Topic Discussion: Artificial Intelligence in Nephrology

Artificial intelligence(AI) is on a rise in science. Using it in medicine and specifically nephrology is sure to come.

According to the dictionary, AI is “the theory and development of computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages.”

Dr Eric Topol has been a big proponent of this concept in medicine for years and recently has written a book called “Deep Medicine “ that details the potential uses of this in medicine.

Basically, AI can help in three main ways: 1) diagnosis that is often challenging in various challenging syndromes and even basic common ones. 2) make the physician’s life easier and decrease paper work and finally leading to the third -the most important 3) spending more time at the bedside.

AI is done via creating an  artificial neural network (ANN ) which is simply a collection of artificial neurons organized in layers. In a recent article in AJKD, authors discuss the potential use of this concept in Nephrology. They describe using it for IgA nephropathy(IgAN) as a recognizable cause for AKI. The ability to identify the patients that will progress to ESRD with IgAN would be useful for prognostic and therapeutic reasons. Geddes et al hypothesized that there exists a function that associates clinical and biological parameters measured at the time of IgAN diagnosis (namely age, sex, blood pressure, proteinuria, serum creatinine level, and antihypertensive treatments) to the probability of developing progressive IgAN. The authors designed and implemented an ANN to approximate this function. The results showed that their ANN could predict the occurrence of progressive IgAN more accurately than experienced nephrologists (correct predictions, 87% vs 69.4%; sensitivity, 86.4% vs 72%; and specificity, 87.5% vs 66%). Hmm, now this might be interesting to help guide a lot of therapies in Nephrology. This might be very useful in transplantation and prognosticating even need for dialysis for the elderly CKD patients.

Interestingly, many AI algorithms have been approved by FDA that are used in clinical practice:- some examples are of Atrial fibrillation detection, EF ECHO determination, Coronary calcium scoring, CT brain bleed diagnosis, device for paramedic stroke diagnosis, breast density via mammography to name a few.  No nephrology related such algorithms are approved to my knowledge.

There is an entire journal dedicated for this in medicine now

https://www.journals.elsevier.com/artificial-intelligence-in-medicine

Nephrologists, let’s get started and catch on!

Topic Discussion: Osmotic Nephrosis

Osmotic nephrosis describes a morphological pattern with vacuolization and swelling of the renal proximal tubular cells.

What does the pathology show:

Usually there is acute tubular necrosis–like changes. Histologically, osmotic nephrosis is characterized by a focal or, less often, diffuse “clear-cell” transformation of proximal tubular epithelial cells showing isometric fine vacuolization of the cytoplasm . The straight part of the proximal tubule primarily is involved and, in severe cases, also the convoluted part. Severely affected tubules are often seen side by side with normal-appearing tubules. Distal tubules and collecting ducts are more or less unchanged

Classic known causes of this entity are:

Intravenous immune globulin preparation(sucrose based)

Mannitol Dextrans
Contrast media
Hydroxyethyl starch
Glucose

How does one differentiate this from vacuolization seen with tacrolimus and cyclosporine? Is that a form of osmotic nephrosis?

Renal Pathologist Dr Lynn Cornell nicely describes this on twitter with these images. The image below shows isometric vacuolization in CNI toxicity. This leads to have focal tubules with this change( see arrow)

In osmotic nephrosis, tends to show vacuolated cytoplasm in tubules diffusely( see below)

Osmotic nephrosis describes a morphological pattern with vacuolization and swelling of the renal proximal tubular cells.

In addition, In paraffin sections, the isometric vacuolization seen in patients with calcineurin-inhibitor toxicity may be indistinguishable from osmotic nephrosis. However, electron microscopy shows dilated endoplasmatic reticulum as the cause of vacuolization in the former.  Osmotic nephrosis cannot be differentiated from lipid storage in tubular cells (foam cells), as seen in patients with nephrotic syndrome, liver failure, or intoxication. In such cases, foam cells also are often found in large amounts in the interstitial space. This does not occur in osmotic nephrosis.

The above image shows  osmotic nephrosis in a kidney biopsy specimen. (A, B) Tubular cross-section with seemingly no lumen. Epithelial cells are massively swollen, cytoplasm is completely filled by vacuoles of about the same size (isometric vacuoles), and nuclei are displaced to the base of the cells and distorted by adjacent vacuoles( source https://www.ajkd.org/article/S0272-6386(07)01592-2/pdf

In the NEWS: The New Kidney Health Order

Few weeks ago, there was an executive order signed to advance kidney health in the US. This is an historic event for the field of Nephrology and for kidney patients. The above image is a visual abstract that summarizes the changes that might be coming in 2020. This image is courtesy of Dr Tejas Desai @nephondemand

The goal of this order is to increase home dialysis options, increase organ transplantation and promote kidney health and keep patients "away from dialysis".  In addition, several incentives have been built in to allow for improved compensation for physicians and what looks like better options for patients. What does this mean for Nephrology?- Time will tell but this is a huge improvement in terms of patient care and patient choices. Hope this also sparks some more interest in the field of nephrology where we are still struggling for trainees.

Concept Map: Oral Agents to treat Hyperkalemia- a summary

This is a concept map of the 3 oral GI agents used to treat hyperkalemia.

Topic Discussion: Amyloidosis and Renal Infarction

Usually when we think of amyloidosis in the kidney- we think of paraprotein mediated amyloidosis (AL or AH) leading to nephrotic syndrome and in some rare cases- vascular amyloid presenting as AKI.

A recent study published in Mayo Clinic Proceedings suggests that renal infarction might be a common finding in patients with cardiac amyloidosis. Three groups of patients were identified according to the underlying amyloidosis disorder: AL amyloidosis in 24 patients, mutated-transthyretin amyloidosis in 24 patients, and wild-type transthyretin amyloidosis in 39 patients. Patients with AL amyloidosis had significantly higher N-terminal pro-B-type natriuretic peptide levels (P=.02) and were more likely to have nephrotic syndrome (P<.001). Renal infarction was detected in 18 patients (20.7%), at similar frequencies in the various groups. The likelihood of RI diagnosis was 47.1% (8 of 17) in the presence of AKI and 14.5% (10 of 69) in its absence (P=.003).  Renal infarction (defined by defect(s) on the DSMA scan) was reported in 20.7% of patients with and 25% without evidence of cardiac amyloidosis. Prior studies have not really shown any association like this before of amyloidosis and infarction. Renal infarcts were described in an autopsy study in 3 kidneys that had either cast nephropathy, plasma cell nodules, or autolysis but not with amyloid deposits. Dang et al interesting are reporting is a high percentage of abnormal DSMA scans in patients with wild-type transthyretin amyloidosis (wtATTR) and mutant transthyretin amyloidosis (mATTR) amyloidosis.

These findings are intriguing. The 20% to 25% prevalence reported by Dang and colleagues was therefore unexpected. Renal involvement in ATTR is thought to be rare, especially in patients with wtATTR amyloidosis. Recent drugs used to treat this form of amyloidosis might lead to a glomerulonephritis( my recent post). The finding from the current study suggests that we may be vastly underestimating the prevalence of kidney involvement in ATTR amyloidosis. These patients usually don’t present with nephrotic range proteinuria but more with AKI and subacute AKI. Perhaps, instead of labeling all of these as cardio-renal syndrome, we should consider looking for renal infarction in these patients. And as I have always thought about ruling out amyloidosis in young males who present with renal infarction, I usually stop at AL-AH amyloidosis testing. Given the above findings, perhaps an amyloid scan to look for wtATTR and mATTR might be important as perhaps renal infarction could be a potential relationship here. 

Quite an interesting association!!

Topic Discussion: Tumor Lysis Syndrome with immunotherapy

At this point the nephrology and oncology community is very aware of the AIN, glomerular diseases including vasculitis and ATN seen with check point inhibitors… but we might not be aware of tumor lysis syndrome that this drug can entice in certain patients. 

In the last 2 years, I found several published reports of TLS with check point inhibitors.

Here is a table I created to help with the theme on this one

Immunotherapy	Age	Gender	Cancer type	Time to TLS	Dialysis needed?	Outcome	Reference
Nivolumab	76	Male	Melanoma	5	Yes but declined	Disease progression-death	http://www.alliedacademies.org/articles/acute-tumor-lysis-syndrome-after-antipd1-immunotherapy-nivolumab-for-metastatic-melanoma-8038.html
Atezolizumab	77	Female	GU cancer	14	Yes	Disease progression-death	http://www.acanceresearch.com/cancer-research/tumor-lysis-syndrome-following-a-single-atezolizumab-infusion-for-metastatic-urothelial-carcinoma-involving-both-upper-and-lower-t.php?aid=18193
Atezolizumab	-	-	Solid tumor	-	-	-	https://www.ncbi.nlm.nih.gov/pubmed/25428504
Atezolizumab	-	-	Solid tumor	-	-	-	https://www.ncbi.nlm.nih.gov/pubmed/25428504
Ipilumumab	73	Male	Melanoma	6	No	Death	https://www.ncbi.nlm.nih.gov/pubmed/27256718
Nivolumab	74	Male	RCC	2	No	Death	https://medcraveonline.com/JCPCR/JCPCR-08-00271.php

Based on this, it is seen with PD-1, PDL1 and CTLA4 inhibitors and melanoma and urological cancers. A recent review in JON showed a case of a patient getting TLS with melanoma.  So it’s hard to tell if these agents are causing it or is it the burden of tumor- usually solid tumors in these cases.

Concept map: Hyponatremia in the cancer patient

This concept map was adapted and inspired by Umut Selamet and Ala Abudayyeh, both onconephrologists.