Clinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patients
Muscle ultrasound has been shown to be a valid and safe imaging modality to assess muscle wasting in critically ill patients in the intensive care unit (ICU). This typically involves manual delineation to measure the rectus femoris cross-sectional area (RFCSA), which is a subjective, time-consuming,...
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Journal article |
| Sprog: | English |
| Udgivet: |
Nature Research
2024
|
| _version_ | 1826313433157468160 |
|---|---|
| author | Nhat, PTH Van Hao, N Yen, LM Anh, NH Khiem, DP Kerdegari, H Phuong, LT Hoang, VT Ngoc, NT Thu, LNM Trung, TN Pisani, L Razavi, R Yacoub, S Van Vinh Chau, N King, AP Thwaites, L Denehy, L Gomez, A |
| author_facet | Nhat, PTH Van Hao, N Yen, LM Anh, NH Khiem, DP Kerdegari, H Phuong, LT Hoang, VT Ngoc, NT Thu, LNM Trung, TN Pisani, L Razavi, R Yacoub, S Van Vinh Chau, N King, AP Thwaites, L Denehy, L Gomez, A |
| author_sort | Nhat, PTH |
| collection | OXFORD |
| description | Muscle ultrasound has been shown to be a valid and safe imaging modality to assess muscle wasting in critically ill patients in the intensive care unit (ICU). This typically involves manual delineation to measure the rectus femoris cross-sectional area (RFCSA), which is a subjective, time-consuming, and laborious task that requires significant expertise. We aimed to develop and evaluate an AI tool that performs automated recognition and measurement of RFCSA to support non-expert operators in measurement of the RFCSA using muscle ultrasound. Twenty patients were recruited between Feb 2023 and July 2023 and were randomized sequentially to operators using AI (n = 10) or non-AI (n = 10). Muscle loss during ICU stay was similar for both methods: 26 ± 15% for AI and 23 ± 11% for the non-AI, respectively (p = 0.13). In total 59 ultrasound examinations were carried out (30 without AI and 29 with AI). When assisted by our AI tool, the operators showed less variability between measurements with higher intraclass correlation coefficients (ICCs 0.999 95% CI 0.998–0.999 vs. 0.982 95% CI 0.962–0.993) and lower Bland Altman limits of agreement (± 1.9% vs. ± 6.6%) compared to not using the AI tool. The time spent on scans reduced significantly from a median of 19.6 min (IQR 16.9–21.7) to 9.4 min (IQR 7.2–11.7) compared to when using the AI tool (p < 0.001). AI-assisted muscle ultrasound removes the need for manual tracing, increases reproducibility and saves time. This system may aid monitoring muscle size in ICU patients assisting rehabilitation programmes. |
| first_indexed | 2024-09-25T04:12:56Z |
| format | Journal article |
| id | oxford-uuid:e972e6b4-8d1d-4c3f-86f3-cae1328dbb71 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:12:56Z |
| publishDate | 2024 |
| publisher | Nature Research |
| record_format | dspace |
| spelling | oxford-uuid:e972e6b4-8d1d-4c3f-86f3-cae1328dbb712024-06-27T20:11:04ZClinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patientsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:e972e6b4-8d1d-4c3f-86f3-cae1328dbb71EnglishJisc Publications RouterNature Research2024Nhat, PTHVan Hao, NYen, LMAnh, NHKhiem, DPKerdegari, HPhuong, LTHoang, VTNgoc, NTThu, LNMTrung, TNPisani, LRazavi, RYacoub, SVan Vinh Chau, NKing, APThwaites, LDenehy, LGomez, AMuscle ultrasound has been shown to be a valid and safe imaging modality to assess muscle wasting in critically ill patients in the intensive care unit (ICU). This typically involves manual delineation to measure the rectus femoris cross-sectional area (RFCSA), which is a subjective, time-consuming, and laborious task that requires significant expertise. We aimed to develop and evaluate an AI tool that performs automated recognition and measurement of RFCSA to support non-expert operators in measurement of the RFCSA using muscle ultrasound. Twenty patients were recruited between Feb 2023 and July 2023 and were randomized sequentially to operators using AI (n = 10) or non-AI (n = 10). Muscle loss during ICU stay was similar for both methods: 26 ± 15% for AI and 23 ± 11% for the non-AI, respectively (p = 0.13). In total 59 ultrasound examinations were carried out (30 without AI and 29 with AI). When assisted by our AI tool, the operators showed less variability between measurements with higher intraclass correlation coefficients (ICCs 0.999 95% CI 0.998–0.999 vs. 0.982 95% CI 0.962–0.993) and lower Bland Altman limits of agreement (± 1.9% vs. ± 6.6%) compared to not using the AI tool. The time spent on scans reduced significantly from a median of 19.6 min (IQR 16.9–21.7) to 9.4 min (IQR 7.2–11.7) compared to when using the AI tool (p < 0.001). AI-assisted muscle ultrasound removes the need for manual tracing, increases reproducibility and saves time. This system may aid monitoring muscle size in ICU patients assisting rehabilitation programmes. |
| spellingShingle | Nhat, PTH Van Hao, N Yen, LM Anh, NH Khiem, DP Kerdegari, H Phuong, LT Hoang, VT Ngoc, NT Thu, LNM Trung, TN Pisani, L Razavi, R Yacoub, S Van Vinh Chau, N King, AP Thwaites, L Denehy, L Gomez, A Clinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patients |
| title | Clinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patients |
| title_full | Clinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patients |
| title_fullStr | Clinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patients |
| title_full_unstemmed | Clinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patients |
| title_short | Clinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patients |
| title_sort | clinical evaluation of ai assisted muscle ultrasound for monitoring muscle wasting in icu patients |
| work_keys_str_mv | AT nhatpth clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT vanhaon clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT yenlm clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT anhnh clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT khiemdp clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT kerdegarih clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT phuonglt clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT hoangvt clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT ngocnt clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT thulnm clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT trungtn clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT pisanil clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT razavir clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT yacoubs clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT vanvinhchaun clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT kingap clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT thwaitesl clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT denehyl clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients AT gomeza clinicalevaluationofaiassistedmuscleultrasoundformonitoringmusclewastinginicupatients |