A Novel You Only Listen Once (YOLO) Deep Learning Model for Automatic Prominent Bowel Sounds Detection: Feasibility Study in Healthy Subjects
Accurate diagnosis of gastrointestinal (GI) diseases typically requires invasive procedures or imaging studies that pose the risk of various post-procedural complications or involve radiation exposure. Bowel sounds (BSs), though typically described during a GI-focused physical exam, are highly inacc...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/15/4735 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849770868613316608 |
|---|---|
| author | Rohan Kalahasty Gayathri Yerrapragada Jieun Lee Keerthy Gopalakrishnan Avneet Kaur Pratyusha Muddaloor Divyanshi Sood Charmy Parikh Jay Gohri Gianeshwaree Alias Rachna Panjwani Naghmeh Asadimanesh Rabiah Aslam Ansari Swetha Rapolu Poonguzhali Elangovan Shiva Sankari Karuppiah Vijaya M. Dasari Scott A. Helgeson Venkata S. Akshintala Shivaram P. Arunachalam |
| author_facet | Rohan Kalahasty Gayathri Yerrapragada Jieun Lee Keerthy Gopalakrishnan Avneet Kaur Pratyusha Muddaloor Divyanshi Sood Charmy Parikh Jay Gohri Gianeshwaree Alias Rachna Panjwani Naghmeh Asadimanesh Rabiah Aslam Ansari Swetha Rapolu Poonguzhali Elangovan Shiva Sankari Karuppiah Vijaya M. Dasari Scott A. Helgeson Venkata S. Akshintala Shivaram P. Arunachalam |
| author_sort | Rohan Kalahasty |
| collection | DOAJ |
| description | Accurate diagnosis of gastrointestinal (GI) diseases typically requires invasive procedures or imaging studies that pose the risk of various post-procedural complications or involve radiation exposure. Bowel sounds (BSs), though typically described during a GI-focused physical exam, are highly inaccurate and variable, with low clinical value in diagnosis. Interpretation of the acoustic characteristics of BSs, i.e., using a phonoenterogram (PEG), may aid in diagnosing various GI conditions non-invasively. Use of artificial intelligence (AI) and improvements in computational analysis can enhance the use of PEGs in different GI diseases and lead to a non-invasive, cost-effective diagnostic modality that has not been explored before. The purpose of this work was to develop an automated AI model, You Only Listen Once (YOLO), to detect prominent bowel sounds that can enable real-time analysis for future GI disease detection and diagnosis. A total of 110 2-minute PEGs sampled at 44.1 kHz were recorded using the Eko DUO<sup>®</sup> stethoscope from eight healthy volunteers at two locations, namely, left upper quadrant (LUQ) and right lower quadrant (RLQ) after IRB approval. The datasets were annotated by trained physicians, categorizing BSs as prominent or obscure using version 1.7 of Label Studio Software<sup>®</sup>. Each BS recording was split up into 375 ms segments with 200 ms overlap for real-time BS detection. Each segment was binned based on whether it contained a prominent BS, resulting in a dataset of 36,149 non-prominent segments and 6435 prominent segments. Our dataset was divided into training, validation, and test sets (60/20/20% split). A 1D-CNN augmented transformer was trained to classify these segments via the input of Mel-frequency cepstral coefficients. The developed AI model achieved area under the receiver operating curve (ROC) of 0.92, accuracy of 86.6%, precision of 86.85%, and recall of 86.08%. This shows that the 1D-CNN augmented transformer with Mel-frequency cepstral coefficients achieved creditable performance metrics, signifying the YOLO model’s capability to classify prominent bowel sounds that can be further analyzed for various GI diseases. This proof-of-concept study in healthy volunteers demonstrates that automated BS detection can pave the way for developing more intuitive and efficient AI-PEG devices that can be trained and utilized to diagnose various GI conditions. To ensure the robustness and generalizability of these findings, further investigations encompassing a broader cohort, inclusive of both healthy and disease states are needed. |
| format | Article |
| id | doaj-art-a0dcda676abd40a483222e7d6cf60ee3 |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-a0dcda676abd40a483222e7d6cf60ee32025-08-20T03:02:51ZengMDPI AGSensors1424-82202025-07-012515473510.3390/s25154735A Novel You Only Listen Once (YOLO) Deep Learning Model for Automatic Prominent Bowel Sounds Detection: Feasibility Study in Healthy SubjectsRohan Kalahasty0Gayathri Yerrapragada1Jieun Lee2Keerthy Gopalakrishnan3Avneet Kaur4Pratyusha Muddaloor5Divyanshi Sood6Charmy Parikh7Jay Gohri8Gianeshwaree Alias Rachna Panjwani9Naghmeh Asadimanesh10Rabiah Aslam Ansari11Swetha Rapolu12Poonguzhali Elangovan13Shiva Sankari Karuppiah14Vijaya M. Dasari15Scott A. Helgeson16Venkata S. Akshintala17Shivaram P. Arunachalam18Digital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USADepartment of Internal Medicine, Wright Medical Center, Scranton, PA 18503, USADepartment of Internal Medicine, MedStar Union Memorial Hospital, Baltimore, MD 21218, USADepartment of Internal Medicine, Lower Bucks Hospital, Bristol, PA 19007, USADepartment of Internal Medicine, UCHealth Parkview Medical Center, Pueblo, CO 81003, USADepartment of Internal Medicine, Mercy Catholic Medical Center, Darby, PA 19023, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USANorth Texas Gastroenterology, Denton, TX 76201, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USADivision of Gastroenterology & Hepatology, Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD 21287, USADigital Engineering & Artificial Intelligence Laboratory (DEAL), Mayo Clinic, Jacksonville, FL 32224, USAAccurate diagnosis of gastrointestinal (GI) diseases typically requires invasive procedures or imaging studies that pose the risk of various post-procedural complications or involve radiation exposure. Bowel sounds (BSs), though typically described during a GI-focused physical exam, are highly inaccurate and variable, with low clinical value in diagnosis. Interpretation of the acoustic characteristics of BSs, i.e., using a phonoenterogram (PEG), may aid in diagnosing various GI conditions non-invasively. Use of artificial intelligence (AI) and improvements in computational analysis can enhance the use of PEGs in different GI diseases and lead to a non-invasive, cost-effective diagnostic modality that has not been explored before. The purpose of this work was to develop an automated AI model, You Only Listen Once (YOLO), to detect prominent bowel sounds that can enable real-time analysis for future GI disease detection and diagnosis. A total of 110 2-minute PEGs sampled at 44.1 kHz were recorded using the Eko DUO<sup>®</sup> stethoscope from eight healthy volunteers at two locations, namely, left upper quadrant (LUQ) and right lower quadrant (RLQ) after IRB approval. The datasets were annotated by trained physicians, categorizing BSs as prominent or obscure using version 1.7 of Label Studio Software<sup>®</sup>. Each BS recording was split up into 375 ms segments with 200 ms overlap for real-time BS detection. Each segment was binned based on whether it contained a prominent BS, resulting in a dataset of 36,149 non-prominent segments and 6435 prominent segments. Our dataset was divided into training, validation, and test sets (60/20/20% split). A 1D-CNN augmented transformer was trained to classify these segments via the input of Mel-frequency cepstral coefficients. The developed AI model achieved area under the receiver operating curve (ROC) of 0.92, accuracy of 86.6%, precision of 86.85%, and recall of 86.08%. This shows that the 1D-CNN augmented transformer with Mel-frequency cepstral coefficients achieved creditable performance metrics, signifying the YOLO model’s capability to classify prominent bowel sounds that can be further analyzed for various GI diseases. This proof-of-concept study in healthy volunteers demonstrates that automated BS detection can pave the way for developing more intuitive and efficient AI-PEG devices that can be trained and utilized to diagnose various GI conditions. To ensure the robustness and generalizability of these findings, further investigations encompassing a broader cohort, inclusive of both healthy and disease states are needed.https://www.mdpi.com/1424-8220/25/15/4735GI diseasesbowel soundsphonoenterogram (PEG)You Only Listen Once (YOLO)artificial intelligenceMel-frequency Cepstral Coefficients (MFCC) |
| spellingShingle | Rohan Kalahasty Gayathri Yerrapragada Jieun Lee Keerthy Gopalakrishnan Avneet Kaur Pratyusha Muddaloor Divyanshi Sood Charmy Parikh Jay Gohri Gianeshwaree Alias Rachna Panjwani Naghmeh Asadimanesh Rabiah Aslam Ansari Swetha Rapolu Poonguzhali Elangovan Shiva Sankari Karuppiah Vijaya M. Dasari Scott A. Helgeson Venkata S. Akshintala Shivaram P. Arunachalam A Novel You Only Listen Once (YOLO) Deep Learning Model for Automatic Prominent Bowel Sounds Detection: Feasibility Study in Healthy Subjects Sensors GI diseases bowel sounds phonoenterogram (PEG) You Only Listen Once (YOLO) artificial intelligence Mel-frequency Cepstral Coefficients (MFCC) |
| title | A Novel You Only Listen Once (YOLO) Deep Learning Model for Automatic Prominent Bowel Sounds Detection: Feasibility Study in Healthy Subjects |
| title_full | A Novel You Only Listen Once (YOLO) Deep Learning Model for Automatic Prominent Bowel Sounds Detection: Feasibility Study in Healthy Subjects |
| title_fullStr | A Novel You Only Listen Once (YOLO) Deep Learning Model for Automatic Prominent Bowel Sounds Detection: Feasibility Study in Healthy Subjects |
| title_full_unstemmed | A Novel You Only Listen Once (YOLO) Deep Learning Model for Automatic Prominent Bowel Sounds Detection: Feasibility Study in Healthy Subjects |
| title_short | A Novel You Only Listen Once (YOLO) Deep Learning Model for Automatic Prominent Bowel Sounds Detection: Feasibility Study in Healthy Subjects |
| title_sort | novel you only listen once yolo deep learning model for automatic prominent bowel sounds detection feasibility study in healthy subjects |
| topic | GI diseases bowel sounds phonoenterogram (PEG) You Only Listen Once (YOLO) artificial intelligence Mel-frequency Cepstral Coefficients (MFCC) |
| url | https://www.mdpi.com/1424-8220/25/15/4735 |
| work_keys_str_mv | AT rohankalahasty anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT gayathriyerrapragada anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT jieunlee anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT keerthygopalakrishnan anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT avneetkaur anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT pratyushamuddaloor anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT divyanshisood anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT charmyparikh anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT jaygohri anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT gianeshwareealiasrachnapanjwani anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT naghmehasadimanesh anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT rabiahaslamansari anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT swetharapolu anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT poonguzhalielangovan anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT shivasankarikaruppiah anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT vijayamdasari anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT scottahelgeson anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT venkatasakshintala anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT shivaramparunachalam anovelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT rohankalahasty novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT gayathriyerrapragada novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT jieunlee novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT keerthygopalakrishnan novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT avneetkaur novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT pratyushamuddaloor novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT divyanshisood novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT charmyparikh novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT jaygohri novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT gianeshwareealiasrachnapanjwani novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT naghmehasadimanesh novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT rabiahaslamansari novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT swetharapolu novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT poonguzhalielangovan novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT shivasankarikaruppiah novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT vijayamdasari novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT scottahelgeson novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT venkatasakshintala novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects AT shivaramparunachalam novelyouonlylistenonceyolodeeplearningmodelforautomaticprominentbowelsoundsdetectionfeasibilitystudyinhealthysubjects |