United States

Background
Chronic Kidney Disease of unknown etiology (CKDu) is a progressive form of kidney damage that disproportionately affects agricultural communities in Sri Lanka, Central America, and parts of India, with emerging hotspots also suspected in the South and Western United States. Despite extensive investigation, the underlying causes of CKDu remain unclear, partly because of a potential long lag between exposure and eventual symptomatic presentation of kidney disease. We applied machine learning (ML) and large language models (LLMs) to explore predictive tools for disease progression in a cohort of persons with CKDu, with the hypothesis that early identification of persons likely to experience kidney function decline will facilitate investigation of proximal (causative) exposures.
Methods
We analyzed baseline data (labs demographics) from 244 participants enrolled in Kidney Progression Project (KiPP), a prospective cohort of farmworkers with kidney disease in Sri Lanka launched in 2018. Among these participants, 22 progressed to the study’s primary outcome (eGFR&lt;15 mL/min/1.73 m²) by the year 2024. For model development, we used data from the first 2.5 years of follow-up.
We developed and optimized several ML classifiers including logistic regression, support vector machines, random forests, and XGBoost. Each model was trained using stratified five-fold cross-validation, and class imbalance was addressed using SMOTE-based oversampling. To identify underlying patterns in the dataset, we applied unsupervised models like K-means clustering(k=7), and the resulting cluster labels were included as categorical features in supervised learning models. Model performance was evaluated using standard classification metrics, and interpretability was assessed using SHAP (SHapley Additive exPlanations). 
Additionally, we used clinical vignettes from KiPP data to evaluate the predictive capabilities of LLMs. We tested five LLMs through SecureGPT on their ability to predict progression.
Results
The best performing ML model was an XGBoost classifier (ROC-AUC= 0.84; F1 score= 0.48). SHAP analysis identified cluster membership and serum uric acid as key predictors. Among the LLMs, GPT 4.5 performed best (Accuracy= 87%; F1 score of 0.42). Both models outperformed existing methods (eGFR slope, Accuracy=67%, F1 score=0.23). 
Conclusion
Our findings demonstrate that both traditional ML models and LLMs can predict CKDu progression from limited clinical data. Custom-tailored ML models slightly outperformed generative AI models such as GPT-4.5. With continued refinement, these tools may not only support early identification of high risk individuals but also aid in identifying causes of CKDu. Future directions include external validation using ongoing international cohorts and incorporation of longitudinal laboratory data to generate clinically-deployable AI tools.


2025 AMA Research Challenge – Member Premier Access

From Algorithms to Agriculture: Applying AI Methods to Predict Kidney Disease in Farmworkers

Background
Chronic Kidney Disease of unknown etiology (CKDu) is a progressive form of kidney damage that disproportionately affects agricultural communities in Sri Lanka, Central America, and parts of India, with emerging hotspots also suspected in the South and Western United States. Despite extensive investigation, the underlying causes of CKDu remain unclear, partly because of a potential long lag between exposure and eventual symptomatic presentation of kidney disease. We applied machine learning (ML) and large language models (LLMs) to explore predictive tools for disease progression in a cohort of persons with CKDu, with the hypothesis that early identification of persons likely to experience kidney function decline will facilitate investigation of proximal (causative) exposures.
Methods
We analyzed baseline data (labs demographics) from 244 participants enrolled in Kidney Progression Project (KiPP), a prospective cohort of farmworkers with kidney disease in Sri Lanka launched in 2018. Among these participants, 22 progressed to the study’s primary outcome (eGFR<15 mL/min/1.73 m²) by the year 2024. For model development, we used data from the first 2.5 years of follow-up.
We developed and optimized several ML classifiers including logistic regression, support vector machines, random forests, and XGBoost. Each model was trained using stratified five-fold cross-validation, and class imbalance was addressed using SMOTE-based oversampling. To identify underlying patterns in the dataset, we applied unsupervised models like K-means clustering(k=7), and the resulting cluster labels were included as categorical features in supervised learning models. Model performance was evaluated using standard classification metrics, and interpretability was assessed using SHAP (SHapley Additive exPlanations). 
Additionally, we used clinical vignettes from KiPP data to evaluate the predictive capabilities of LLMs. We tested five LLMs through SecureGPT on their ability to predict progression.
Results
The best performing ML model was an XGBoost classifier (ROC-AUC= 0.84; F1 score= 0.48). SHAP analysis identified cluster membership and serum uric acid as key predictors. Among the LLMs, GPT 4.5 performed best (Accuracy= 87%; F1 score of 0.42). Both models outperformed existing methods (eGFR slope, Accuracy=67%, F1 score=0.23). 
Conclusion
Our findings demonstrate that both traditional ML models and LLMs can predict CKDu progression from limited clinical data. Custom-tailored ML models slightly outperformed generative AI models such as GPT-4.5. With continued refinement, these tools may not only support early identification of high risk individuals but also aid in identifying causes of CKDu. Future directions include external validation using ongoing international cohorts and incorporation of longitudinal laboratory data to generate clinically-deployable AI tools.


poster

Congratulations to all the researchers who have qualified for the AMA Research Challenge virtual poster symposium and semifinals!

Welcome to the **largest national, multi-specialty research event** featuring research from nearly 1,000 medical students, residents, fellows, and international medical graduates across six topic areas - basic science, clinical and translational research, clinical vignettes, health systems science, medical education, and public health and health policy.

#### Access the Event
Use the buttons below or navigation menu to access the event. 

[![](https://assets.underline.io/markdown_image/1/image/d4076f2146939317a29eb9f69c53ad41.png)](https://underline.io/events/506/sessions?searchGroup=all)
[![](https://assets.underline.io/markdown_image/1/image/6bcee0b523a4874c4292ca0415d88dde.png)](https://underline.io/events/506/posters?searchGroup=all)
[![](https://assets.underline.io/markdown_image/1/image/0ca1b933deefd7731529477b45345166.png)](https://underline.io/events/506/schedule)

#### Event Details
The 2025 AMA Research Challenge includes the following symposium halls:
* **Semifinals hall:** Features research from 54 medical students, residents and international medical graduates that received top scores during first round scoring. 
* **Poster symposium hall:** Features research from nearly 1,000 medical students, residents and international medical graduates categorized by topics and subtopics.

**Here’s how to participate:**
* **View posters and presentations** on a variety of topics and specialties
* **Score posters in the semifinals** to help decide the top five finalists (AMA member exclusive opportunity)
* **Connect with presenters** and provide feedback to help advance their research
* **New this year: Watch live poster presentations** by topic area and engage directly with researchers

At the conclusion of this event, the AMA will announce the top five finalists who will advance to the AMA Research Challenge final round, present their research to an elite panel of judges, and compete to win a $10,000 grand prize presented by Laurel Road.

#### A message from Dr. Bobby Mukkamala, AMA President
<div style="position: relative; width: 100%; padding-bottom: 56.25%; height: 0; overflow: hidden;">
  <iframe 
    src="https://underline.io/embed/136894-ama-video?t=0"
    title="AMA Welcome Video"
    allowfullscreen
    style="position: absolute; top: 0; left: 0; width: 100%; height: 100%; border: 0;">
  </iframe>
</div>


#### Recognized Institutions
In 2025, 1,400 abstracts were submitted across six topic areas representing 174 medical schools and more than 150 residency and health care institutions. [See if your institution is represented this year!](https://drive.google.com/file/d/1eFrTqCmCeobx9pr5drJK2hllvsIpFNOY/view?usp=drive_link)

#### Grand Prize Sponsor
AMA would like to thank Laurel Road, a brand of KeyBank, for sponsoring a $10,000 grand prize for the winner of the AMA Research Challenge. Laurel Road and KeyBank are not involved in winner selection process. The winner will be announced during the AMA Research Challenge final round. Payment of the grand prize will be directly from Laurel Road/KeyBank. See the [AMA Research Challenge Official Rules for terms and conditions](https://www.ama-assn.org/system/files/research-challenge-official-rules.pdf).

[![](https://assets.underline.io/uploads/markdown_image/1/image/611e331d4a0eba0920f240cfc04b4d77.png)](https://www.laurelroad.com/)

#### Code of Conduct
<html>
AMA has a code of conduct for its meetings – we ask all attendees to adhere to this code to participate in this year’s meeting. Please read and <a href="https://www.ama-assn.org/about/code-conduct" target="_blank">learn more here</a> about your conduct requirements.
<br><br>
	</html>
	

#### Semifinals Judges

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Need help? Contact us at <support@underline.io>.

Please log in to explore this event.

If you have used the AMA Research Challenge platform previously, please click the ‘Log-in’ button below. If you do not remember your password, please click “forgot password” and follow prompts to reset your password. After resetting your password, please refresh your webpage to access the platform. 

Register to explore research in a variety of topics. AMA members get exclusive access to score posters in the semifinals. 

**Please use [this link here](https://www.ama-assn.org/member-benefits/events/ama-research-challenge) to register for free. **

Registration Is Required

Join the AMA Research Challenge poster symposium and semifinals to explore top research posters and score posters in the semifinals (an AMA member exclusive opportunity).

Background
Epileptic seizures disrupt normal brain activity, with pathological activity detectable on electroencephalograms. While seizure classification guides diagnosis and treatment, current systems often fail to capture individual variability in drug response, even among patients with similar clinical phenotypes. This dissertation applies dynamotype classification—a framework grounded in bifurcation theory and dynamical systems—to quantify seizure onset and offset patterns and their modulation by antiseizure medications (ASMs).
Methods
Data from over 7500 seizures was analyzed from 100+ mice from two models: the intra-amygdala kainate (IAK) model of temporal lobe epilepsy and the genetic Scn1a+/- model of Dravet syndrome. In the IAK model, spontaneous seizures were tracked over a 90-day period. Dynamotypes were visually scored in a randomized, blinded manner by two human raters and a custom DynamoSort machine learning tool we developed. Seizure onsets were categorized into three dynamotypes: (1) SupH, characterized by increasing spike amplitude (supercritical Hopf); (2) SNIC, by increasing frequency (saddle-node on invariant circle); and (3) SubH, by arbitrary or disorganized features. Seizure offsets were similarly categorized: SupH (decreasing amplitude), SNIC (decreasing frequency), and FLC (fold limit cycle, showing arbitrary declines).
Results
Longitudinal analysis of the IAK model revealed a temporal shift in dynamotype prevalence, with early seizures dominated by arbitrary transitions (SubH, FLC) and later seizures showing more structured bifurcation types (SupH, SNIC). Dynamotypes also predicted seizure duration and severity, with SNIC onset seizures being more severe and FLC offset seizures being longer in duration. Drug trials demonstrated that ASMs selectively modulated bifurcation types in a mechanism-dependent manner. GABAergic drugs (diazepam, phenobarbital) predominantly suppressed seizure onsets, indicating preferential disruption of initiation dynamics. In contrast, sodium channel blockers (phenytoin, valproate) exerted stronger effects on seizure terminations: phenytoin reduced SupH offsets, while valproate increased SNIC offsets in treatment responders, indicating SNIC offset seizures may be pharmacoresistant to VPA. Baseline dynamotype distributions also differed across models. Dravet mice displayed elevated SubH onset proportions relative to IAK, but GABAergic drugs caused similar dynamotype changes, showing conserved responses to ASMs across models.
Conclusion
Overall, this work demonstrates that bifurcation-informed seizure classification captures dynamic features of epileptogenesis and drug response, revealing mechanistically distinct signatures across ASM classes and models. These findings support the use of dynamotypes as a model-driven framework for evaluating treatment efficacy and tailoring therapies in epilepsy.

Seizure Dynamotype Patterns Predict Drug Response in Animal Models of Epilepsy

Oral contraceptive pills (OCPs) are one of the most widely used reversible contraceptive methods in the United States. Since their introduction in the 1960s, OCPs have been prescribed globally for birth control as well as management of hormonally influenced conditions including menstrual irregularities, menorrhagia, dysmenorrhea, acne, premenstrual syndrome, and hormonal migraines. Despite their therapeutic benefits, the effectiveness of OCPs varies between individuals, and the physiological mechanisms underlying these effects remain incompletely understood. While OCPs are known to influence menstrual bleeding patterns, little is known about their impact on the vasculature of the female reproductive system, specifically the uterine and ovarian arteries.
In comparison, intrauterine devices (IUDs) have been studied extensively for their vascular effects. Doppler ultrasound studies, which measure pulsatility index (PI) and resistance index (RI) as indicators of arterial blood flow, generally show no significant vascular changes pre- and post-IUD insertion. However, notable exceptions have been reported between copper and hormonal IUDs. Women experiencing abnormal bleeding with copper IUDs exhibited significant changes in PI and RI; however, another study demonstrated an increased RI in the uterine artery following levonorgestrel IUD (LNG-IUD) placement, potentially explaining its association with reduced menstrual bleeding. Given that copper IUDs tend to increase menstrual bleeding, while LNG-IUDs and OCPs typically reduce it, vascular changes may be an important underlying mechanism. This study aimed to investigate the effects of OCPs on uterine and ovarian artery blood flow using Doppler ultrasound in healthy, nulliparous women and to compare self-reported menstrual symptoms, including pain, cycle regularity, PMS manifestations, and skin changes using a standardized Menstrual Symptom Survey between OCP users and non-users.

The Vascular and Menstrual Symptom Impact of Oral Contraceptives: A Comparative Analysis of Uterine and Ovarian Artery Indices via Doppler Ultrasound

Background: Total hip arthroplasty (THA) alleviates pain and improves mobility in individuals with end-stage hip disease. However, THA patients with neuropathic bladder may face increased postoperative risks. This study aimed to assess how neuropathic bladder conditions influence outcomes after primary THA and propose recommendations to avoid associated complications.

Methods: A retrospective cohort analysis was conducted using data from TriNetX Research Network, including 193,988 patients aged 18 years and older who underwent primary THA between January 1, 2003, and January 1, 2020. Patients were categorized into two cohorts: those with (NB) and without (no-NB) neuropathic bladder conditions prior to THA. Propensity score matching yielded 1,482 patients in each cohort. Rates of postoperative outcomes at 30 days, 90 days, 1 year, and 5 years were compared.

Results: Within 30 days of surgery, NB patients demonstrated significantly elevated rates of urinary tract infection, pneumonia, periprosthetic joint infection (PJI), deep vein thrombosis, and transfusion compared to no-NB patients (P < 0.01). Similar trends continued at 90 days post-THA, with the NB cohort also showing a higher risk of pulmonary embolism and acute renal failure (P < 0.01). Furthermore, the NB cohort faced increased risks of PJI over a 1-year period (risk ratio (RR): 1.8; 95% confidence intervals (CI): 1.3, 2.4) and revision arthroplasty over a 5-year period (RR: 2.6; CI: 1.8, 3.8) compared to the no-NB cohort.

Conclusion: Patients with neuropathic bladder undergoing THA faced significantly elevated risks of postoperative complications, highlighting the need for tailored postoperative management strategies of neuropathic bladder to mitigate these risks and improve THA outcomes.

Assessing the Impact of Neuropathic Bladder on Total Hip Arthroplasty Outcomes:
A Matched Cohort Analysis

Evaluation of Cadaver Lung Tissue and the Histologic Characterization of Viral Interstitial Pneumonitis
Background
Histologic characterization offers a framework for the understanding and diagnosis
of viral interstitial pneumonitis (VIP). Moreover, due to the serious consequence in delayed diagnosis, in particular respiratory failure, the clinical findings and physiology of interstitial pneumonitis are fundamental to prevent mortality. Previous studies highlighted the high mortality associated with respiratory failure from VIP, emphasizing the urgency of diagnosis and treatment [1]. Thus, there is a need for earlier detection and treatment of VIP. Here, human cadaver lung tissue is evaluated and characterized in a cadaver with a known cause of death of “respiratory failure.” Notably, cadaveric studies are relevant due to pathological study of human remains being the gold standard for the diagnosis of many diseases.
Methods
Human lung tissue specimens were collected by dissection from a donated cadaver
made available by the department of anatomy. The samples were processed as standard
tissue specimens to create hematoxylin-eosin stained slides. A board-certified pathologist evaluated the slides under a light microscope to assess alveolar morphology, immune cells, and tissue architecture.
Results
The histologic slides were high quality without evidence of staining or other
artifacts from the embalming process. The lung sections showed diffuse thickening of the alveolar septa with some cuboidalization of the alveolar epithelium. Furthermore, there was presence of a predominantly lymphocytic infiltrate within the lung interstitium, in the absence of bacteria. Together, these findings are highly suggestive of viral interstitial pneumonitis as the underlying mechanism of death.
Conclusion
Lung tissue from human cadavers is particularly useful to observe the histologic
manifestations of lung disease. This cadaveric study and microscopic findings highlight the feasibility in histologic analysis to diagnose viral interstitial pneumonitis. In contrast to the neutrophil-predominant intra-alveolar exudate seen in pneumonia, VIP presents with lymphocyte-predominant interstitial inflammatory infiltrate. By leveraging lung samples and histological analysis at an earlier time, physicians can more rapidly diagnose VIP and initiate appropriate therapy. This ultimately will reduce the risk of respiratory failure and prevent mortality.


Evaluation of Cadaver Lung Tissue and Histologic Characterization of Viral Interstitial Pneumonitis

Abstract Title
Propofol-Induced Cannabinoid Hyperemesis Syndrome in a Chronic Cannabis User

Background

Cannabinoid Hyperemesis Syndrome (CHS) is a paradoxical condition in chronic cannabis users characterized by cyclic nausea and vomiting, despite cannabis's known antiemetic effects. Propofol-induced Cannabinoid Hyperemesis Syndrome (PI-CHS) is an emerging, under-recognized phenomenon in which propofol anesthesia may trigger CHS-like symptoms in chronic cannabis users. The suspected mechanism involves propofol’s lipophilic nature mobilizing stored delta-9-tetrahydrocannabinol (THC) from adipose tissue, potentially precipitating an acute emetic response.

Case Presentation

A 56-year-old male presented at the stand-alone surgical center for a routine screening colonoscopy. He reported daily cannabis use for over 40 years, with no history of chronic illness, alcohol, or tobacco use. His previous colonoscopy, performed six years prior, was followed by severe nausea and vomiting, which he attributed to an unknown cause at the time. Preoperative evaluation was otherwise unremarkable. He denied baseline gastrointestinal symptoms, cyclic vomiting, or any personal or family history of anesthesia complications. Following the current colonoscopy, which was performed under propofol sedation, the patient again developed intractable nausea and vomiting within hours post-procedure, necessitating emergency department evaluation. Workup revealed no surgical or infectious cause. Supportive care and cessation of cannabis use led to resolution of symptoms over several days.

Discussion

This case highlights a potential association between propofol administration and the unmasking of CHS in chronic cannabis users. The theory that propofol may mobilize THC from fat stores into circulation offers a possible mechanism for PI-CHS. As cannabis use continues to rise, anesthesiologists and perioperative providers should be aware of this phenomenon. Preoperative screening for chronic cannabis use may help identify at-risk patients and guide perioperative planning. Further studies are needed to elucidate the pathophysiology of PI-CHS and to establish appropriate prevention and management strategies.


Propofol-Induced Cannabinoid Hyperemesis Syndrome in a Chronic Cannabis User: A Case Report

Title- Intravascular Lithotripsy as a Facilitator for Stenting in Heavily Calcified Subclavian Artery Lesions: A Clinical Case Report

Background- Subclavian artery stenosis is a rare but clinically significant cause of
vertebrobasilar insufficiency and upper extremity ischemia. Management is challenging, especially in the presence of heavily calcified lesions. Intravascular lithotripsy (IVL) is an emerging adjunctive therapy for calcified lesions, primarily studied in coronary and lower extremity vessels; however, its application in subclavian interventions remains minimally studied.

Case Presentation- A 78-year-old female with a history of hypertension, diabetes,
Hyperlipidemia and peripheral artery disease presented with recurrent dizziness and nausea. Carotid duplex demonstrated moderate left internal carotid stenosis and retrograde flow in the left vertebral artery, consistent with subclavian steal syndrome. Subsequent angiography revealed 90% eccentric, calcified stenosis of the proximal left subclavian artery. Given the lesion’s heavy calcification, the patient underwent percutaneous intervention with a Serranator scoring balloon, followed by intravascular lithotripsy (IVL) using an 8x30 mm peripheral balloon (2 rounds, 30 pulses each). This resulted in significant lesion modification and relief of the balloon waist. A 7x27 mm Express LD bare-metal stent was then deployed with excellent angiographic results and residual stenosis <10%. IVUS confirmed adequate stent expansion. The procedure was performed via right femoral access with no complications. Post-procedure, the patient reported complete resolution of dizziness and no further symptoms of vertebrobasilar insufficiency. She was discharged on dual antiplatelet therapy for 30 days, followed by aspirin monotherapy. At 1-month follow-up, she remained asymptomatic with a patent stent and no evidence of restenosis.

Discussion- This case highlights the utility of IVL in treating severely calcified subclavian artery stenosis. Traditional balloon angioplasty and stenting in such lesions are associated with suboptimal expansion, risk of dissection, and restenosis. IVL offers a safe and effective means of calcium modification, facilitating optimal stent deployment. To our knowledge, reports of IVL use in subclavian arteries are scarce, and this case adds to the growing body of evidence supporting its application in complex peripheral vascular interventions. Intravascular lithotripsy is a valuable adjunct in the endovascular management of heavily calcified subclavian artery stenosis, enabling successful stent placement and symptomatic relief. Further studies are warranted to define its role in this vascular territory.

Intravascular Lithotripsy as a Facilitator for Stenting in Heavily Calcified
Subclavian Artery Lesions: A Clinical Case Report

Background: Intentional drug overdose remains a pressing public health issue, with calcium channel blockers (CCBs) frequently involved due to their widespread use in the treatment of hypertension and cardiovascular conditions. CCB toxicity can be particularly lethal, as inhibition of L-type calcium channels may result in severe bradycardia, hypotension, cardiogenic shock, and death. Prompt and aggressive intervention is critical, with emerging evidence supporting advanced therapies such as extracorporeal membrane oxygenation (ECMO) and intravenous lipid emulsion in cases of refractory toxicity. Effective management becomes even more challenging in rural or critical access hospitals (CAHs), where limited resources can delay access to life-saving interventions.

Case Presentation: We report the case of a 15-year-old male who presented to a CAH following intentional ingestion of over 100 pills, including verapamil, sertraline, risperidone, gabapentin, and levetiracetam. Initially stable, the patient rapidly deteriorated, experiencing seizures, unresponsiveness, and hypotension. He was emergently intubated and received activated charcoal, IV fluids, magnesium, norepinephrine, and empiric antibiotics. Despite aggressive stabilization efforts, refractory hypotension persisted, prompting urgent transfer to a quaternary care center. There, he required multiple vasopressors and initiation of veno-arterial ECMO. Hyperinsulinemic euglycemia therapy was also administered. After three days on ECMO and a prolonged ICU course, the patient made a full neurologic recovery and was discharged home on hospital day 11.

Discussion: This case underscores the challenges of managing complex toxicologic emergencies in resource-limited rural settings. Polypharmacy ingestion involving a high-potency CCB like verapamil increases the risk of rapid hemodynamic collapse. Early recognition and prompt stabilization at the CAH enabled safe transfer, demonstrating that favorable outcomes are possible with coordinated care. High-dose insulin therapy and ECMO remain the cornerstone interventions for severe CCB toxicity, especially when conventional therapies fail. Notably, this is only the second pediatric case of CCB overdose reported in the literature to result in full recovery; the first involved acute kidney injury. Our case illustrates the importance of prehospital triage protocols and equitable access to advanced resuscitative therapies like ECMO, even in rural populations.


Pediatric Calcium Channel Blocker Polypharmacy Overdose in a Resource-Limited Emergency Department: Full Recovery After ECMO


Background
Emphysematous pyelonephritis (EPN) is a life-threatening necrotizing infection of the renal parenchyma and surrounding tissues. It is most commonly seen in patients with uncontrolled diabetes and obstructive uropathy. Rapid diagnosis and timely radiologic intervention are essential to prevent progression to sepsis or death.

Case Presentation
A 67-year-old woman with poorly controlled diabetes and recent history of nephrolithiasis presented to the emergency department with fever, chills, altered mental status, and right flank pain. She was febrile, hypotensive, and tachycardic on arrival. Laboratory studies showed leukocytosis, acute kidney injury, and hyperglycemia. Urinalysis revealed pyuria and bacteriuria.
Initial ultrasound showed a markedly echogenic right kidney with poor corticomedullary differentiation and dirty shadowing, raising concern for gas formation. Non-contrast CT confirmed the diagnosis of emphysematous pyelonephritis, demonstrating parenchymal destruction and extensive gas within the renal collecting system and perinephric space.
Given the patient’s instability and imaging findings, she was admitted to the ICU and started on broad-spectrum IV antibiotics. Urology was consulted, and interventional radiology performed emergent image-guided percutaneous nephrostomy and drainage catheter placement. Cultures grew E. coli. Over the following days, the patient’s hemodynamics improved, and nephrectomy was avoided.

Discussion
This case highlights the importance of early imaging in patients with sepsis and risk factors for EPN, such as diabetes and obstructive uropathy. Although nephrectomy has historically been the treatment of choice, image-guided drainage has emerged as a kidney-sparing alternative, particularly in critically ill patients. Ultrasound can provide initial clues, but CT is the diagnostic gold standard. Multidisciplinary collaboration between critical care, urology, and interventional radiology is essential for optimal outcomes.

Emphysematous Pyelonephritis in a Critically Ill Patient: Prompt Diagnosis and Image-Guided Drainage to Avoid Nephrectomy


Background: 
Kawasaki Disease (KD) is an acute, self-limited medium vessel vasculitis of unknown etiology that is the leading cause of acquired heart disease in children in developed countries. Kawasaki disease primarily affects infants and young children, primarily those under the age of 5 years old. The odds of recurrences after the fifth year following recurrence are 4%. We present a case of recurrent KD presenting 8 years following the patient's initial diagnosis at 4 months. 
Case Presentation: 
An 8-year-old male patient with a history of Kawasaki Disease at 4 months presented initially to the ED with 6 days of fever, malaise, bilateral conjunctival injection and one day of bilateral joint pain. There was a recent history of mild viral illness among household contacts. On examination, bilateral erythema of the hands and feet were also noted. The patient also presented with bilateral testicles visualized in the superior inguinal canal on ultrasound. Upon admission, crusting of the oral mucosa, bilateral joint effusion, and unilateral cervical lymphadenopathy were also noted. An echocardiogram demonstrated a mildly distended left anterior descending artery. The patient was diagnosed with KD and subsequently treated with aspirin 325 mg four times a day, IVIG, and methylprednisolone 30 mg twice a day. The patient then experienced significant improvement in appetite, appearance, and decreased neck, joint, and eye pain over the next three days. However, the patient was only followed up 17 days later by pediatrics with no cardiology or urology follow-up 6 months after discharge. 
Discussion: 
In patients whose initial KD occurred at a younger age, there is an increased risk of recurrence. Patients less than <6 months and >9 years old are at an increased risk for diagnosis taking over 12 days. While this patient was quickly treated, delayed diagnosis of KD can result in treatment resistance due to the clinical progression of the disease. KD should be considered in the setting of prolonged fever even at extreme ages of presentation. Furthermore, this case highlights the need for cardiac follow-up for patients with recurrent KD, especially in the setting of recurrence where cardiovascular consequences can be devastating. Those who are >6 years of age are at an increased risk for cardiovascular sequelae compared to those <3 years of age. Thus, the suspicion of cardiac complications must remain high after discharge, and adequate follow-up should be established prior to discharge.

A Case of Kawasaki Disease Recurring 8 years later with Cardiac Complications

Dominic Theodore, MS; Nita Bhatt, MD, MPH Department of Psychiatry, Boonshoft School of Medicine, Wright State University
Background
Cochlear implants are widely used to restore hearing in individuals with severe sensorineural hearing loss. However, their placement in individuals with psychotic disorders presents unique challenges. Historically, psychosis was considered a contraindication to cochlear implantation due to concerns about exacerbating hallucinations and delusions. While research suggests that cochlear implants can improve quality of life, there remains a lack of formal guidelines for their use in individuals with schizophrenia or high-risk psychotic disorders. This case highlights the complex interplay between auditory rehabilitation and psychiatric symptomatology.
Case Presentation
A 47-year-old male with schizophrenia and post-traumatic stress disorder (PTSD) was admitted for competency restoration following legal issues related to delusional beliefs and impaired judgment. His psychiatric history included multiple hospitalizations and persistent auditory hallucinations. He had profound hearing loss secondary to childhood encephalitis, with a cochlear implant placed in 2015. Upon admission, the patient exhibited disorganized thoughts, paranoia, and auditory hallucinations directly involving his cochlear implant. He reported experiencing command hallucinations perceived as broadcasts through the device, as well as delusions that it had been modified into a "Neurolink" system to control his thoughts.
During hospitalization, the patient was treated with olanzapine and haloperidol, leading to some improvement in disorganized behavior and hallucinations. However, paranoid delusions related to surveillance and external control persisted. His case underscores the difficulty in distinguishing auditory hallucinations from implant-related perceptual experiences, further complicating treatment and competency restoration efforts.
Discussion
This case highlights the complexities of treating psychosis in individuals with cochlear implants. While hearing restoration can reduce the social isolation that exacerbates psychosis, it may also introduce distressing experiences in patients predisposed to paranoia or delusions. The absence of formal guidelines for screening or managing psychotic symptoms in cochlear implant candidates raises ethical and clinical concerns. Prior research suggests that cochlear implants are not an absolute contraindication in psychosis, yet careful consideration must be given to patient selection and psychiatric stability. Future research and standardized protocols are needed to optimize care for this unique patient population and to balance the benefits of auditory rehabilitation with the risks of exacerbating psychotic symptoms.

Next from 2025 AMA Research Challenge – Member Premier Access

Seizure Dynamotype Patterns Predict Drug Response in Animal Models of Epilepsy