrics
Verified
Journal Article
Open access
PDF file
SBSunee Bovonsunthonchai
Sunee Bovonsunthonchai
RVRoongtiwa Vachalathiti
Roongtiwa Vachalathiti
VHVimonwan Hiengkaew
Vimonwan Hiengkaew
MBMon S. Bryant
Mon S. Bryant
Jim RichardsJim Richards
Jim Richards
VSVorapun Senanarong
Vorapun Senanarong
Background: Cognitive age-related decline is linked to dementia development and gait has been proposed to measure the change in brain function. This study aimed to investigate if spatiotemporal gait variables could be used to differentiate between the three cognitive status groups. Methods: Ninety-three older adults were screened and classified into three groups; mild cognitive impairment (MCI) (n = 32), dementia (n = 31), and a cognitively intact (n = 30). Spatiotemporal gait variables were assessed under single- and dual-tasks using an objective platform system. Effects of cognitive status and walking task were analyzed using a two-way ANCOVA. Sub-comparisons for between- and within-group were performed by one-way ANCOVA and Paired t-tests. Area Under the Curve (AUC) of Receiver Operating Characteristics (ROC) was used to discriminate between three groups on gait variables. Results: There were significant effects (P < 0.05) of cognitive status during both single and dual-task walking in several variables between the MCI and dementia and between dementia and cognitively intact groups, while no difference was seen between the MCI and cognitively intact groups. A large differentiation effect between the groups was found for step length, stride length, and gait speed during both conditions of walking. Conclusions: Spatiotemporal gait variables showed discriminative ability between dementia and cognitively intact groups in both single and dual-tasks. This suggests that gait could potentially be used as a clinical differentiation marker for individuals with cognitive problems.

14 October 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
SKSupavit Kongwudhikunakorn
Supavit Kongwudhikunakorn
SKSuktipol Kiatthaveephong
Suktipol Kiatthaveephong
KTKamonwan Thanontip
Kamonwan Thanontip
PLPitshaporn Leelaarporn
Pitshaporn Leelaarporn
MPMaytus Piriyajitakonkij
Maytus Piriyajitakonkij
TWTheerawit Wilaiprasitporn
Theerawit Wilaiprasitporn
In the status quo, dementia (DEM) is yet to be cured. Precise diagnosis prior to the onset of the symptoms can prevent the rapid progression of the emerging cognitive impairment. Recent progress has shown that electroencephalography (EEG) is the promising and cost-effective test to facilitate the detection of neurocognitive disorders. However, most of the existing works have been using only resting-state EEG. The efficiencies of EEG signals from various cognitive tasks, for DEM classification, have yet to be thoroughly investigated. In this study, we designed four cognitive tasks that engage different cognitive performances: attention, working memory, and executive function. We investigated these tasks by using statistical analysis on both time and frequency domains of EEG signals from three classes of human subjects: DEM, mild cognitive impairment (MCI), and normal control (NC). We also further evaluated the classification performances of two features extraction methods: principal component analysis (PCA) and filter bank common spatial pattern (FBCSP). We found that the working memory-related tasks yielded good performances for DEM recognition in both cases using PCA and FBCSP. Moreover, FBCSP with features combination from four tasks revealed the best sensitivity of 0.87 and the specificity of 0.80. To our best knowledge, this is the first work that concurrently investigated several cognitive tasks for DEM recognition using both statistical analysis and classification scores. Our results yielded essential information to design and aid in conducting further experimental tasks to early diagnose DEM patients.

1 June 2020 in Dementia & Neuropsychologia
Verified
Journal Article
Open access
PDF file
RRRommanee Rojasavastera
Rommanee Rojasavastera
SBSunee Bovonsunthonchai
Sunee Bovonsunthonchai
VHVimonwan Hiengkaew
Vimonwan Hiengkaew
VSVorapun Senanarong
Vorapun Senanarong
It is well known that early treatment can reduce the likelihood of developing severe symptoms, hospitalization and financial burden.4 Treating MCI is crucial because it can develop to more severe stages such as dementia. However, pharmacological treatment for this group has not proven completely successful and side effects have been observed.5 Therefore, nonpharmacological treatment becomes of more interest. The American Academy of Neurology guidelines in 2018,5 recommended that exercise has a benefit for MCI on general health and cognition. However, discovering the most appropriate exercise program is key for more specific and effective results in this population.

11 November 2022 in IEEE Sensors Journal
Verified
Journal Article
Closed access
PCPhuridet Cherachapridi
Phuridet Cherachapridi
PWPatcharapol Wachiraphan
Patcharapol Wachiraphan
PRPhurin Rangpong
Phurin Rangpong
SKSuktipol Kiatthaveephong
Suktipol Kiatthaveephong
SKSupavit Kongwudhikunakorn
Supavit Kongwudhikunakorn
TSThapanun Sudhawiyangkul
Thapanun Sudhawiyangkul
Detection of mild cognitive impairment (MCI) and dementia (DEM) is an important topic because, unless it is treated early, MCI can progress to DEM, which is an untreatable disease. This paper proposes a timed-up-and-go (TUG) task features analysis and classification of MCI and DEM using inertial measurement units (IMU) in wearable devices. Our goal is to create a generalized model that can be used for pre-clinical screening. As a result, rather than classifying only one subtype of dementia, such as Alzheimer’s disease (AD) or Parkinson’s disease (PD), we classify all subtypes as DEM. We also utilize feature selection methods on features from TUG tasks to optimize the MCI and DEM classification performance. From the results, our generalized model can outperform other works in NC-MCI&DEM classification with accuracy of 86.94% and sensitivity of 97.40%. For NC-DEM classification, the performance of our generalized model is slightly lower than that of specific-subtype models (e.g., NC vs. AD). However, our generalized model can outperform the specific-subtype models when using with a diverse variety of subtypes. It is a reasonable trade-off, and it can be a good first step toward a future where the patient can pre-clinically self-screening the cognitive impairments using wearable devices in free-living environments. This could allow patients to notice the cognitive impairment early on and seek a comprehensive diagnosis from a doctor.

22 September 2023 in BMC Neurology
Verified
Journal Article
Open access
PDF file
CDChaisak Dumrikarnlert
Chaisak Dumrikarnlert
STSmathorn Thakolwiboon
Smathorn Thakolwiboon
VSVorapun Senanarong
Vorapun Senanarong
Background: Hashimoto encephalopathy has multiple clinical presentations, and other than the presence of thyroid antibody, laboratory and imaging investigations are all non-specific. Data specific to the clinical presentations and treatment outcomes of patients with Hashimoto encephalopathy in Thailand remain scarce. Objectives: To retrospectively investigate the clinical presentations and treatment outcomes of patients with Hashimoto encephalopathy at Siriraj Hospital. Methods: Patients who presented with acute encephalopathy at our center during July 2012-March 2017 were evaluated for eligibility. The inclusion criteria were positive anti-thyroperoxidase (anti-TPO) or anti-thyroglobulin (anti-Tg) in serum with negative neuronal antibody in serum or cerebral spinal fluid (CSF). Clinical presentations, symptom duration, laboratory results of thyroid status and thyroid autoantibody, CSF study, and clinical outcomes were collected. Results: Of the 204 patients who presented with encephalopathy, 31 (15.2%) were positive for the anti-TPO or anti-Tg antibody. Of those, 13 patients met the diagnostic criteria for Hashimoto encephalopathy. Clinical presentations included cognitive impairment (76.9%), clouding of consciousness (46.2%), and behavior change (30.8%). The neuropsychiatric presentations were visual hallucination (30.8%), auditory hallucination (15.4%), delusion (7.7%), and mood disturbance (23.1%). Other clinical presentations included seizure (38.5%), abnormal movement (23.1%), sleep disturbance (38.5%), ataxia (46.2%), stroke-like episode (15.4%), and fever (15.4%). Most patients (76.9%) had onset within < 3 months. Regarding outcomes, 1 patient who did not receive corticosteroid died from status epilepticus and septic shock. Among the 12 patients who received corticosteroid, 9 (75%) had marked improvement, 1 (8.3%) had slight improvement, and 2 (16.6%) had no clinical improvement. Seven patients (53.9%) had normal thyroid function, 4 patients (30.8%) had subclinical hypothyroidism, and 2 patients (15.4%) had subclinical hyperthyroidism. Conclusions: The results of this study revealed cognitive impairment, neuropsychiatric symptoms, seizure, ataxia, and sleep disturbance to be common manifestations of Hashimoto encephalopathy. This condition should always be considered in individuals with subacute onset of unexplained cognitive impairment or cerebellar ataxia. Laboratory and neuroimaging investigations were all found to be nonspecific in Hashimoto encephalopathy. Most patients responded well to treatment, so clinical suspicion and early diagnosis and treatment will lead to improved patient outcomes.