Skip to main content
. 2022 Oct 26;56(6):5261–5315. doi: 10.1007/s10462-022-10304-3

Table 5.

List of XAI studies with tabular data performing clinical validation of explanations

References # Cit. Application Input Data AI model(s) XAI method(s) Dataset(s)
Beebe-Wang et al. (2021) 7 Imminent dementia diagnosis EHR XGBoost SHAP ROSMAP dataset Bennett et al. (2012)
Sha et al. (2021) 4 AD diagnosis Plasma metabolite concentrations Evolutionary algorithms LGP AD metabolomic dataset Wang et al. (2014)
Kim et al. (2021) 3 END detection in stroke patients EHR LightGBM SHAP K-Attention dataset Jung et al. (2019)
Rashed-Al-Mahfuz et al. (2021) 6 CKD diagnosis EHR RF, GBDT, XGBoost SHAP UCI CKD dataset Rubini and Eswaran (2015)
Pang et al. (2019) 10 Early childhood obesity prediction EHR XGBoost SHAP Retrospective study
Zeng et al. (2021) 5 Post-operative complication risk prediction EHR XGBoost SHAP Retrospective study
Zhang et al. (2021) 10 post-LT AKI prediction EHR RF SHAP Retrospective study
Lu et al. (2020) 5 COVID-19 diagnosis and prognosis EHR GBDT, RF SHAP Retrospective study
Gupta et al. (2021) 1 COVID-19 recovered subject detection HR/HRV features XGBoost SHAP Retrospective study
Pal and Sankarasubbu (2021) 50 COVID-19 diagnosis Cough sounds, symptoms metadata TabNet, DNN Attention Pilot study
Dissanayake et al. (2020) 18 Heart anomaly detection PCG features stacked LSTM-CNN-MLP network SHAP, occlusion maps PhysioNet DB Goldberger et al. (2000)