TY  - JOUR
AU  - Singh, Abhishek
AU  - Hasan, Zohaib
PY  - 2026
DA  - 2026/06/27
TI  - ANFIS-PSO: A Particle Swarm Optimized Adaptive Neuro-Fuzzy Inference System for Early Diagnosis and Risk Stratification of Chronic Kidney Disease
JO  - Biomedical Informatics and Smart Healthcare
T2  - Biomedical Informatics and Smart Healthcare
JF  - Biomedical Informatics and Smart Healthcare
VL  - 2
IS  - 2
SP  - 86
EP  - 97
DO  - 10.62762/BISH.2026.692582
UR  - https://www.icck.org/article/abs/BISH.2026.692582
KW  - chronic kidney disease
KW  - ANFIS
KW  - particle swarm optimization
KW  - fuzzy inference system
KW  - explainable AI
KW  - clinical decision support
KW  - KNN imputation
KW  - rural healthcare
AB  - Chronic Kidney Disease (CKD) affects 697.5 million people globally, with \~{}115 million in India. Early detection is clinically challenging as the disease remains asymptomatic through stages 1–3, particularly in resource-limited rural settings like Madhya Pradesh. While high-accuracy black-box models (SVM, Random Forest, DNN) achieve 91.5–98% accuracy on the UCI CKD benchmark, they lack interpretability—creating a Transparency Gap that hinders clinical adoption. This paper proposes ANFIS-PSO, a Particle Swarm Optimization-tuned Adaptive Neuro-Fuzzy Inference System for early CKD diagnosis. A five-stage pipeline incorporating KNN imputation and Min-Max normalization was applied to the 400-record UCI dataset with a 70:30 split. A five-layer ANFIS with Gaussian fuzzification and Takagi-Sugeno defuzzification was constructed, optimizing 125 membership function centers via PSO with validation-based fitness. Evaluation using both single holdout and 5-fold stratified cross-validation yielded 100% test accuracy on the single split (120/120, zero FP/FN, RMSE=0.1440) and mean CV accuracy of 87.00% ± 3.59% (95% CI: [83.85%, 90.15%]), with sensitivity of 91.60% ± 2.33% and specificity of 79.33% ± 9.04%. Five interpretable fuzzy rules were extracted, corresponding to three clinically meaningful CKD patterns. The model is
SN  - 3068-5524
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Singh2026ANFISPSO,
  author = {Abhishek Singh and Zohaib Hasan},
  title = {ANFIS-PSO: A Particle Swarm Optimized Adaptive Neuro-Fuzzy Inference System for Early Diagnosis and Risk Stratification of Chronic Kidney Disease},
  journal = {Biomedical Informatics and Smart Healthcare},
  year = {2026},
  volume = {2},
  number = {2},
  pages = {86-97},
  doi = {10.62762/BISH.2026.692582},
  url = {https://www.icck.org/article/abs/BISH.2026.692582},
  abstract = {Chronic Kidney Disease (CKD) affects 697.5 million people globally, with \~{}115 million in India. Early detection is clinically challenging as the disease remains asymptomatic through stages 1–3, particularly in resource-limited rural settings like Madhya Pradesh. While high-accuracy black-box models (SVM, Random Forest, DNN) achieve 91.5–98\% accuracy on the UCI CKD benchmark, they lack interpretability—creating a Transparency Gap that hinders clinical adoption. This paper proposes ANFIS-PSO, a Particle Swarm Optimization-tuned Adaptive Neuro-Fuzzy Inference System for early CKD diagnosis. A five-stage pipeline incorporating KNN imputation and Min-Max normalization was applied to the 400-record UCI dataset with a 70:30 split. A five-layer ANFIS with Gaussian fuzzification and Takagi-Sugeno defuzzification was constructed, optimizing 125 membership function centers via PSO with validation-based fitness. Evaluation using both single holdout and 5-fold stratified cross-validation yielded 100\% test accuracy on the single split (120/120, zero FP/FN, RMSE=0.1440) and mean CV accuracy of 87.00\% ± 3.59\% (95\% CI: [83.85\%, 90.15\%]), with sensitivity of 91.60\% ± 2.33\% and specificity of 79.33\% ± 9.04\%. Five interpretable fuzzy rules were extracted, corresponding to three clinically meaningful CKD patterns. The model is},
  keywords = {chronic kidney disease, ANFIS, particle swarm optimization, fuzzy inference system, explainable AI, clinical decision support, KNN imputation, rural healthcare},
  issn = {3068-5524},
  publisher = {Institute of Central Computation and Knowledge}
}