Non-Cochrane · DTA · PM41530736
Application of artificial intelligence and radiomics in the prediction of lymph node metastasis and tumour grading of oral cancer - a systematic review and meta analysis.
Mohideen Khadijah, Ghosh Snehashish, Krithika Chandrasekaran, et al. · BMC oral health · 2026 · PubMed · doi:10.1186/s12903-026-07658-3
Findings
Population Patients with oral or oropharyngeal squamous cell carcinoma
80 findings
| All AI models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled specificity for lymph node metastasis | Specificity 0.91 [0.87, 0.93] GRADE not reported 29 studies |
| AI (ML/DL) radiomics prediction models | Not specified | Pooled false positive rate for prediction of lymph node metastasis | False positive rate 0.09 [0.07, 0.15] GRADE not reported 29 studies |
| All AI models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled diagnostic odds ratio for lymph node metastasis | DOR 56.58 [21.68, 91.48] GRADE not reported 29 studies |
| AI (ML/DL) radiomics prediction models | Not specified | Pooled logit of sensitivity for prediction of lymph node metastasis | logit(sensitivity) 2.01 [1.40, 2.50] GRADE not reported 29 studies |
| All AI models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled positive likelihood ratio for lymph node metastasis | LR+ 9.13 [5.8, 12.45] GRADE not reported 29 studies |
| All AI models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled sensitivity for lymph node metastasis | Sensitivity 0.86 [0.8, 0.9] GRADE not reported 29 studies |
| All AI models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled negative likelihood ratio for lymph node metastasis | LR- 0.16 [0.11, 0.22] GRADE not reported 29 studies |
| All AI models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled area under the SROC curve for lymph node metastasis | AUC 0.87 [0.54, 0.99] GRADE not reported 29 studies |
| Machine learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled specificity for lymph node metastasis ML models | Specificity 0.89 [0.83, 0.93] GRADE not reported 21 studies |
| AI radiomics prediction models: ML models | Not specified | Pooled logit of sensitivity for prediction of lymph node metastasis Type of AI model: machine learning | logit(sensitivity) 1.64 [1.14, 2.15] GRADE not reported 21 studies |
| AI radiomics prediction models: ML models | Not specified | Pooled false positive rate for prediction of lymph node metastasis Type of AI model: machine learning | False positive rate 0.11 [0.07, 0.17] GRADE not reported 21 studies |
| Machine learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled negative likelihood ratio for lymph node metastasis ML models | LR- 0.182 [0.1, 0.26] GRADE not reported 21 studies |
| Machine learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled diagnostic odds ratio for lymph node metastasis ML models | DOR 41.14 [7.23, 75.04] GRADE not reported 21 studies |
| Machine learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled positive likelihood ratio for lymph node metastasis ML models | LR+ 7.5 [3.91, 11.09] GRADE not reported 21 studies |
| Machine learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled area under the SROC curve for lymph node metastasis ML models | AUC 0.85 [0.54, 0.98] GRADE not reported 21 studies |
| Machine learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled sensitivity for lymph node metastasis ML models | Sensitivity 0.84 [0.76, 0.9] GRADE not reported 21 studies |
| Deep learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled specificity for lymph node metastasis DL models | Specificity 0.91 [0.86, 0.94] GRADE not reported 13 studies |
| Deep learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled area under the SROC curve for lymph node metastasis DL models | AUC 0.9 [0.76, 0.99] GRADE not reported 13 studies |
| AI radiomics prediction models: DL models | Not specified | Pooled logit of sensitivity for prediction of lymph node metastasis Type of AI model: deep learning | logit(sensitivity) 2.01 [1.45, 2.56] GRADE not reported 13 studies |
| Deep learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled sensitivity for lymph node metastasis DL models | Sensitivity 0.88 [0.81, 0.93] GRADE not reported 13 studies |
| Deep learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled negative likelihood ratio for lymph node metastasis DL models | LR- 0.13 [0.07, 0.2] GRADE not reported 13 studies |
| Deep learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled positive likelihood ratio for lymph node metastasis DL models | LR+ 9.5 [5.18, 13.81] GRADE not reported 13 studies |
| AI radiomics prediction models: DL models | Not specified | Pooled false positive rate for prediction of lymph node metastasis Type of AI model: deep learning | False positive rate 0.09 [0.06, 0.14] GRADE not reported 13 studies |
| Deep learning models: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled diagnostic odds ratio for lymph node metastasis DL models | DOR 72.81 [15.97, 129.66] GRADE not reported 13 studies |
| AI models on CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled negative likelihood ratio for lymph node metastasis CT imaging | LR- 0.12 [0.03, 0.2] GRADE not reported 12 studies |
| AI models on CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled positive likelihood ratio for lymph node metastasis CT imaging | LR+ 14.21 [0.79, 27.62] GRADE not reported 12 studies |
| AI models on CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled diagnostic odds ratio for lymph node metastasis CT imaging | DOR 123.07 [55.42, 201.56] GRADE not reported 12 studies |
| AI models on CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled sensitivity for lymph node metastasis CT imaging | Sensitivity 0.89 [0.79, 0.95] GRADE not reported 12 studies |
| AI radiomics prediction models: CT-based models | Not specified | Pooled false positive rate for prediction of lymph node metastasis Image modality: CT | False positive rate 0.06 [0.03, 0.15] GRADE not reported 12 studies |
| AI models on CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled specificity for lymph node metastasis CT imaging | Specificity 0.94 [0.85, 0.98] GRADE not reported 12 studies |
| AI radiomics prediction models: CT-based models | Not specified | Pooled logit of sensitivity for prediction of lymph node metastasis Image modality: CT | logit(sensitivity) 2.11 [1.31, 2.91] GRADE not reported 12 studies |
| AI models on CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled area under the SROC curve for lymph node metastasis CT imaging | AUC 0.89 [0.76, 0.98] GRADE not reported 12 studies |
| AI models on PET-CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled diagnostic odds ratio for lymph node metastasis PET-CT imaging | DOR 80.32 [23.66, 174.29] GRADE not reported 6 studies |
| AI models on PET-CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled area under the SROC curve for lymph node metastasis PET-CT imaging | AUC 0.93 [0.79, 0.99] GRADE not reported 6 studies |
| AI models on PET-CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled specificity for lymph node metastasis PET-CT imaging | Specificity 0.9 [0.82, 0.95] GRADE not reported 6 studies |
| AI models on PET-CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled positive likelihood ratio for lymph node metastasis PET-CT imaging | LR+ 8.92 [3.24, 14.6] GRADE not reported 6 studies |
| AI radiomics prediction models: PET-CT-based models | Not specified | Pooled false positive rate for prediction of lymph node metastasis Image modality: PET-CT | False positive rate 0.1 [0.05, 0.18] GRADE not reported 6 studies |
| AI models on PET-CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled sensitivity for lymph node metastasis PET-CT imaging | Sensitivity 0.9 [0.79, 0.96] GRADE not reported 6 studies |
| AI models on PET-CT imaging: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled negative likelihood ratio for lymph node metastasis PET-CT imaging | LR- 0.11 [0.02, 0.2] GRADE not reported 6 studies |
| AI radiomics prediction models: PET-CT-based models | Not specified | Pooled logit of sensitivity for prediction of lymph node metastasis Image modality: PET-CT | logit(sensitivity) 2.20 [1.33, 3.07] GRADE not reported 6 studies |
| AI models on MRI: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled diagnostic odds ratio for lymph node metastasis MRI | DOR 15.13 [2.69, 27.57] GRADE not reported 5 studies |
| AI models on MRI: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled sensitivity for lymph node metastasis MRI | Sensitivity 0.73 [0.65, 0.79] GRADE not reported 5 studies |
| AI models on MRI: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled specificity for lymph node metastasis MRI | Specificity 0.85 [0.77, 0.91] GRADE not reported 5 studies |
| AI radiomics prediction models: MRI-based models | Not specified | Pooled logit of sensitivity for prediction of lymph node metastasis Image modality: MRI | logit(sensitivity) 0.97 [0.60, 1.34] GRADE not reported 5 studies |
| AI models on MRI: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled positive likelihood ratio for lymph node metastasis MRI | LR+ 4.88 [2.36, 7.4] GRADE not reported 5 studies |
| AI models on MRI: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled area under the SROC curve for lymph node metastasis MRI | AUC 0.81 [0.66, 0.87] GRADE not reported 5 studies |
| AI radiomics prediction models: MRI-based models | Not specified | Pooled false positive rate for prediction of lymph node metastasis Image modality: MRI | False positive rate 0.15 [0.09, 0.23] GRADE not reported 5 studies |
| AI models on MRI: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled negative likelihood ratio for lymph node metastasis MRI | LR- 0.32 [0.22, 0.43] GRADE not reported 5 studies |
| AI models on histopathology images: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled negative likelihood ratio for lymph node metastasis Histopathology (HP) images | LR- 0.2 [0.06, 0.34] GRADE not reported 8 studies |
| AI radiomics prediction models: Histopathology (HP) image-based models | Not specified | Pooled logit of sensitivity for prediction of lymph node metastasis Image modality: histopathology | logit(sensitivity) 1.62 [0.8, 2.44] GRADE not reported 8 studies |
| AI models on histopathology images: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled area under the SROC curve for lymph node metastasis Histopathology (HP) images | AUC 0.8 [0.54, 0.96] GRADE not reported 8 studies |
| AI radiomics prediction models: Histopathology (HP) image-based models | Not specified | Pooled false positive rate for prediction of lymph node metastasis Image modality: histopathology | False positive rate 0.16 [0.1, 0.26] GRADE not reported 8 studies |
| AI models on histopathology images: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled diagnostic odds ratio for lymph node metastasis Histopathology (HP) images | DOR 25.69 [10.28, 51.66] GRADE not reported 8 studies |
| AI models on histopathology images: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled sensitivity for lymph node metastasis Histopathology (HP) images | Sensitivity 0.84 [0.69, 0.92] GRADE not reported 8 studies |
| AI models on histopathology images: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled specificity for lymph node metastasis Histopathology (HP) images | Specificity 0.84 [0.74, 0.9] GRADE not reported 8 studies |
| AI models on histopathology images: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled positive likelihood ratio for lymph node metastasis Histopathology (HP) images | LR+ 5.08 [2.55, 7.62] GRADE not reported 8 studies |
| AI models assessing the tumour site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled area under the SROC curve for lymph node metastasis Tumour as target site | AUC 0.84 [0.54, 0.96] GRADE not reported 20 studies |
| AI models assessing the tumour site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled specificity for lymph node metastasis Tumour as target site | Specificity 0.88 [0.82, 0.92] GRADE not reported 20 studies |
| AI models assessing the tumour site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled positive likelihood ratio for lymph node metastasis Tumour as target site | LR+ 7.03 [3.77, 10.3] GRADE not reported 20 studies |
| AI radiomics prediction models: Models targeting the tumour site | Not specified | Pooled false positive rate for prediction of lymph node metastasis Target site: tumour | False positive rate 0.12 [0.08, 0.18] GRADE not reported 20 studies |
| AI models assessing the tumour site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled sensitivity for lymph node metastasis Tumour as target site | Sensitivity 0.84 [0.76, 0.9] GRADE not reported 20 studies |
| AI radiomics prediction models: Models targeting the tumour site | Not specified | Pooled logit of sensitivity for prediction of lymph node metastasis Target site: tumour | logit(sensitivity) 1.68 [1.16, 2.21] GRADE not reported 20 studies |
| AI models assessing the tumour site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled negative likelihood ratio for lymph node metastasis Tumour as target site | LR- 0.18 [0.09, 0.26] GRADE not reported 20 studies |
| AI models assessing the tumour site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled diagnostic odds ratio for lymph node metastasis Tumour as target site | DOR 39.41 [5.81, 73.01] GRADE not reported 20 studies |
| AI models assessing the lymph node site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled negative likelihood ratio for lymph node metastasis Lymph node as target site | LR- 0.14 [0.07, 0.2] GRADE not reported 14 studies |
| AI models assessing the lymph node site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled specificity for lymph node metastasis Lymph node as target site | Specificity 0.92 [0.87, 0.95] GRADE not reported 14 studies |
| AI models assessing the lymph node site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled positive likelihood ratio for lymph node metastasis Lymph node as target site | LR+ 10.32 [5.32, 15.31] GRADE not reported 14 studies |
| AI models assessing the lymph node site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled sensitivity for lymph node metastasis Lymph node as target site | Sensitivity 0.88 [0.8, 0.92] GRADE not reported 14 studies |
| AI models assessing the lymph node site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled diagnostic odds ratio for lymph node metastasis Lymph node as target site | DOR 75.31 [18.04, 132.57] GRADE not reported 14 studies |
| AI models assessing the lymph node site: machine learning or deep learning radiomics prediction of lymph node metastasis | Not specified (reference standard not stated) | Pooled area under the SROC curve for lymph node metastasis Lymph node as target site | AUC 0.9 [0.66, 0.99] GRADE not reported 14 studies |
| AI radiomics prediction models: Models targeting the lymph node site | Not specified | Pooled false positive rate for prediction of lymph node metastasis Target site: lymph node | False positive rate 0.09 [0.05, 0.14] GRADE not reported 14 studies |
| AI radiomics prediction models: Models targeting the lymph node site | Not specified | Pooled logit of sensitivity for prediction of lymph node metastasis Target site: lymph node | logit(sensitivity) 1.94 [1.39, 2.5] GRADE not reported 14 studies |
| All AI models: machine learning or deep learning radiomics prediction of histopathological grade of OSCC | Not specified (reference standard not stated) | Pooled positive likelihood ratio for histopathological grade of OSCC | LR+ 8.71 [5, 22.41] GRADE not reported 4 studies |
| AI (ML/DL) radiomics prediction models | Not specified | Pooled logit of sensitivity for prediction of histopathological grade of OSCC | logit(sensitivity) 2.03 [0.15, 3.91] GRADE not reported 4 studies |
| All AI models: machine learning or deep learning radiomics prediction of histopathological grade of OSCC | Not specified (reference standard not stated) | Pooled negative likelihood ratio for histopathological grade of OSCC | LR- 0.25 [0.14, 0.37] GRADE not reported 4 studies |
| All AI models: machine learning or deep learning radiomics prediction of histopathological grade of OSCC | Not specified (reference standard not stated) | Pooled area under the SROC curve for histopathological grade of OSCC | AUC 0.86 [0.74, 0.94] GRADE not reported 4 studies |
| All AI models: machine learning or deep learning radiomics prediction of histopathological grade of OSCC | Not specified (reference standard not stated) | Pooled sensitivity for histopathological grade of OSCC | Sensitivity 0.88 [0.54, 0.98] GRADE not reported 4 studies |
| All AI models: machine learning or deep learning radiomics prediction of histopathological grade of OSCC | Not specified (reference standard not stated) | Pooled specificity for histopathological grade of OSCC | Specificity 0.82 [0.76, 0.87] GRADE not reported 4 studies |
| All AI models: machine learning or deep learning radiomics prediction of histopathological grade of OSCC | Not specified (reference standard not stated) | Pooled diagnostic odds ratio for histopathological grade of OSCC | DOR 34.38 [24.24, 103] GRADE not reported 4 studies |
| AI (ML/DL) radiomics prediction models | Not specified | Pooled false positive rate for prediction of histopathological grade of OSCC | False positive rate 0.18 [0.13, 0.24] GRADE not reported 4 studies |
Included primary studies 72
Open in Studies| Study | Year | Also included by | Outcomes it informs here | Trial data |
|---|---|---|---|---|
| Wang 2022 Magnetic Resonance Imaging-Based Radiomics Features Associated with Depth of Invasion Predicted Lymph Node Metastasis and Prognosis in… PMID:34888985 | 2022 | 2 other reviews | not stated | not extracted yet |
| Yuan 2021 Machine learning-based MRI texture analysis to predict occult lymph node metastasis in early-stage oral tongue squamous cell carcinoma. PMID:33569617 | 2021 | 2 other reviews | not stated | not extracted yet |
| Committeri 2022 Radiomics Metrics Combined with Clinical Data in the Surgical Management of Early-Stage (cT1-T2 N0) Tongue Squamous Cell Carcinomas: A… PMID:35336841 | 2022 | 1 other review | not stated | not extracted yet |
| Kubo 2022 Development of a radiomics and machine learning model for predicting occult cervical lymph node metastasis in patients with tongue cancer. PMID:35431177 | 2022 | 1 other review | not stated | not extracted yet |
| Kudoh 2023 Radiomics analysis of [18F]-fluoro-2-deoxyglucose positron emission tomography for the prediction of cervical lymph node metastasis in… PMID:35254609 | 2023 | 1 other review | not stated | not extracted yet |
| Liu 2024 The application of radiomics machine learning models based on multimodal MRI with different sequence combinations in predicting cervical… PMID:38108536 | 2024 | 1 other review | not stated | not extracted yet |
| Ren 2022 Histogram analysis of diffusion-weighted imaging and dynamic contrast-enhanced MRI for predicting occult lymph node metastasis in… PMID:34642806 | 2022 | 1 other review | not stated | not extracted yet |
| Traverso 2020 matched by author and year (probable) | NR | 1 other review | not stated | not extracted yet |
| Vidiri 2023 Magnetic resonance imaging-based prediction models for tumor stage and cervical lymph node metastasis of tongue squamous cell carcinoma. PMID:37701020 | 2023 | 1 other review | not stated | not extracted yet |
| Zhong 2022 Tumor radiomics signature for artificial neural network-assisted detection of neck metastasis in patient with tongue cancer. PMID:34358534 | 2022 | 1 other review | not stated | not extracted yet |
| Ariji 2019 Contrast-enhanced computed tomography image assessment of cervical lymph node metastasis in patients with oral cancer by using a deep… DOI:10.1016/j.oooo.2018.10.002 | 2019 | this review only | not stated | not extracted yet |
| Ariji 2019 Contrast-enhanced computed tomography image assessment of cervical lymph node metastasis in patients with oral cancer by using a deep… PMID:30497907 | 2019 | this review only | not stated | not extracted yet |
| Ariji 2020a CT evaluation of extranodal extension of cervical lymph node metastases in patients with oral squamous cell carcinoma using deep learning… DOI:10.1007/s11282-019-00391-4 | 2019 | this review only | not stated | not extracted yet |
| Ariji 2020a CT evaluation of extranodal extension of cervical lymph node metastases in patients with oral squamous cell carcinoma using deep learning… PMID:31197738 | 2020 | this review only | not stated | not extracted yet |
| Ariji 2020b matched by author and year (probable) | NR | this review only | not stated | not extracted yet |
| Ariji 2022 Segmentation of metastatic cervical lymph nodes from CT images of oral cancers using deep-learning technology DOI:10.1259/dmfr.20210515 | 2022 | this review only | not stated | not extracted yet |
| Ariji 2022 Segmentation of metastatic cervical lymph nodes from CT images of oral cancers using deep-learning technology. PMID:35113725 | 2022 | this review only | not stated | not extracted yet |
| Bardosi 2022 Benchmarking Eliminative Radiomic Feature Selection for Head and Neck Lymph Node Classification DOI:10.3390/cancers14030477 | 2022 | this review only | not stated | not extracted yet |
| Bardosi 2022 Benchmarking Eliminative Radiomic Feature Selection for Head and Neck Lymph Node Classification. PMID:35158745 | 2022 | this review only | not stated | not extracted yet |
| Bur 2019 Machine learning to predict occult nodal metastasis in early oral squamous cell carcinoma DOI:10.1016/j.oraloncology.2019.03.011 | 2019 | this review only | not stated | not extracted yet |
| Bur 2019 Machine learning to predict occult nodal metastasis in early oral squamous cell carcinoma. PMID:31010618 | 2019 | this review only | not stated | not extracted yet |
| Chen 2019 Combining many-objective radiomics and 3D convolutional neural network through evidential reasoning to predict lymph node metastasis in… DOI:10.1088/1361-6560/ab083a | 2019 | this review only | not stated | not extracted yet |
| Chen 2019 Combining many-objective radiomics and 3D convolutional neural network through evidential reasoning to predict lymph node metastasis in… PMID:30780137 | 2019 | this review only | not stated | not extracted yet |
| Chen 2021 Attention Guided Lymph Node Malignancy Prediction in Head and Neck Cancer DOI:10.1016/j.ijrobp.2021.02.004 | 2021 | this review only | not stated | not extracted yet |
| Chen 2021 Attention Guided Lymph Node Malignancy Prediction in Head and Neck Cancer. PMID:33561508 | 2021 | this review only | not stated | not extracted yet |
| Chen 2023 A deep learning and radiomics fusion model based on contrast-enhanced computer tomography improves preoperative identification of cervical… DOI:10.1007/s00784-023-05423-2 | 2023 | this review only | not stated | not extracted yet |
| Chen 2023 A deep learning and radiomics fusion model based on contrast-enhanced computer tomography improves preoperative identification of cervical… PMID:38151672 | 2023 | this review only | not stated | not extracted yet |
| Committeri 2022 Radiomics Metrics Combined with Clinical Data in the Surgical Management of Early-Stage (cT1–T2 N0) Tongue Squamous Cell Carcinomas: A… DOI:10.3390/biology11030468 | 2022 | this review only | Pooled sensitivity for histopathological grade of OSCC | not extracted yet |
| Das 2018 Automatic identification of clinically relevant regions from oral tissue histological images for oral squamous cell carcinoma diagnosis DOI:10.1016/j.tice.2018.06.004 | 2018 | this review only | not stated | not extracted yet |
| Das 2018 Automatic identification of clinically relevant regions from oral tissue histological images for oral squamous cell carcinoma diagnosis. PMID:30060821 | 2018 | this review only | not stated | not extracted yet |
| Dohopolski 2020 Predicting lymph node metastasis in patients with oropharyngeal cancer by using a convolutional neural network with associated epistemic… DOI:10.1088/1361-6560/abb71c | 2020 | this review only | not stated | not extracted yet |
| Dohopolski 2020 Predicting lymph node metastasis in patients with oropharyngeal cancer by using a convolutional neural network with associated epistemic… PMID:33179605 | 2020 | this review only | not stated | not extracted yet |
| Kawazu 2003 matched by author and year (probable) | NR | this review only | not stated | not extracted yet |
| Kim 2011 A novel algorithm for lymph node status prediction of oral cancer before surgery DOI:10.1016/j.oraloncology.2011.07.017 | 2011 | this review only | not stated | not extracted yet |
| Kim 2011 A novel algorithm for lymph node status prediction of oral cancer before surgery. PMID:21840750 | 2011 | this review only | not stated | not extracted yet |
| Konishi 2023 Radiomics analysis of intraoral ultrasound images for prediction of late cervical lymph node metastasis in patients with tongue cancer DOI:10.1002/hed.27487 | 2023 | this review only | not stated | not extracted yet |
| Konishi 2023 Radiomics analysis of intraoral ultrasound images for prediction of late cervical lymph node metastasis in patients with tongue cancer. PMID:37584449 | 2023 | this review only | not stated | not extracted yet |
| Kubo 2022 Development of a radiomics and machine learning model for predicting occult cervical lymph node metastasis in patients with tongue cancer DOI:10.1016/j.oooo.2021.12.122 | 2022 | this review only | not stated | not extracted yet |
| Kudoh 2023 Radiomics analysis of [18F]-fluoro-2-deoxyglucose positron emission tomography for the prediction of cervical lymph node metastasis in… DOI:10.1007/s11282-022-00600-7 | 2022 | this review only | not stated | not extracted yet |
| Lavanya 2019 matched by author and year (probable) | NR | this review only | not stated | not extracted yet |
| Liu 2024 The application of radiomics machine learning models based on multimodal <scp>MRI</scp> with different sequence combinations in predicting… DOI:10.1002/hed.27605 | 2023 | this review only | not stated | not extracted yet |
| Mermod 2020 Development and validation of a multivariable prediction model for the identification of occult lymph node metastasis in oral squamous… DOI:10.1002/hed.26105 | 2020 | this review only | not stated | not extracted yet |
| Mermod 2020 Development and validation of a multivariable prediction model for the identification of occult lymph node metastasis in oral squamous… PMID:32057148 | 2020 | this review only | not stated | not extracted yet |
| Nagata 2000 matched by author and year (probable) | NR | this review only | not stated | not extracted yet |
| Nagata 2005 Application of fuzzy inference to European patients to predict cervical lymph node metastasis in carcinoma of the tongue DOI:10.1016/j.ijom.2004.03.012 | 2005 | this review only | not stated | not extracted yet |
| Nagata 2005 Application of fuzzy inference to European patients to predict cervical lymph node metastasis in carcinoma of the tongue. PMID:15695041 | 2005 | this review only | not stated | not extracted yet |
| Nawandhar 2019 matched by author and year (probable) | NR | this review only | not stated | not extracted yet |
| Nawandhar 2020 matched by author and year (probable) | NR | this review only | not stated | not extracted yet |
| Nikkuni 2024 Prediction of Histological Grade of Oral Squamous Cell Carcinoma Using Machine Learning Models Applied to 18F-FDG-PET Radiomics DOI:10.3390/biomedicines12071411 | 2024 | this review only | Pooled sensitivity for histopathological grade of OSCC | not extracted yet |
| Nikkuni 2024 Prediction of Histological Grade of Oral Squamous Cell Carcinoma Using Machine Learning Models Applied to 18F-FDG-PET Radiomics. PMID:39061984 | 2024 | this review only | not stated | not extracted yet |
| Onoue 2021 Cystic cervical lymph nodes of papillary thyroid carcinoma, tuberculosis and human papillomavirus positive oropharyngeal squamous cell… DOI:10.1016/j.amjoto.2021.103026 | 2021 | this review only | not stated | not extracted yet |
| Onoue 2021 Cystic cervical lymph nodes of papillary thyroid carcinoma, tuberculosis and human papillomavirus positive oropharyngeal squamous cell… PMID:33862564 | 2021 | this review only | not stated | not extracted yet |
| Ren 2020 Machine Learning–Based MRI Texture Analysis to Predict the Histologic Grade of Oral Squamous Cell Carcinoma DOI:10.2214/ajr.19.22593 | 2020 | this review only | Pooled sensitivity for histopathological grade of OSCC | not extracted yet |
| Ren 2020 Machine Learning-Based MRI Texture Analysis to Predict the Histologic Grade of Oral Squamous Cell Carcinoma. PMID:32930606 | 2020 | this review only | not stated | not extracted yet |
| Ren 2022 Histogram analysis of diffusion-weighted imaging and dynamic contrast-enhanced MRI for predicting occult lymph node metastasis in… DOI:10.1007/s00330-021-08310-0 | 2021 | this review only | not stated | not extracted yet |
| Romeo 2020 Prediction of Tumor Grade and Nodal Status in Oropharyngeal and Oral Cavity Squamous-cell Carcinoma Using a Radiomic Approach DOI:10.21873/anticanres.13949 | 2019 | this review only | Pooled sensitivity for histopathological grade of OSCC | not extracted yet |
| Romeo 2020 Prediction of Tumor Grade and Nodal Status in Oropharyngeal and Oral Cavity Squamous-cell Carcinoma Using a Radiomic Approach. PMID:31892576 | 2020 | this review only | not stated | not extracted yet |
| Schwarzer 2003 Comparison of fuzzy inference, logistic regression, and classification trees (CART). Prediction of cervical lymph node metastasis in… PMID:14654893 | 2003 | this review only | not stated | not extracted yet |
| Shan 2020 Machine Learning Predicts Lymph Node Metastasis in Early-Stage Oral Tongue Squamous Cell Carcinoma DOI:10.1016/j.joms.2020.06.015 | 2020 | this review only | not stated | not extracted yet |
| Shan 2020 Machine Learning Predicts Lymph Node Metastasis in Early-Stage Oral Tongue Squamous Cell Carcinoma. PMID:32649894 | 2020 | this review only | not stated | not extracted yet |
| Sun 2024 [Clinical study of cervical lymph node metastasis in oral tongue squamous carcinoma by a machine learning model based on contrast-enhanced… PMID:40007291 | 2024 | this review only | not stated | not extracted yet |
| Tomita 2021a Nodal-based radiomics analysis for identifying cervical lymph node metastasis at levels I and II in patients with oral squamous cell… DOI:10.1007/s00330-021-07758-4 | 2021 | this review only | not stated | not extracted yet |
| Tomita 2021a Nodal-based radiomics analysis for identifying cervical lymph node metastasis at levels I and II in patients with oral squamous cell… PMID:33787970 | 2021 | this review only | not stated | not extracted yet |
| Tomita 2021b Deep Learning for the Preoperative Diagnosis of Metastatic Cervical Lymph Nodes on Contrast-Enhanced Computed ToMography in Patients with… DOI:10.3390/cancers13040600 | 2021 | this review only | not stated | not extracted yet |
| Tomita 2021b Deep Learning for the Preoperative Diagnosis of Metastatic Cervical Lymph Nodes on Contrast-Enhanced Computed ToMography in Patients with… PMID:33546279 | 2021 | this review only | not stated | not extracted yet |
| Traverso 2019 matched by author and year (probable) | NR | this review only | not stated | not extracted yet |
| Vidiri 2023 Magnetic resonance imaging-based prediction models for tumor stage and cervical lymph node metastasis of tongue squamous cell carcinoma DOI:10.1016/j.csbj.2023.08.020 | 2023 | this review only | not stated | not extracted yet |
| Wang 2022 Magnetic Resonance Imaging‐Based Radiomics Features Associated with Depth of Invasion Predicted Lymph Node Metastasis and Prognosis in… DOI:10.1002/jmri.28019 | 2021 | this review only | not stated | not extracted yet |
| Xu 2023 Deep learning assisted contrast-enhanced CT–based diagnosis of cervical lymph node metastasis of oral cancer: a retrospective study of… DOI:10.1007/s00330-022-09355-5 | 2022 | this review only | not stated | not extracted yet |
| Xu 2023 Deep learning assisted contrast-enhanced CT-based diagnosis of cervical lymph node metastasis of oral cancer: a retrospective study of… PMID:36576543 | 2023 | this review only | not stated | not extracted yet |
| Yuan 2021 Machine learning–based MRI texture analysis to predict occult lymph node metastasis in early-stage oral tongue squamous cell carcinoma DOI:10.1007/s00330-021-07731-1 | 2021 | this review only | not stated | not extracted yet |
| Zhong 2022 Tumor radiomics signature for artificial neural network-assisted detection of neck metastasis in patient with tongue cancer DOI:10.1016/j.neurad.2021.07.006 | 2022 | this review only | not stated | not extracted yet |
Overlap with other reviews
Reviews that include the same primary studies are not independent evidence. Shared counts match studies by PMID, DOI or NCT, and otherwise by author and year (a probable match). Only the non-Cochrane dental reviews have study lists, so overlap with Cochrane reviews is not counted yet.
Review question
| Element | Planned (methods) | Found (results) |
|---|---|---|
| Population | Research on ML/DL applied to radiomic features from CT, PET, MRI, ultrasound and histopathology images for tumour grading or staging in OSCC/OPSCC | Patients with OSCC or OPSCC (n=40 studies; 33 in quantitative synthesis) |
| Intervention | ML/DL-based radiomics framework for prediction of tumour grading and lymph node metastasis | ML and DL radiomics models on CT, PET-CT, MRI, ultrasound and histopathology images |
| Comparison | Model performance by any commonly used ML/DL parameters | Not specified |
| Outcomes | Performance of AI models (sensitivity, specificity, DOR, AUC) for predicting tumour grading or lymph node metastasis | Lymph node metastasis prediction (29 studies in pooled analysis) and histopathological grading prediction (4 studies) |
| Study designs | Studies of AI model performance; reviews, abstracts, non-English and animal studies excluded | Diagnostic accuracy studies of AI prediction models |
| Timing | Not specified | Not specified |