EMERGING ROLE OF ARTIFICIAL INTELLIGENCE IN KIDNEY DISEASE DIAGNOSIS AND MANAGEMENT

EMERGING ROLE OF ARTIFICIAL INTELLIGENCE IN KIDNEY DISEASE DIAGNOSIS AND MANAGEMENT

Ankur Awasthi, Akash Yadav * and Dinesh Kumar Jain

IPS Academy College of Pharmacy, Knowledge Village, Rajendra Nagar, A.B. Road, Indore, Madhya Pradesh, India.

ABSTRACT: Kidney diseases continue to impose a substantial global health burden due to their progressive nature, delayed clinical detection, and strong association with cardiovascular morbidity and mortality. Conventional diagnostic and prognostic tools in nephrology, including serum creatinine, estimated glomerular filtration rate, and imaging modalities, often provide limited insight into early disease mechanisms and fail to capture the multidimensional complexity of renal pathology. Recent advances in artificial intelligence (AI), encompassing machine learning, deep learning, and multimodal data analytics, offer promising opportunities to enhance kidney care through early risk prediction, improved diagnostic accuracy, and personalized therapeutic strategies. This review critically examines current trends and applications of AI in nephrology, with emphasis on chronic kidney disease and acute kidney injury prediction, AI-assisted renal imaging, digital histopathology, dialysis optimization, and clinical decision support systems. Emerging approaches such as multimodal learning frameworks, explainable AI, and precision nephrology models are also discussed in relation to future clinical integration. In parallel, key challenges including data heterogeneity, limited external validation, ethical and privacy concerns, regulatory barriers, and issues related to clinical adoption are highlighted.

Keywords: Artificial Intelligence, Nephrology, Chronic Kidney Disease, Acute Kidney Injury, Machine Learning, Precision Medicine

INTRODUCTION: Kidney diseases, including chronic kidney disease (CKD) and acute kidney injury (AKI), represent a major and growing global health burden, contributing substantially to morbidity, mortality, and healthcare expenditure ¹. The progressive nature of CKD, which often remains asymptomatic until advanced stages, poses significant challenges for early diagnosis and timely intervention ². Similarly, AKI is associated with high short-term mortality and an increased risk of long-term renal dysfunction, particularly among critically ill and hospitalized patients.

Consequently, effective early detection and accurate risk stratification are essential for improving clinical outcomes and reducing disease progression³. Conventional diagnostic and prognostic approaches in nephrology primarily rely on serum biomarkers, imaging modalities, and histopathological evaluation. Although these tools remain clinically indispensable, their ability to detect early disease changes and provide individualized risk assessment is often constrained by biological variability, inter-observer differences, and limited integration of longitudinal patient data ⁴.

Traditional prediction models may also inadequately reflect disease heterogeneity, dynamic progression, and the multifactorial nature of renal disorders, thereby limiting their overall predictive performance ⁵.

FIG. 1: AI IN KIDNEY CARE

Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have created new opportunities to address these challenges by enabling comprehensive analysis of high-dimensional clinical data ⁶. AI-based algorithms can integrate information from electronic health records, medical imaging, genomics, and wearable technologies to identify clinically relevant patterns and support more accurate prediction, diagnosis, and management of kidney diseases. In nephrology, these approaches have shown promise in early disease detection, prognostic modeling, treatment optimization, and clinical decision support ⁷.

This review critically examines the emerging role of AI in kidney disease diagnosis and management, highlighting recent technological advances, current clinical applications, and their implications for patient care. In addition, it discusses key challenges related to data quality, model interpretability, ethical considerations, and clinical integration, while outlining future directions for the responsible and effective adoption of AI in nephrology practice.

Current Trends in AI for Kidney Care: The application of artificial intelligence within nephrology has expanded rapidly in recent years, driven by the increasing availability of electronic health data, high-resolution imaging, and advancements in machine learning and deep learning techniques. AI technologies are now being integrated into risk prediction models, diagnostic workflows, and therapeutic decision-making processes. These developments reflect a broader shift toward data-driven precision medicine, allowing clinicians to interpret complex patterns that would otherwise remain undetected using conventional methods. The following subsections discuss major trends in AI-driven renal healthcare, highlighting their clinical significance and evolving roles.

AI for Chronic Kidney Disease (CKD) Detection and Risk Prediction: Artificial intelligence-based approaches, particularly machine learning and deep learning models, have been increasingly applied for the early prediction and risk stratification of chronic kidney disease. By analyzing large-scale, multidimensional datasets derived from electronic health records, laboratory parameters, demographic variables, and imaging data, these models enable more comprehensive assessment of disease trajectories compared to conventional statistical methods. Such integrative analysis supports improved identification of individuals at high risk for CKD progression, even at earlier and clinically asymptomatic stages ^{8, 9}.

FIG. 2: WORKFLOW OF AI IN CKD PREDICTION

Several studies have demonstrated that AI-driven prediction models can enhance prognostic accuracy and support timely clinical decision-making by facilitating personalized risk assessment and monitoring. Rather than solely emphasizing algorithmic performance metrics, the primary clinical value of these models lies in their potential to enable earlier interventions, optimize patient follow-up strategies, and reduce progression to end-stage renal disease. Collectively, these advancements highlight the growing role of AI as a supportive tool for improving CKD management and long-term patient outcomes ¹⁰.

AI in Acute Kidney Injury (AKI) Prediction: Artificial intelligence-based models have demonstrated significant potential for the early prediction of acute kidney injury, particularly in high-risk clinical environments such as intensive care units and perioperative settings ¹¹. By leveraging routinely collected clinical data-including vital signs, laboratory parameters, medication exposure, and comorbidities-machine learning and deep learning algorithms can identify subtle physiological changes that precede clinically overt AKI. This enables earlier risk stratification and supports proactive clinical decision-making ¹². AI-driven prediction models have consistently shown improved prognostic performance compared to conventional rule-based criteria by facilitating continuous analysis of time-series data and dynamic risk assessment ¹³. When integrated into electronic health record systems, these models provide clinicians with real-time insights that enhance situational awareness and enable timely preventive interventions.

The principal clinical benefit lies in supporting early recognition and mitigation of AKI risk rather than repeated emphasis on algorithmic superiority ^{14, 15}.

AI-enabled alert systems represent a key translational application of AKI prediction models, serving as decision-support tools that notify healthcare providers of elevated risk and prompt preventive measures such as medication adjustment, fluid management, and closer patient monitoring ¹⁶. However, challenges including alert fatigue, variability in performance across diverse patient populations, and limited external validation necessitate careful implementation and continuous evaluation. Future research should prioritize model interpretability, standardized validation frameworks, and seamless clinical integration to maximize real-world impact and patient safety ^{17, 18}.

TABLE 1: AI TOOLS FOR AKI FORECASTING

AI Applications in Renal Imaging: AI-assisted imaging has become one of the most dynamic areas of innovation in nephrology. Traditional imaging interpretation relies heavily on radiologist expertise and is subject to inter-observer variability. AI tools, particularly deep learning models, help standardize image interpretation by identifying disease-specific patterns with greater consistency and speed ^{19, 20}. In cross-sectional imaging (CT and MRI), AI algorithms perform automated segmentation of renal parenchyma, quantify cortical thickness, detect cystic and solid lesions, and assess tumor characteristics with high accuracy ²¹. These capabilities are especially beneficial for renal oncology, where early and accurate identification of renal cell carcinoma is crucial. AI models trained on annotated datasets can differentiate between benign and malignant lesions and even classify RCC subtypes with performance comparable to experienced radiologists ^{22, 23}.

TABLE 2: APPLICATIONS OF AI IN RENAL IMAGING

Renal ultrasound-a widely accessible but operator-dependent modality-has also benefitted from AI technologies. Machine learning systems can reduce noise, enhance structural visualization, and identify hydronephrosis or parenchymal abnormalities more reliably than manual interpretation in some settings ²⁴.

AI in Renal Histopathology and Digital Pathology: Artificial intelligence has increasingly been applied to optimize dialysis management by supporting individualized treatment planning and real-time monitoring of patient parameters. AI-based models analyze longitudinal clinical data, dialysis machine outputs, and patient-specific variables to assist in tailoring dialysis prescriptions, predicting intradialytic complications, and improving treatment efficiency. These approaches enable clinicians to move beyond standardized protocols toward more patient-centered dialysis care ^{25, 26}.

FIG. 3: AI BASED RENAL BIOPSY ANALYSIS

In the context of digital pathology, AI models integrate morphometric data with clinical and laboratory parameters to improve disease stratification, prognostic assessment, and treatment response prediction in various renal disorders. By analyzing longitudinal pathological changes, AI-driven tools assist in identifying subtle morphological patterns that may be overlooked in conventional microscopy, supporting early disease detection and refined classification of complex renal pathologies. Furthermore, AI-enabled platforms contribute to workflow optimization by prioritizing cases, assisting pathologists during slide review, and enabling large-scale research through high-throughput image analysis ²⁷.

Despite promising results, the successful clinical implementation of AI in dialysis management depends on data quality, interoperability with dialysis infrastructure, and clinician acceptance. Ongoing validation studies and real-world evaluations are essential to ensure reliability, safety, and sustained clinical impact in routine nephrology practice ²⁸.

AI in Dialysis Management: Artificial intelligence has gained increasing attention in the optimization of dialysis management, particularly in improving treatment safety, efficiency, and individualization. AI-driven models analyze large volumes of dialysis-related data, including hemodynamic parameters, ultrafiltration rates, laboratory values, and patient-specific characteristics, to support real-time clinical decision-making. One of the most impactful applications of AI in dialysis is the prediction of intradialytic hypotension. Machine learning algorithms can identify subtle physiological patterns that precede blood pressure drops, enabling early risk stratification and proactive adjustment of dialysis parameters. By integrating predictive insights into dialysis workflows, these systems may help reduce treatment-related complications and improve patient tolerance ²⁹.

In addition, AI supports personalized dialysis prescriptions by tailoring ultrafiltration profiles, session duration, and fluid removal targets based on individual patient responses. Rather than relying on fixed protocols, AI-based approaches allow dynamic treatment adaptation, which may enhance cardiovascular stability and overall treatment outcomes. However, the clinical translation of these technologies requires further validation, interoperability with dialysis machines, and careful consideration of workflow integration ³⁰.

Emerging Innovations and Future Prospective: The field of nephrology is undergoing a significant transformation as artificial intelligence evolves from isolated predictive models into integrated systems capable of supporting comprehensive clinical decision-making. Emerging innovations increasingly emphasize multimodal learning, interpretability, personalization, and seamless clinical integration, collectively advancing kidney care toward a more precise and patient-centered paradigm. These developments reflect a shift from purely technical performance toward clinically meaningful and ethically responsible AI deployment ³¹. Multimodal artificial intelligence represents a promising direction for precision nephrology by enabling the integration of diverse data sources, including electronic health records, laboratory parameters, medical imaging, digital pathology, and molecular profiles.

By combining heterogeneous data modalities, multimodal frameworks aim to improve disease characterization, risk stratification, and outcome prediction beyond the capabilities of single-source models. Although early evidence suggests potential benefits, most applications remain at an exploratory stage, and their clinical utility requires validation through large-scale prospective studies across diverse patient populations ^{32, 33}. As AI systems become more deeply embedded in clinical practice, explainability, ethics, and governance have emerged as interdependent pillars for responsible implementation. Many advanced AI models, particularly deep learning architectures, operate as complex systems that offer limited transparency, which can undermine clinician trust and hinder adoption. Explainable AI approaches seek to address this challenge by providing interpretable insights into how predictions are generated and which clinical variables most strongly influence outcomes. Such transparency supports clinical validation, enhances accountability, and facilitates safer integration into routine nephrology workflows ³⁴.

FIG. 4: MULTIMODAL AI FRAMEWORK IN NEPHROLOGY

Ethical considerations are closely intertwined with interpretability and governance. Ensuring patient data privacy, minimizing algorithmic bias, and promoting equitable care are essential to prevent unintended harm. AI models trained on non-representative datasets may perpetuate healthcare disparities, highlighting the importance of diverse data sources, continuous performance monitoring, and adherence to regulatory and data protection frameworks. Together, explainability, ethical oversight, and governance structures form a unified foundation for trustworthy AI in kidney care ³⁵. AI-enhanced clinical decision support systems represent a key translational bridge between innovation and bedside practice. By embedding predictive models within electronic health record platforms, these systems enable real-time risk assessment, diagnostic support, and treatment planning. Their effectiveness depends on thoughtful design that aligns with clinical workflows, delivers context-aware recommendations, and minimizes alert fatigue. Ongoing evaluation and clinician engagement are critical to ensuring sustained real-world impact ³⁶. Looking ahead, AI is expected to play an increasingly important role in personalized nephrology by supporting individualized risk stratification, therapy optimization, and outcome prediction. Beyond clinical care, AI is also reshaping renal research and education through large-scale data analytics, automated knowledge discovery, and innovative training platforms. Collectively, these emerging innovations highlight the potential of AI to advance kidney care while underscoring the need for careful validation, ethical stewardship, and clinically grounded implementation ³⁷.

Challenges and Limitations: Despite rapid advances in artificial intelligence applications within nephrology, translation into routine clinical practice remains constrained by multiple interrelated technical, clinical, regulatory, and ethical challenges. Addressing these limitations is essential to ensure that AI-based tools are safe, reliable, equitable, and clinically applicable across diverse patient populations ³⁸.

A major barrier to effective AI implementation lies in the heterogeneity and variability of clinical data, which directly influences model robustness and generalizability. Data originating from different healthcare institutions often differ in structure, measurement standards, imaging protocols, and documentation practices ³⁹. Incomplete records, missing values, and inconsistencies within electronic health records further complicate model development and evaluation. Additionally, models trained on narrowly defined or localized datasets may fail to maintain predictive accuracy when applied to external populations with differing demographic characteristics, comorbidity profiles, or healthcare settings. These challenges underscore the need for standardized data collection, diverse training cohorts, and rigorous multicenter validation strategies prior to widespread clinical deployment ⁴⁰. Regulatory and legal challenges further impede clinical adoption. Existing regulatory frameworks are not fully adapted to adaptive and continuously learning AI systems, creating uncertainty around approval pathways, accountability, and liability. The absence of universally accepted standards for model validation, reporting, and post-deployment monitoring also limits regulatory clarity and clinician confidence ⁴¹.

FIG. 5:  CHALLENGES AND LIMITATIONS OF AI IN NEPHROLOGY

Clinical acceptance and trust represent additional limitations. Many high-performing deep learning models operate as complex systems with limited interpretability, which can hinder clinician understanding and confidence in AI-assisted recommendations. Concerns related to workflow disruption, alert fatigue, and the need for specialized training further challenge seamless integration into everyday nephrology practice ⁴². Ethical considerations, including fairness, bias, and data privacy, remain central to responsible AI adoption. Models trained on non-representative datasets risk perpetuating healthcare disparities, particularly when deployed across diverse socioeconomic or geographic contexts. Robust data governance frameworks, secure data-sharing mechanisms, and compliance with ethical and legal standards are essential to protect patient privacy and maintain public trust as AI-enabled collaborations expand ⁴³. Addressing these challenges will require coordinated efforts among clinicians, data scientists, healthcare institutions, regulators, and policymakers. Through improved data standardization, transparent model design, rigorous validation, and clinician-centered implementation strategies, AI technologies can progress from experimental tools to trusted components of routine nephrology care ^{44, 45}.

CONCLUSION: Artificial intelligence is increasingly influencing nephrology by enabling earlier detection, improved risk stratification, and more personalized management of kidney diseases. Applications spanning chronic kidney disease, acute kidney injury, digital pathology, dialysis optimization, and clinical decision support demonstrate the potential of AI to enhance diagnostic accuracy and support evidence-based care. Advances in deep learning, multimodal data integration, and explainable AI are particularly important in improving clinical trust and usability. Despite these advances, significant challenges remain, including data heterogeneity, limited generalizability, ethical concerns, and regulatory uncertainties. Addressing these barriers through robust validation, transparent model design, and interdisciplinary collaboration will be essential for safe and effective clinical implementation.

With responsible development and integration into existing workflows, AI has the potential to advance precision nephrology, support proactive interventions, and ultimately improve patient outcomes in renal healthcare.

ACKNOWLEDGEMENTS: The authors are grateful to IPS Academy College of Pharmacy, Indore, for providing necessary facilities and academic support to carry out this work. The authors also acknowledge the support of faculty members for their valuable suggestions during manuscript preparation.

CONFLICTS OF INTEREST: The authors declare that there is no conflict of interest regarding the publication of this manuscript.

REFERENCES:

1. Rank N, Pfohl S and Lundberg SM: Reliability of machine learning in cardiology, radiology, and nephrology: a review. NPJ Digit Med 2020; 3: 36.
2. Sabanayagam C, Banu R and Lim C: Artificial intelligence in chronic kidney disease management: a scoping review. J Nephrol 2024; 37(2): 435-450.
3. Nicosia A, Cancilla N and Guerrero JDM: Artificial Intelligence in Nephrology: From Early Detection to Clinical Management of Kidney Diseases. Bioengineering 2023; 10(10): 1069.
4. Chaudhuri S, Long A and Zhang H: Artificial intelligence enabled applications in kidney disease. Semin Dial 2021; 33(6): 441-452.
5. Neri L, Zhang H and Usvyat LA: Artificial intelligence in kidney disease and dialysis: from data mining to clinical impact. Curr Opin Nephrol Hypertens 2026; 35(1): 30-35.
6. Rajpurkar P, Chen E and Banerjee O: AI in health and medicine. Nat Med 2022; 28(1): 31-38.
7. Isaza-Ruget MA, López-Vargas PA and Tong A: Predicting chronic kidney disease progression using artificial intelligence. BMC Nephrol 2024; 25: 345.
8. Okita J, Nakata T and Uchida H: Development and validation of a machine learning model to predict time to renal replacement therapy in chronic kidney disease. BMC Nephrol 2024; 25: 101.
9. Chan L, Nadkarni GN and Fleming F: Derivation and validation of a machine learning risk score for CKD progression. Kidney 360 2021; 2(2): 243-254.
10. Kanda E, Epureanu BI, Adachi T and Kashihara N: Machine learning-based web system for prediction of chronic kidney disease progression and mortality. PLOS Digit Health 2023; 2(1): 0000188.
11. Aoki Y, Kawazoe Y and Iwagami M: Development and validation of machine learning models for predicting renal replacement therapy in critically ill patients. Kidney Med 2023; 5(3): 100692.
12. Zappalà S, Alfieri F and Ancona A: Development and external validation of a machine learning model for prediction of persistent acute kidney injury stage 3 in multicentric multinational intensive care cohorts. Crit Care 2024; 28: 189.
13. Luo XQ, Zhao Y and Zhang J: Machine learning for early discrimination between transient and persistent acute kidney injury in critically ill patients with sepsis. Sci Rep 2021; 11: 99840.
14. Alfieri F, Ancona A and Tripepi G: Continuous early prediction of moderate-to-severe acute kidney injury: multicenter multinational external validation. PLOS One 2023; 18(7): 0287398.
15. Shi J, Han H, Chen S, Liu W and Li Y: Machine learning prediction of acute kidney injury in sepsis critical care patients. PLOS One 2024; 19(4): 0301014.
16. Le S, Allen A and Calvert J: Convolutional neural network model for intensive care unit acute kidney injury prediction. Kidney Int Rep 2021; 6(5): 1289-1298.
17. Ding X, Li Y and Zhang Z: Machine learning model for early prediction of acute kidney injury in heatstroke patients using the first 24 hours of hospitalization data. Sci Rep 2025; 15: 17590.
18. Okawa T, Mizuno T and Hanabusa S: Machine learning-based prediction model of cisplatin-induced acute kidney injury in older adults. PLOS One 2022; 17(1): 0262021.
19. Kowalewski KF, Egen L and Fischetti CE: Artificial intelligence for renal cancer: From imaging to histology and beyond. Asian J Urol 2022; 9(3): 243-252.
20. Distante A, Marandino L and Bertolo R: Artificial intelligence in renal cell carcinoma histopathology: current applications and future perspectives. Diagnostics 2023; 13(13): 2294-2310.
21. Shmatko A, Ghaffari Laleh N and Gerstung M: Artificial intelligence in histopathology: Enhancing cancer research and clinical oncology. Nat Cancer 2022; 3(9): 1026-1038.
22. Giulietti M, Cecati M and Sabanovic B: The role of artificial intelligence in the diagnosis and prognosis of renal cell tumors. Diagnostics 2021; 11(2): 206-220.
23. Yoo D, Lee J and Park S: A machine learning-driven virtual biopsy system for donor kidney day-zero biopsy findings. Nat Commun 2024; 15: 1045.
24. Li X, Davis RC and Xu Y: Deep learning-based segmentation of glomeruli on kidney donor frozen sections. J Med Imaging (Bellingham) 2021; 8(6): 067501.
25. Dong J, Zhang M and Yang X: Machine learning method to predict 1-year mortality risk in maintenance hemodialysis patients. BMC Nephrol 2025; 26: 568.
26. Xu D, Zhou B and Zhang J: Prediction of hyperkalemia in ESRD patients by identification of multiple leads on ECG. Ren Fail 2023; 45(1): 2212800-2212812.
27. Zhou F, Lu Y and Xu Y: Correlation between neutrophil-to-lymphocyte ratio and contrast-induced acute kidney injury and machine-learning models. Ren Fail 2023; 45(2): 2258983-2258995.
28. Altini N, Cascarano GD and Brunetti A: Deep learning instance segmentation for global glomerulosclerosis assessment in donor kidney biopsies. Electronics (Basel) 2020; 9(11): 1768.
29. Marsh JN, Matlock MK and Kudose S: Deep learning global glomerulosclerosis in transplant kidney frozen sections. JAMA Netw Open 2021; 4(2): 2030939.
30. Dovgan E, Gradišek A and Luštrek M: Machine learning models for predicting initiation of renal replacement therapy among chronic kidney disease patients. PLOS One 2020; 15(6): 0233976.
31. Haider HA, Hussain M and Kharisma IL: Predictive Analysis of Chronic Kidney Disease in Machine Learning Eng Proc 2025; 107(1): 118.
32. Salybekov AA, Wolfien M and Hahn W: Artificial Intelligence reporting guidelines’ adherence in nephrology for improved research and clinical outcomes. Biomedicines 2024; 12(3): 606.
33. Oh SW, Byun SS and Kim JK: Machine learning models for predicting the onset of chronic kidney disease after nephrectomy. BMC Med Inform Decis Mak 2024; 24: 85.
34. Bai Q, Su C, Tang W and Li Y: Machine learning to predict end-stage kidney disease in chronic kidney disease. Sci Rep 2022; 12: 8377.
35. Ghosh SK and Khandoker AH: A machine learning-driven nomogram for predicting chronic kidney disease stages 3–5. Sci Rep 2023; 13: 21613.
36. Chuah LL, Khatri R and Teo BW: Machine learning improves clinicians’ prediction of end-stage kidney disease. Front Med (Lausanne) 2022; 9: 837232.
37. Tsai MH, Hsu CY and Lin MY: Integrated machine learning predictive scheme for longitudinal laboratory data to evaluate renal function changes in chronic kidney disease. Front Med (Lausanne) 2023; 10: 1155426.
38. Liu X, Cruz Rivera S, Moher D, Calvert MJ and Denniston AK: SPIRIT-AI and CONSORT-AI Working Group. Reporting guidelines for clinical trials involving artificial intelligence: CONSORT-AI extension. BMJ 2020; 370: 3164.
39. Nakagawa N, Sofue T and Kanda E: J-CKD-DB: a nationwide multicentre electronic health record-based chronic kidney disease database in Japan. Sci Rep 2020; 10(1): 7351-7362.
40. Chen H, Huang Y and Chen L: Ensemble machine learning for predicting renal function decline in chronic kidney disease: development and external validation. Front Med (Lausanne) 2025; 12: 1598065.
41. Rivera SC, Liu X and Chan AW: SPIRIT-AI extension for clinical trial protocols involving artificial intelligence. BMJ 2020; 370: 3210.
42. Collins GS, Moons KGM and Dhiman P: TRIPOD+AI statement: updated reporting guidance for clinical prediction models using artificial intelligence. BMJ 2024; 385: 078378.
43. Collins GS, Dhiman P and Andaur Navarro CL: Protocol for the development of the TRIPOD-AI reporting guideline. BMJ Open 2021; 11(7): 048008.
44. Sounderajah V, Ashrafian H and Golub RM: Developing specific reporting guidelines for diagnostic accuracy studies using artificial intelligence: STARD-AI protocol. BMJ Open 2021; 11(6): 047709.
45. Gottlieb ER, Samuel M and Bonventre JV: Machine learning for acute kidney injury prediction in the intensive care unit. Advances in Chronic Kidney Disease 2022; 29(5): 431-438.
    

    ---

    How to cite this article:

    Awasthi A, Yadav A and Jain DK: Emerging role of artificial intelligence in kidney disease diagnosis and management. Int J Pharm Sci & Res 2026; 17(6): 1750-57. doi: 10.13040/IJPSR.0975-8232.17(6).1750-57.

    ---

    All © 2026 are reserved by International Journal of Pharmaceutical Sciences and Research. This Journal licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.