1.Novel Deep Learning-Based Vocal Biomarkers for Stress Detection in Koreans
Junghyun NAMKUNG ; Seok Min KIM ; Won Ik CHO ; So Young YOO ; Beomjun MIN ; Sang Yool LEE ; Ji-Hye LEE ; Heyeon PARK ; Soyoung BAIK ; Je-Yeon YUN ; Nam Soo KIM ; Jeong-Hyun KIM
Psychiatry Investigation 2024;21(11):1228-1237
Objective:
The rapid societal changes have underscored the importance of effective stress detection and management. Chronic mental stress significantly contributes to both physical and psychological illnesses. However, many individuals often remain unaware of their stress levels until they face physical health issues, highlighting the necessity for regular stress monitoring. This study aimed to investigate the effectiveness of vocal biomarkers in detecting stress levels among healthy Korean employees and to contribute to digital healthcare solutions.
Methods:
We conducted a multi-center clinical study by collecting voice recordings from 115 healthy Korean employees under both relaxed and stress-induced conditions. Stress was induced using the socially evaluated cold pressor test. The Emphasized Channel Attention, Propagation and Aggregation in Time delay neural network (ECAPA-TDNN) deep learning architecture, renowned for its advanced capabilities in analyzing person-specific voice features, was employed to develop stress prediction scores.
Results:
The proposed model achieved a 70% accuracy rate in detecting stress. This performance underscores the potential of vocal biomarkers as a convenient and effective tool for individuals to self-monitor and manage their stress levels within digital healthcare frameworks.
Conclusion
The findings emphasize the promise of voice-based mental stress assessments within the Korean population and the importance of continued research on vocal biomarkers across diverse linguistic demographics.
2.Novel Deep Learning-Based Vocal Biomarkers for Stress Detection in Koreans
Junghyun NAMKUNG ; Seok Min KIM ; Won Ik CHO ; So Young YOO ; Beomjun MIN ; Sang Yool LEE ; Ji-Hye LEE ; Heyeon PARK ; Soyoung BAIK ; Je-Yeon YUN ; Nam Soo KIM ; Jeong-Hyun KIM
Psychiatry Investigation 2024;21(11):1228-1237
Objective:
The rapid societal changes have underscored the importance of effective stress detection and management. Chronic mental stress significantly contributes to both physical and psychological illnesses. However, many individuals often remain unaware of their stress levels until they face physical health issues, highlighting the necessity for regular stress monitoring. This study aimed to investigate the effectiveness of vocal biomarkers in detecting stress levels among healthy Korean employees and to contribute to digital healthcare solutions.
Methods:
We conducted a multi-center clinical study by collecting voice recordings from 115 healthy Korean employees under both relaxed and stress-induced conditions. Stress was induced using the socially evaluated cold pressor test. The Emphasized Channel Attention, Propagation and Aggregation in Time delay neural network (ECAPA-TDNN) deep learning architecture, renowned for its advanced capabilities in analyzing person-specific voice features, was employed to develop stress prediction scores.
Results:
The proposed model achieved a 70% accuracy rate in detecting stress. This performance underscores the potential of vocal biomarkers as a convenient and effective tool for individuals to self-monitor and manage their stress levels within digital healthcare frameworks.
Conclusion
The findings emphasize the promise of voice-based mental stress assessments within the Korean population and the importance of continued research on vocal biomarkers across diverse linguistic demographics.
3.Novel Deep Learning-Based Vocal Biomarkers for Stress Detection in Koreans
Junghyun NAMKUNG ; Seok Min KIM ; Won Ik CHO ; So Young YOO ; Beomjun MIN ; Sang Yool LEE ; Ji-Hye LEE ; Heyeon PARK ; Soyoung BAIK ; Je-Yeon YUN ; Nam Soo KIM ; Jeong-Hyun KIM
Psychiatry Investigation 2024;21(11):1228-1237
Objective:
The rapid societal changes have underscored the importance of effective stress detection and management. Chronic mental stress significantly contributes to both physical and psychological illnesses. However, many individuals often remain unaware of their stress levels until they face physical health issues, highlighting the necessity for regular stress monitoring. This study aimed to investigate the effectiveness of vocal biomarkers in detecting stress levels among healthy Korean employees and to contribute to digital healthcare solutions.
Methods:
We conducted a multi-center clinical study by collecting voice recordings from 115 healthy Korean employees under both relaxed and stress-induced conditions. Stress was induced using the socially evaluated cold pressor test. The Emphasized Channel Attention, Propagation and Aggregation in Time delay neural network (ECAPA-TDNN) deep learning architecture, renowned for its advanced capabilities in analyzing person-specific voice features, was employed to develop stress prediction scores.
Results:
The proposed model achieved a 70% accuracy rate in detecting stress. This performance underscores the potential of vocal biomarkers as a convenient and effective tool for individuals to self-monitor and manage their stress levels within digital healthcare frameworks.
Conclusion
The findings emphasize the promise of voice-based mental stress assessments within the Korean population and the importance of continued research on vocal biomarkers across diverse linguistic demographics.
4.Novel Deep Learning-Based Vocal Biomarkers for Stress Detection in Koreans
Junghyun NAMKUNG ; Seok Min KIM ; Won Ik CHO ; So Young YOO ; Beomjun MIN ; Sang Yool LEE ; Ji-Hye LEE ; Heyeon PARK ; Soyoung BAIK ; Je-Yeon YUN ; Nam Soo KIM ; Jeong-Hyun KIM
Psychiatry Investigation 2024;21(11):1228-1237
Objective:
The rapid societal changes have underscored the importance of effective stress detection and management. Chronic mental stress significantly contributes to both physical and psychological illnesses. However, many individuals often remain unaware of their stress levels until they face physical health issues, highlighting the necessity for regular stress monitoring. This study aimed to investigate the effectiveness of vocal biomarkers in detecting stress levels among healthy Korean employees and to contribute to digital healthcare solutions.
Methods:
We conducted a multi-center clinical study by collecting voice recordings from 115 healthy Korean employees under both relaxed and stress-induced conditions. Stress was induced using the socially evaluated cold pressor test. The Emphasized Channel Attention, Propagation and Aggregation in Time delay neural network (ECAPA-TDNN) deep learning architecture, renowned for its advanced capabilities in analyzing person-specific voice features, was employed to develop stress prediction scores.
Results:
The proposed model achieved a 70% accuracy rate in detecting stress. This performance underscores the potential of vocal biomarkers as a convenient and effective tool for individuals to self-monitor and manage their stress levels within digital healthcare frameworks.
Conclusion
The findings emphasize the promise of voice-based mental stress assessments within the Korean population and the importance of continued research on vocal biomarkers across diverse linguistic demographics.
5.Novel Deep Learning-Based Vocal Biomarkers for Stress Detection in Koreans
Junghyun NAMKUNG ; Seok Min KIM ; Won Ik CHO ; So Young YOO ; Beomjun MIN ; Sang Yool LEE ; Ji-Hye LEE ; Heyeon PARK ; Soyoung BAIK ; Je-Yeon YUN ; Nam Soo KIM ; Jeong-Hyun KIM
Psychiatry Investigation 2024;21(11):1228-1237
Objective:
The rapid societal changes have underscored the importance of effective stress detection and management. Chronic mental stress significantly contributes to both physical and psychological illnesses. However, many individuals often remain unaware of their stress levels until they face physical health issues, highlighting the necessity for regular stress monitoring. This study aimed to investigate the effectiveness of vocal biomarkers in detecting stress levels among healthy Korean employees and to contribute to digital healthcare solutions.
Methods:
We conducted a multi-center clinical study by collecting voice recordings from 115 healthy Korean employees under both relaxed and stress-induced conditions. Stress was induced using the socially evaluated cold pressor test. The Emphasized Channel Attention, Propagation and Aggregation in Time delay neural network (ECAPA-TDNN) deep learning architecture, renowned for its advanced capabilities in analyzing person-specific voice features, was employed to develop stress prediction scores.
Results:
The proposed model achieved a 70% accuracy rate in detecting stress. This performance underscores the potential of vocal biomarkers as a convenient and effective tool for individuals to self-monitor and manage their stress levels within digital healthcare frameworks.
Conclusion
The findings emphasize the promise of voice-based mental stress assessments within the Korean population and the importance of continued research on vocal biomarkers across diverse linguistic demographics.
6.Laparoscopic Repair of Diastasis Recti: A Case Report and Literature Review
Woohyung LEE ; Jin Kyu CHO ; Jae Yool JANG ; Soon Chan HONG ; Chi Young JEONG
Journal of Minimally Invasive Surgery 2019;22(3):127-130
Diastasis recti is a state with separated aponeurosis between two recti caused by weakening of the intercrossing fibers in the linea alba and it causes abdominal protrusion. Common causes comprised of increased intraabdominal pressure, or congenital weakening of myoaponeurotic layer. We describe a patient who underwent laparoscopic repair of diastasis recti. A 30-year-old woman was referred to our outpatient department for an abdominal mass that had appeared 1 year earlier. Physical examination revealed an abdominal wall defect along the midline and computed tomography showed thinning and stretching of the linea alba. The patient underwent laparoscopic repair for diastasis recti. The stretched linea alba was approximated using interrupted sutures from the epigastrium to the suprapubic area. A dual mesh was applied below the peritoneum to prevent recurrence. The patient was discharged without complications, and was followed up for 1 year without recurrence. Laparoscopic repair could be a considerable is a treatment modality for diastasis recti.
Abdominal Wall
;
Adult
;
Female
;
Humans
;
Laparoscopy
;
Outpatients
;
Peritoneum
;
Physical Examination
;
Recurrence
;
Sutures
7.Laparoscopic Cholecystectomy in Two Patients with Situs Inversus Totalis: A Case Report.
Jae Yool JANG ; Woohyung LEE ; Jinkyu CHO ; Chi Yeong JEONG ; Soon Chan HONG
Journal of Minimally Invasive Surgery 2018;21(2):82-85
Situs inversus totalis (SIT) is a rare condition in which the viscera are transposed in a mirror image reversal. We report two cases of laparoscopic cholecystectomy (LC) performed for SIT patients. A 63-year old male patient with SIT was diagnosed with symptomatic gallstones. We performed LC by 3-port method. The patient was discharged uneventfully on postoperative day 2. A 57-year old female patient with SIT underwent LC for acute cholecystitis. Due to severe inflammation an assistant was needed. The patient was discharged uneventfully on postoperative day 3. Over 80 cases of LCs in SIT patients have been reported so far and LC has become the standard treatment. The current report confirms the safety of laparoscopy in such cases. Laparoscopic cholecystectomy can be performed safely in SIT patients if care is taken. Surgeons need to be careful of reversed anatomy and unaccustomed working hand.
Cholecystectomy, Laparoscopic*
;
Cholecystitis, Acute
;
Female
;
Gallstones
;
Hand
;
Humans
;
Inflammation
;
Laparoscopy
;
Male
;
Methods
;
Situs Inversus*
;
Surgeons
;
Viscera
8.Single Incision Laparoscopic Cholecystectomy without a Camera Operator.
YoungRok CHOI ; Ho Seong HAN ; Yoo Seok YOON ; Jae Young CHO ; Jae Yool JANG ; Han Lim CHOI ; Jae Seong JANG ; Seong Uk KWON ; Sungho KIM ; Jangkyu CHOI
Journal of Minimally Invasive Surgery 2017;20(2):63-68
PURPOSE: This study aimed to evaluate the implementation of solo surgery using a laparoscopic scope holder for single incision laparoscopic cholecystectomy (SILC). METHODS: With a glove port and a flexible high-definition scope, SILC was performed through a single trans-umbilical incisional site with CO2 pneumoperitoneum at a pressure of 12 mmHg. Fifty-eight patients who underwent solo SILC using a scope holder (Solo-SILC) were compared to 15 patients who underwent camera operator-assisted SILC (Ca-SILC) in terms of intraoperative and postoperative outcomes. RESULTS: The mean BMI and operation time were 23.0±3.6 kg/m² and 64.4±16.6 min in Ca-SILC and 25.0±3.8 kg/m² and 58.2±27.1 min in Solo-SILC, respectively (p=0.067 and p=0.410). Estimated blood loss was negligible and an additional assistant port was not required in either groups. A case of gallbladder perforation and bile leak was noted in the Ca-SILC group, and 13 cases of bile leak in the Solo-SILC group, with no significant differences (p=0.167) during the surgery. Postoperative outcomes including surgical complications, diet restriction, diarrhea and hospital stay were not significantly different except for shoulder pain (p<0.001). CONCLUSION: Even with the limitations of a small number of patients, Solo-SILC proved to be a feasible technique. To confirm the safety of solo-SILC, further studies with a larger sample size are required.
Bile
;
Cholecystectomy, Laparoscopic*
;
Diarrhea
;
Diet
;
Gallbladder
;
Humans
;
Length of Stay
;
Minimally Invasive Surgical Procedures
;
Pneumoperitoneum
;
Sample Size
;
Shoulder Pain
9.Laparoscopic resection of hilar cholangiocarcinoma.
Woohyung LEE ; Ho Seong HAN ; Yoo Seok YOON ; Jai Young CHO ; Youngrok CHOI ; Hong Kyung SHIN ; Jae Yool JANG ; Hanlim CHOI
Annals of Surgical Treatment and Research 2015;89(4):228-232
Laparoscopic resection of hilar cholangiocarcinoma is technically challenging because it involves complicated laparoscopic procedures that include laparoscopic hepatoduodenal lymphadenectomy, hemihepatectomy with caudate lobectomy, and hepaticojejunostomy. There are currently very few reports describing this type of surgery. Between August 2014 and December 2014, 5 patients underwent total laparoscopic or laparoscopic-assisted surgery for hilar cholangiocarcinoma. Two patients with type I or II hilar cholangiocarcinoma underwent radical hilar resection. Three patients with type IIIa or IIIb cholangiocarcinoma underwent extended hemihepatectomy together with caudate lobectomy. The median (range) age, operation time, blood loss, and length of hospital stay were 63 years (43-76 years), 610 minutes (410-665 minutes), 650 mL (450-1,300 mL), and 12 days (9-21 days), respectively. Four patients had a negative margin, but 1 patient was diagnosed with high-grade dysplasia on the proximal resection margin. The median tumor size was 3.0 cm. One patient experienced postoperative biliary leakage, which resolved spontaneously. Laparoscopic resection is a feasible surgical approach in selected patients with hilar cholangiocarcinoma.
Cholangiocarcinoma*
;
Humans
;
Klatskin's Tumor
;
Laparoscopy
;
Length of Stay
;
Lymph Node Excision
10.The Effect of Intestinal Permeability and Endotoxemia on the Prognosis of Acute Pancreatitis.
Young Yool KOH ; Woo Kyu JEON ; Yong Kyun CHO ; Hong Joo KIM ; Won Gil CHUNG ; Chang Uk CHON ; Tae Yun OH ; Jun Ho SHIN
Gut and Liver 2012;6(4):505-511
BACKGROUND/AIMS: Early intestinal mucosal damage plays an important role in severe acute pancreatitis (AP). Previous studies have shown that intestinal permeability (IP), serum endotoxin and cytokines contribute to the early intestinal barrier dysfunction in AP. This study explored the predictive capacity of IP, endotoxemia and cytokines as prognostic indicators in AP patients. METHODS: Eighty-seven AP patients were included in the study. The patients were classified into three groups according to the Balthazar computed tomography severity index (CTSI). We compared the biochemical parameters, including IP, serum endotoxin level and cytokine level among the three groups. The associations of IP with serum endotoxin, cytokines, CTSI, and other widely used biochemical parameters and scoring systems were also examined. RESULTS: IP, serum endotoxin, interleukin (IL-6) and tumor necrosis factor (TNF)-alpha had a positive correlation with the CTSI of AP. Endotoxin, IL-6, TNF-alpha, CTSI, the Ranson/APACHE II score, the duration of hospital stay, complications and death significantly affect IP in the AP patients. CONCLUSIONS: We believe that IP with subsidiary measurements of serum endotoxin, IL-6 and TNF-alpha may be reliable markers for predicting the prognosis of AP. Further studies that can restore and preserve gut barrier function in AP patients are warranted.
Cytokines
;
Endotoxemia
;
Endotoxins
;
Humans
;
Interleukin-6
;
Interleukins
;
Length of Stay
;
Pancreatitis
;
Permeability
;
Prognosis
;
Tumor Necrosis Factor-alpha

Result Analysis
Print
Save
E-mail