Dear Editor,
I read the article titled “Mind the Gap in Kidney Care: Translating What We Know into What We Do” by Luyckx et al.,[1] as published in JFMPC. (2024). With much appreciation, I must acknowledge the thorough investigations the authors did to prepare a comprehensive review of the present scenario on kidney diseases.
They have successfully highlighted the immediate need to fill the gap between routinely followed procedures and the current understanding on diagnosis and treatment of kidney diseases, more so as advancing medical care promises a very good outcome if prompt treatment is available to patients.
Early identification and intervention are crucial to improving patient outcomes in CKD. The article clearly highlights the limitations of present techniques, particularly the over-reliance on creatinine as a marker of renal function.
The present approach for the diagnosis of CKD relies heavily on the measurement of Serum creatinine. However, because of its limited sensitivity and specificity, serum creatinine misses early diagnosis and prompt intervention during the golden window period when the damage to the kidney is still at the reversal stage. Furthermore, serum creatinine rises late, by which significant damage to the kidney has already occurred.
In this context, I feel if any diagnostic-cum-monitoring algorithm is created by integrating computational techniques with multiple biomarkers assessment, it will help in the early diagnosis of kidney illness.
The multiple biomarker assessment approach has the possibility to provide a better and more comprehensive view of kidney functions. These can include many kidney biomarkers such as NGAL, cystatin C, microalbuminuria, beta-2 microglobulin, eGFR, and KIM-1 in addition to serum creatinine and osmolality.[2] These markers are more sensitive and specific to kidney ailments as compared to other unrelated contributing factors.
Furthermore, the development and availability of automated procedures for these biomarkers by immunoturbidimetry- and nephelometry-based analytical kits has greatly increased clinicians’ access to these biomarkers, allowing for faster and more precise diagnosis.[3]
However, the true potential of this multiple biomarkers study lies in its combination with computational approaches. Effective algorithms, which are capable of integrating all or some of these biomarkers, will be capable of detecting minute changes suggestive of premature renal failure and can significantly improve diagnostic accuracy.
Machine learning algorithms use enormous datasets to detect patterns and relationships between kidney function and these biomarkers, allowing for highly accurate CKD prediction.[4] These algorithms then can be used for risk assessment and can also be trained to suggest medicines customized to patients’ specific biomarker profile. Whenever necessary, more intense monitoring and specific treatment can be provided to high-risk people.[4] Personalized medicine, in fact, offers more exciting possibilities. Algorithms can be used to build personalized treatment regimens that incorporate individual parameters such as age, gender, and any other comorbidities. This will also prompt optimization of the treatment offered, which ultimately will improve patient outcomes.[4] This can be further enhanced by integrating the algorithm with patients’ electronic health records, which will ensure monitoring of patients’ kidney function in real-time and even remotely.[4] As artificial intelligence can quickly analyze large datasets and can generate prediction models, it can greatly improve kidney care.[4]
In conclusion, a new approach is required due to over-reliance on serum creatinine as the sole evidence of kidney function. This gap, as identified by Luyckx et al., can be closed by incorporating multiple biomarkers assessment and a powerful computational algorithm. This will totally change the way CKD is diagnosed, resulting in early interventions and significantly improved patient outcomes.
Conflicts of interest
There are no conflicts of interest.
Funding Statement
Nil.
References
- 1.Luyckx VA, Tuttle KR, Abdellatif D, Correa-Rotter R, Fung WW, Haris A, et al. Mind the gap in kidney care: Translating what we know into what we do. J Family Med Prim Care. 2024;13:1594–611. doi: 10.4103/jfmpc.jfmpc_518_24. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 2.Padhy M, Kaushik S, Girish MP, Mohapatra S, Shah S, Koner BC. Serum neutrophil gelatinase associated lipocalin (NGAL) and cystatin C as early predictors of contrast-induced acute kidney injury in patients undergoing percutaneous coronary intervention. Clin Chim Acta. 2014;435:48–52. doi: 10.1016/j.cca.2014.04.016. https://doi.org/10.1016/j.cca.2014.04.016. [DOI] [PubMed] [Google Scholar]
- 3.Zhang WR, Parikh CR. Biomarkers of acute and chronic kidney disease. Annu Rev Physiol. 2019;81:309–333. doi: 10.1146/annurev-physiol-020518-114605. https://doi.org/10.1146/annurev-physiol-020518-114605. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 4.Topol EJ. High-performance medicine: The convergence of human and artificial intelligence. Nat Med. 2019;25:44–56. doi: 10.1038/s41591-018-0300-7. https://doi.org/10.1038/s41591-018-0300-7. [DOI] [PubMed] [Google Scholar]