Goli Sri Charan Nivas completed his MBBS at Sri Devraj Urs Medical College in Kolar. 

He earned a University Gold Medal while studying MD [Pediatrics] at the Dutta Meghe Institute of Medical Sciences in Wardha, Maharashtra. 

He specialized in nephrology and earned a DM [nephrology] from Andhra Medical College in Visakhapatnam with a university gold medal. 

INDIAai interviewed Goli Sri Charan Nivas for his perspective on using AI in healthcare.

Tell us about your clinical background. What motivated you to go into nephrology?

My clinical journey started in 2012 when I interned at Sri Devraj Urs Medical College, Kolar, followed by an MD in paediatrics from Jawaharlal Nehru Medical College, Wardha, with a university gold medal. I worked as an assistant professor at GITAM Medical College, Vizag, followed by DM Nephrology from Andhra Medical College, Visakhapatnam, with a university gold medal in Nephrology. Now, I am working as a consultant at LG Hospitals, Visakhapatnam. Nephrology is a branch that is an extension of medicine, and kidney injury can occur secondary to any organ involvement. Diagnostic challenges always excite me, and treating their problems gives me immense satisfaction. The speciality also involves dealing with various electrolyte abnormalities in the body, which tests our mathematical minds.

Is it possible to predict acute kidney injury with any parameters?

An elevation of serum creatinine historically diagnoses AKI. The KDIGO criteria define an increase in SCr of ≥ 0.3 mg/dL within 48 hours, an increase in SCr of 1.5 to 1.9 times baseline within the prior seven days, or reduced urine output over 6–12 hours. Over the last few decades, a large number of biomarkers were extensively reasserted and tested; some had advantages over others, such as cystatin C and neutrophil gelatinase-associated lipocalin [NGAL], etc., but they are practically far less commonly used even today. There is a persistent unmet need for earlier identification of patients with AKI. Furthermore, diagnostic tools that identify AKI's location, mechanism, etiology, severity, and prognosis are necessary.

Recent research states that AI applications can accurately predict the onset of acute kidney injury before notable biochemical changes occur. What is your view on this?

Several AI techniques have been employed to improve the ability to detect AKI across various hospitalized settings. Research is underway in using plenty of algorithms to the detriment of logistic regression to develop predictive models with the help of artificial intelligence. Still, more research is needed for the accurate prediction of AKI.

What is your opinion on using AI applications in diagnostics and prognostics for high-prevalence and high-morbidity types of nephropathy? Have you tried any AI applications?

AI can help clinicians make more accurate and timely diagnoses by analyzing vast amounts of patient data and identifying patterns that may not be visible to the human eye. By incorporating AI into clinical practice, clinicians can make more informed decisions, leading to better patient outcomes. ML (Machine learning) is a significant branch of AI in which computers are trained using algorithms and statistical models to learn and analyze sample data. Integrating clinical expertise with ML experts opens up new possibilities to provide the best predictions to the patient. In our clinic, we are using Fundus images of the eye, with the help of AI, to detect Diabetic Retinopathy, which in turn helps our Diabetic patients assist in the diagnosis of Diabetic Nephropathy. A new era of AKI prediction and detection has started with the increasing use of risk prediction scores and e-alerts.

An AI tool that can predict the 10-year risk of deadly heart attacks could transform treatment for patients who undergo CT scans to investigate chest pain, according to British Heart Foundation-funded research. What is your view?

Yes, true. According to British Heart Foundation-funded research, AI technology could save the lives of thousands with chest pain who may not have been identified as at risk of a heart attack. AI tools could be hugely valuable in guiding and informing how patients with chest pain are managed, ensuring early identification and preventative treatment of those at the highest risk.

Current research on AKI mainly focuses on risk prediction, detection, and automatic alerting. The use of automated electronic alerts (e-alerts) has received considerable attention. England's National Health Service recommended widely adopting automated computer software for detecting AKI. Google has developed the Streams Program, which may predict AKI and alert doctors for early intervention. Can we use such tools in the future in India?

Using automated electronic alerts for AKI detection is a promising avenue, but successful implementation in India would require addressing the infrastructure and cost. Government support and initiatives can significantly impact the adoption of new technologies and their implementation.

Kindly furnish details regarding the technology apps and tools you frequently employ in your clinic.

We are still in the early phase of utilizing AI. We are using teleconsultation and telepharmacy after the COVID-19 pandemic. Machine learning techniques are used in our research to analyze extensive patient data. In kidney transplants, the connection between the donor and recipient is particular and time-consuming. Technological advances in transplant technology, such as RNA matching, enable us to pick the correct pair of patients. AI is helping in the accumulation of large amounts of data by reducing the time taken to attain results, thereby reducing the time taken for workup before we do transplant.

What is your future goal in nephrology research?

I am exploring AI-driven diagnostics and predictive models to help detect kidney injury early and find biomarkers that can help in the prognostication of kidney disease—improving Remote Monitoring and Telemedicine in Nephrology, thereby taking medical care in remote villages in India and trying more innovations in renal replacement therapies to improve quality of life in renal failure patients. Finally, I would like to see wearable devices such as Apple watches showing even kidney health with the help of AI.