Skip to main content
. 2022 Dec 9;10(12):2493. doi: 10.3390/healthcare10122493

Table 2.

Benchmarking of studies.

C1 C2 C3 C4 C5 C6 C7 C8 C9 C10 C11
SN Author Country Journal Study Type FoV Objective PS Cli-Val Diagnosis (Invasive/Noninvasive) Treatment (Invasive/Noninvasive)
1 Smetherman et al. [182] (2021) USA Breast Imaging P.R. Cancer Improving the quality of care and/or reducing healthcare costs by using AI 1012 No Noninvasive NR
2 Challen et al. [183] (2019) UK Artificial intelligence, bias and clinical safety R. Clinical safety To set short and medium ML clinical safety goals NR No Noninvasive NR
3 Almazán et al. [82] (2019) Italy Clinical Pharmacy P.R. Renal Evaluate the effectiveness, safety, and economic cost of nivolumab in real-world clinical practice 221 No Noninvasive NR
4 Yuan et al. [184] (2020) China Medical Sciences P.R. Renal Challenges in kidney diagnosis and treatment NR No Noninvasive NR
5 Solanki et al. [185] (2022) Australia Operational ethics in AI framework R NA NR NR No Noninvasive NR
6 Biswas et al. [102] (2018) India DL-based strategy for accurate Carotid Intima-Media Measurement R Heart The carotid intima-media thickness (cIMT) is an important biomarker for monitoring cardiovascular disease and stroke 204 No Noninvasive NR
7 Siy et al. [186] (2018) Taiwan IEEE Conference R Skin DL-based psoriasis detection 5700 No Noninvasive NR
8 Aijaz et al. [71] (2022) Pakistan Journal of Healthcare Engineering R Skin Effective classification of different psoriasis types using deep learning applications 473 No Noninvasive NR
9 Ali et al. [188] (2022) Iraq Kidney Diseases Transplantation P. Renal Renal medicine NR No NR NR
10 Viswanathan et al. [189] (2020) India Preventive health check in patients with diabetes R. Diabetes Cost-effective carotid ultrasound screening for diabetes patients NR NR Noninvasive NR
11 Sarki et al. [198] (2020) USA Health Information Science and Systems P.R. Diabetes Retinopathy Deep learning-based automated identification of multiple classes of diabetic eye disorders 1748 NR Noninvasive NR
12 Quan et al. [199] (2021) Japan IEEE Access P.R. Parkinson’s Using dynamic speech features, a deep learning-based approach for Parkinson’s disease detection 45 NR Noninvasive NR
13 Kamble et al. [191] (2021) India Measurement and Sensor P.R. Parkinson’s Parkinson’s disease classification using digital spiral drawings 25 NR Noninvasive NR
C12 C13 C14
SN Author AI Type Cost Analysis Parameter Outcome of study
AI Type ACC SEN SPE AUC MCC F1 Cost Analysis Parameter Input Modality Model Analysis Screening cost Maintain Cost Cost Savings (USD) Per. Sample
1 Smetherman et al. [182] (2021) NR NR NR NR NR NR NR NR Image Yes Yes NR 318 AI could assess individual situations, make appropriate decisions, and aid in the management of renal disease.
2 Challen et al. [183] (2019) NR NR NR NR NR NR NR NR NR NR NR NR NR ML DSS deployment will most likely concentrate on diagnostic decision support. ML Diagnostic decision assistance should be assessed with the same rigors as a novel laboratory screening test.
3 Almazán et al. [82] (2019) NR NR NR NR NR NR NR NR Point Data Yes Yes NR 61 AI for improved clinical benefit from nivolumab therapy.
4 Yuan et al. [184] (2020) NR NR NR NR NR NR NR NR Point Data Yes Yes NR 62 Artificial intelligence can consider individual situations, make appropriate decisions, and make significant advancements in the management of renal disease.
5 Solanki et al. [185] (2022) NR NR NR NR NR NR NR NR NR Yes Yes Yes Yes Guidelines, frameworks, and advancement of technologies for ethical AI that reflect human values, such as self-direction, in healthcare.
6 Biswas et al. [102] (2018) DL 86.78 0.76 NR 0.86 NR NR NR Image NR NR NR NR High-level features are extracted from the CCA US photos using CNN’s 13 layers. To produce clear and crisp segmented images, these features were upsampled using FCN upsampling layers, and the skipping operation was carried out.
7 Siy et al. [186] (2018) DL 91.5 NR NR NR NR NR NR Image NR NR NR NR A DNN-based psoriasis detection presented having 91.5% accuracy.
8 Aijaz et al. [71] (2022) DL 84.2 0.81 0.71 NR NR NR NR Image NR NR NR NR This study employed a CNN-based deep learning classification strategy to categorize the five types of psoriasis.
9 Ali et al. [188] (2022) NR NR NR NR NR NR NR NR NR NR NR NR NR Machine learning and artificial intelligence have ushered in a new era in medicine and nephrology.
10 Viswanathan et al. [189] (2020) NR NR NR NR NR NR NR NR Image NR NR NR 14 Diabetes exacerbated the deposition of atherosclerotic plaque. Risk assessment includes other factors in addition to the degree of vessel stenosis.
11 Sarki et al. [198] (2020) DL 84.88 0.87 NR NR NR NR NR Image NR NR NR NR The development of moderate and multi-class DL algorithms for the automatic detection of DED, according to the British Diabetic Association (BDA) criteria.
12 Quan et al. [199] (2021) DL 80.90 0.87 0.92 0.83 0.53 NR NR Speech NR NR NR NR The dynamic articulation transition features and the bidirectional LSTM model are combined ingeniously in the proposed method to record the time-series properties of continuous speech data.
13 Kamble et al. [191] (2021) ML 91.6 NR NR NR NR 0.8 NR Image NR NR NR NR Digitalized spiral drawing tests significantly affect how PD patients and healthy controls are classified.