Sodium Intake Estimation in Hospital Patients Using AI-Based Imaging: Prospective Pilot Study
BackgroundMeasurement of sodium intake in hospitalized patients is critical for their care. In this study, artificial intelligence (AI)–based imaging was performed to determine sodium intake in these patients. ObjectiveThe applicability of a diet management system...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2024-02-01
|
| Series: | JMIR Formative Research |
| Online Access: | https://formative.jmir.org/2024/1/e48690 |
| _version_ | 1797305003018289152 |
|---|---|
| author | Jiwon Ryu Sejoong Kim Yejee Lim Jung Hun Ohn Sun-wook Kim Jae Ho Cho Hee Sun Park Jongchan Lee Eun Sun Kim Nak-Hyun Kim Ji Eun Song Su Hwan Kim Eui-Chang Suh Doniyorjon Mukhtorov Jung Hyun Park Sung Kweon Kim Hye Won Kim |
| author_facet | Jiwon Ryu Sejoong Kim Yejee Lim Jung Hun Ohn Sun-wook Kim Jae Ho Cho Hee Sun Park Jongchan Lee Eun Sun Kim Nak-Hyun Kim Ji Eun Song Su Hwan Kim Eui-Chang Suh Doniyorjon Mukhtorov Jung Hyun Park Sung Kweon Kim Hye Won Kim |
| author_sort | Jiwon Ryu |
| collection | DOAJ |
| description |
BackgroundMeasurement of sodium intake in hospitalized patients is critical for their care. In this study, artificial intelligence (AI)–based imaging was performed to determine sodium intake in these patients.
ObjectiveThe applicability of a diet management system was evaluated using AI-based imaging to assess the sodium content of diets prescribed for hospitalized patients.
MethodsBased on the information on the already investigated nutrients and quantity of food, consumed sodium was analyzed through photographs obtained before and after a meal. We used a hybrid model that first leveraged the capabilities of the You Only Look Once, version 4 (YOLOv4) architecture for the detection of food and dish areas in images. Following this initial detection, 2 distinct approaches were adopted for further classification: a custom ResNet-101 model and a hyperspectral imaging-based technique. These methodologies focused on accurate classification and estimation of the food quantity and sodium amount, respectively.
The 24-hour urine sodium (UNa) value was measured as a reference for evaluating the sodium intake.
ResultsResults were analyzed using complete data from 25 participants out of the total 54 enrolled individuals. The median sodium intake calculated by the AI algorithm (AI-Na) was determined to be 2022.7 mg per day/person (adjusted by administered fluids). A significant correlation was observed between AI-Na and 24-hour UNa, while there was a notable disparity between them. A regression analysis, considering patient characteristics (eg, gender, age, renal function, the use of diuretics, and administered fluids) yielded a formula accounting for the interaction between AI-Na and 24-hour UNa. Consequently, it was concluded that AI-Na holds clinical significance in estimating salt intake for hospitalized patients using images without the need for 24-hour UNa measurements. The degree of correlation between AI-Na and 24-hour UNa was found to vary depending on the use of diuretics.
ConclusionsThis study highlights the potential of AI-based imaging for determining sodium intake in hospitalized patients. |
| first_indexed | 2024-03-08T00:19:32Z |
| format | Article |
| id | doaj.art-f0bfe61dc6d54a659ac07c946126427c |
| institution | Directory Open Access Journal |
| issn | 2561-326X |
| language | English |
| last_indexed | 2024-03-08T00:19:32Z |
| publishDate | 2024-02-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Formative Research |
| spelling | doaj.art-f0bfe61dc6d54a659ac07c946126427c2024-02-16T14:15:54ZengJMIR PublicationsJMIR Formative Research2561-326X2024-02-018e4869010.2196/48690Sodium Intake Estimation in Hospital Patients Using AI-Based Imaging: Prospective Pilot StudyJiwon Ryuhttps://orcid.org/0000-0002-2372-8948Sejoong Kimhttps://orcid.org/0000-0002-7238-9962Yejee Limhttps://orcid.org/0000-0002-3540-0202Jung Hun Ohnhttps://orcid.org/0000-0001-5415-4505Sun-wook Kimhttps://orcid.org/0000-0003-1506-7366Jae Ho Chohttps://orcid.org/0000-0002-8391-0557Hee Sun Parkhttps://orcid.org/0000-0003-4408-507XJongchan Leehttps://orcid.org/0000-0001-7862-3257Eun Sun Kimhttps://orcid.org/0000-0002-6024-5777Nak-Hyun Kimhttps://orcid.org/0000-0003-1134-1364Ji Eun Songhttps://orcid.org/0009-0001-5227-4922Su Hwan Kimhttps://orcid.org/0000-0002-8465-3564Eui-Chang Suhhttps://orcid.org/0009-0004-6658-2426Doniyorjon Mukhtorovhttps://orcid.org/0009-0007-0485-650XJung Hyun Parkhttps://orcid.org/0009-0003-4641-5324Sung Kweon Kimhttps://orcid.org/0009-0001-8724-4037Hye Won Kimhttps://orcid.org/0000-0001-9450-3626 BackgroundMeasurement of sodium intake in hospitalized patients is critical for their care. In this study, artificial intelligence (AI)–based imaging was performed to determine sodium intake in these patients. ObjectiveThe applicability of a diet management system was evaluated using AI-based imaging to assess the sodium content of diets prescribed for hospitalized patients. MethodsBased on the information on the already investigated nutrients and quantity of food, consumed sodium was analyzed through photographs obtained before and after a meal. We used a hybrid model that first leveraged the capabilities of the You Only Look Once, version 4 (YOLOv4) architecture for the detection of food and dish areas in images. Following this initial detection, 2 distinct approaches were adopted for further classification: a custom ResNet-101 model and a hyperspectral imaging-based technique. These methodologies focused on accurate classification and estimation of the food quantity and sodium amount, respectively. The 24-hour urine sodium (UNa) value was measured as a reference for evaluating the sodium intake. ResultsResults were analyzed using complete data from 25 participants out of the total 54 enrolled individuals. The median sodium intake calculated by the AI algorithm (AI-Na) was determined to be 2022.7 mg per day/person (adjusted by administered fluids). A significant correlation was observed between AI-Na and 24-hour UNa, while there was a notable disparity between them. A regression analysis, considering patient characteristics (eg, gender, age, renal function, the use of diuretics, and administered fluids) yielded a formula accounting for the interaction between AI-Na and 24-hour UNa. Consequently, it was concluded that AI-Na holds clinical significance in estimating salt intake for hospitalized patients using images without the need for 24-hour UNa measurements. The degree of correlation between AI-Na and 24-hour UNa was found to vary depending on the use of diuretics. ConclusionsThis study highlights the potential of AI-based imaging for determining sodium intake in hospitalized patients.https://formative.jmir.org/2024/1/e48690 |
| spellingShingle | Jiwon Ryu Sejoong Kim Yejee Lim Jung Hun Ohn Sun-wook Kim Jae Ho Cho Hee Sun Park Jongchan Lee Eun Sun Kim Nak-Hyun Kim Ji Eun Song Su Hwan Kim Eui-Chang Suh Doniyorjon Mukhtorov Jung Hyun Park Sung Kweon Kim Hye Won Kim Sodium Intake Estimation in Hospital Patients Using AI-Based Imaging: Prospective Pilot Study JMIR Formative Research |
| title | Sodium Intake Estimation in Hospital Patients Using AI-Based Imaging: Prospective Pilot Study |
| title_full | Sodium Intake Estimation in Hospital Patients Using AI-Based Imaging: Prospective Pilot Study |
| title_fullStr | Sodium Intake Estimation in Hospital Patients Using AI-Based Imaging: Prospective Pilot Study |
| title_full_unstemmed | Sodium Intake Estimation in Hospital Patients Using AI-Based Imaging: Prospective Pilot Study |
| title_short | Sodium Intake Estimation in Hospital Patients Using AI-Based Imaging: Prospective Pilot Study |
| title_sort | sodium intake estimation in hospital patients using ai based imaging prospective pilot study |
| url | https://formative.jmir.org/2024/1/e48690 |
| work_keys_str_mv | AT jiwonryu sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT sejoongkim sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT yejeelim sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT junghunohn sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT sunwookkim sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT jaehocho sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT heesunpark sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT jongchanlee sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT eunsunkim sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT nakhyunkim sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT jieunsong sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT suhwankim sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT euichangsuh sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT doniyorjonmukhtorov sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT junghyunpark sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT sungkweonkim sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy AT hyewonkim sodiumintakeestimationinhospitalpatientsusingaibasedimagingprospectivepilotstudy |