Keddis, Mira

Background: There is a paucity of evidence to inform the value of pharmacogenomic (PGx) results in patients after kidney transplant and how these results differ between Indigenous Americans and Whites. This study aims to identify the frequency of recommended medication changes based on PGx results and compare the pharmacogenomic (PGx) results and patients’ perceptions of the findings between a cohort of Indigenous American and White kidney transplant recipients. Methods: Thirty-one Indigenous Americans and fifty White kidney transplant recipients were studied prospectively. Genetic variants were identified using the OneOme RightMed PGx test of 27 genes. PGx pharmacist generated a report of the genetic variation and recommended changes. Pre- and post-qualitative patient surveys were obtained. Results: White and Indigenous American subjects had a similar mean number of medications at the time of PGx testing (mean 13 (SD 4.5)). In the entire cohort, 53% received beta blockers, 30% received antidepressants, 16% anticoagulation, 47% pain medication, and 25% statin therapy. Drug–gene interactions that warranted a clinical action were present in 21.5% of patients. In 12.7%, monitoring was recommended. Compared to the Whites, the Indigenous American patients had more normal CYP2C19 (p = 0.012) and CYP2D6 (p = 0.012) activities. The Indigenous American patients had more normal CYP4F2 (p = 0.004) and lower VKORC (p = 0.041) activities, phenotypes for warfarin drug dosing, and efficacy compared to the Whites. SLC6A4, which affects antidepressant metabolism, showed statistical differences between the two cohorts (p = 0.017); specifically, SLC6A4 had reduced expression in 45% of the Indigenous American patients compared to 20% of the White patients. There was no significant difference in patient perception before and after PGx. Conclusions: Kidney transplant recipients had several drug–gene interactions that were clinically actionable; over one-third of patients were likely to benefit from changes in medications or drug doses based on the PGx results. The Indigenous American patients differed in the expression of drug-metabolizing enzymes and drug transporters from the White patients.

Background: We aimed to develop and validate an automated machine learning (autoML) prediction model for cardiac surgery-associated acute kidney injury (CSA-AKI). Methods: Using 69 preoperative variables, we developed several models to predict post-operative AKI in adult patients undergoing cardiac surgery. Models included autoML and non-autoML types, including decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), and artificial neural network (ANN), as well as a logistic regression prediction model. We then compared model performance using area under the receiver operating characteristic curve (AUROC) and assessed model calibration using Brier score on the independent testing dataset. Results: The incidence of CSA-AKI was 36%. Stacked ensemble autoML had the highest predictive performance among autoML models, and was chosen for comparison with other non-autoML and multivariable logistic regression models. The autoML had the highest AUROC (0.79), followed by RF (0.78), XGBoost (0.77), multivariable logistic regression (0.77), ANN (0.75), and DT (0.64). The autoML had comparable AUROC with RF and outperformed the other models. The autoML was well-calibrated. The Brier score for autoML, RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.18, 0.18, 0.21, 0.19, 0.19, and 0.18, respectively. We applied SHAP and LIME algorithms to our autoML prediction model to extract an explanation of the variables that drive patient-specific predictions of CSA-AKI. Conclusion: We were able to present a preoperative autoML prediction model for CSA-AKI that provided high predictive performance that was comparable to RF and superior to other ML and multivariable logistic regression models. The novel approaches of the proposed explainable preoperative autoML prediction model for CSA-AKI may guide clinicians in advancing individualized medicine plans for patients under cardiac surgery.

Background: The objectives of this study were to classify patients with serum magnesium derangement on hospital admission into clusters using unsupervised machine learning approach and to evaluate the mortality risks among these distinct clusters. Methods: Consensus cluster analysis was performed based on demographic information, principal diagnoses, comorbidities, and laboratory data in hypomagnesemia (serum magnesium ≤ 1.6 mg/dL) and hypermagnesemia cohorts (serum magnesium ≥ 2.4 mg/dL). Each cluster’s key features were determined using the standardized mean difference. The associations of the clusters with hospital mortality and one-year mortality were assessed. Results: In hypomagnesemia cohort (n = 13,320), consensus cluster analysis identified three clusters. Cluster 1 patients had the highest comorbidity burden and lowest serum magnesium. Cluster 2 patients had the youngest age, lowest comorbidity burden, and highest kidney function. Cluster 3 patients had the oldest age and lowest kidney function. Cluster 1 and cluster 3 were associated with higher hospital and one-year mortality compared to cluster 2. In hypermagnesemia cohort (n = 4671), the analysis identified two clusters. Compared to cluster 1, the key features of cluster 2 included older age, higher comorbidity burden, more hospital admissions primarily due to kidney disease, more acute kidney injury, and lower kidney function. Compared to cluster 1, cluster 2 was associated with higher hospital mortality and one-year mortality. Conclusion: Our cluster analysis identified clinically distinct phenotypes with differing mortality risks in hospitalized patients with dysmagnesemia. Future studies are required to assess the application of this ML consensus clustering approach to care for hospitalized patients with dysmagnesemia.

ABSTRACT Background Nephrolithiasis in allograft kidneys is rare, but this diagnosis may lead to allograft complications and patient morbidity. Previous studies that have evaluated nephrolithiasis posttransplant have focused on surgical stone management, with limited data on urine metabolic risk factors and the presence of stones after follow-up. Methods We retrospectively evaluated kidney transplant recipients who were diagnosed with transplant nephrolithiasis between 2009 and 2019. Computed tomography and ultrasound imaging were used to confirm stone presence. Results The incidence of allograft kidney stone formation was 0.86% of 6548 kidney transplant recipients. Of the 56 cases identified, 17 (30%) had a pretransplant history of nephrolithiasis. Only four (7%) patients received a known kidney stone at the time of allograft implantation. Of the 56 cases, 34 had a 24-h supersaturation study. The urine supersaturation study showed 32 patients (94%) had a urine citrate of <450 mg excreted in 24 h (median 124.5 mg/24 h, reference range >500 mg/24 h), along with 22 patients (61%) having a urine oxalate excretion of ≥30 mg in 24 h (median 34.4 mg/24 h, reference range <30 mg/24 h). Calcium oxalate composition was most common (91% with >1 supersaturation for calcium oxalate crystals), with normal median urine calcium levels (median urine calcium 103.5 mg/24 h, reference range <200 mg/24 h). After a 4-year follow-up, 50% (n = 28) required surgical intervention and 43 (77%) patients continued to have evidence of transplant nephrolithiasis on imaging. Conclusions This is the largest study of transplant nephrolithiasis confirming that hypocitraturia and hyperoxaluria were the most significant urine metabolic risk factors associated with allograft nephrolithiasis and that hyperoxaluria was the most prevalent driver for calcium oxalate stone composition. Our study is first to show low stone-free rates at the last follow-up and a significant proportion requiring surgical intervention.

ABSTRACT Background Hospitalized patients with hypokalemia are heterogeneous and cluster analysis, an unsupervised machine learning methodology, may discover more precise and specific homogeneous groups within this population of interest. Our study aimed to cluster patients with hypokalemia at hospital admission using an unsupervised machine learning approach and assess the mortality risk among these distinct clusters. Methods We performed consensus clustering analysis based on demographic information, principal diagnoses, comorbidities and laboratory data among 4763 hospitalized adult patients with admission serum potassium ≤3.5 mEq/L. We calculated the standardized mean difference of each variable and used the cutoff of ±0.3 to identify each cluster's key features. We assessed the association of the hypokalemia cluster with hospital and 1-year mortality. Results Consensus cluster analysis identified three distinct clusters that best represented patients’ baseline characteristics. Cluster 1 had 1150 (32%) patients, cluster 2 had 1344 (28%) patients and cluster 3 had 1909 (40%) patients. Based on the standardized difference, patients in cluster 1 were younger, had less comorbidity burden but higher estimated glomerular filtration rate (eGFR) and higher hemoglobin; patients in cluster 2 were older, more likely to be admitted for cardiovascular disease and had higher serum sodium and chloride levels but lower eGFR, serum bicarbonate, strong ion difference (SID) and hemoglobin, while patients in cluster 3 were older, had a greater comorbidity burden, higher serum bicarbonate and SID but lower serum sodium, chloride and eGFR. Compared with cluster 1, cluster 2 had both higher hospital and 1-year mortality, whereas cluster 3 had higher 1-year mortality but comparable hospital mortality. Conclusion Our study demonstrated the use of consensus clustering analysis in the heterogeneous cohort of hospitalized hypokalemic patients to characterize their patterns of baseline clinical and laboratory data into three clinically distinct clusters with different mortality risks.

Summary Background Hospitalized patients with hyperkalemia are heterogeneous, and cluster approaches may identify specific homogenous groups. This study aimed to cluster patients with hyperkalemia on admission using unsupervised machine learning (ML) consensus clustering approach, and to compare characteristics and outcomes among these distinct clusters. Methods Consensus cluster analysis was performed in 5133 hospitalized adult patients with admission hyperkalemia, based on available clinical and laboratory data. The standardized mean difference was used to identify each cluster’s key clinical features. The association of hyperkalemia clusters with hospital and 1-year mortality was assessed using logistic and Cox proportional hazard regression. Results Three distinct clusters of hyperkalemia patients were identified using consensus cluster analysis: 1661 (32%) in cluster 1, 2455 (48%) in cluster 2 and 1017 (20%) in cluster 3. Cluster 1 was mainly characterized by older age, higher serum chloride and acute kidney injury (AKI), but lower estimated glomerular filtration rate (eGFR), serum bicarbonate and hemoglobin. Cluster 2 was mainly characterized by higher eGFR, serum bicarbonate and hemoglobin, but lower comorbidity burden, serum potassium and AKI. Cluster 3 was mainly characterized by higher comorbidity burden, particularly diabetes and end-stage kidney disease, AKI, serum potassium, anion gap, but lower eGFR, serum sodium, chloride and bicarbonate. Hospital and 1-year mortality risk was significantly different among the three identified clusters, with highest mortality in cluster 3, followed by cluster 1 and then cluster 2. Conclusion In a heterogeneous cohort of hyperkalemia patients, three distinct clusters were identified using unsupervised ML. These three clusters had different clinical characteristics and outcomes.

Objective Native Americans suffer from lower rates of kidney transplantation compared with whites. Our goal was to elicit patients’ perceptions of and attitudes about kidney transplant and the impact of financial burden and cultural taboos. Design This is an exploratory qualitative interview study of 12 Native American patients recruited after completion of the kidney transplant evaluation. Setting Semistructured interviews were conducted. Interviews were coded using inductive methods, followed by interpretive coding by the investigators. Results Thematic analysis revealed the following themes: (1) experience with kidney transplant education by the healthcare team; (2) cultural beliefs regarding kidney transplant; (3) personal motivation and attitude towards kidney transplant; (4) financial burden of kidney transplant and post-transplant care and (5) attitude about living donation. Most participants were educated about transplant as a treatment option after dialysis initiation. All patients in this study recognised that some taboos exist about the process of organ procurement and transplantation; however, the traditional views did not negatively impact their decision to pursue kidney transplant evaluation. Patients shared the common theme of preferring an organ from a living rather than a deceased person; however, the majority did not have a living donor and preferred not to receive an organ from a family member. Most patients did not perceive transplant-related cost as negatively impacting their attitude about receiving a transplant even for patients with below poverty level income. Conclusions Native American patients presenting for kidney transplant were less likely to be educated about transplant before dialysis initiation; did not perceive financial burden and cultural beliefs were not discussed as obstacles to transplant. While a living donor was the preferred option, enthusiasm for living donation from family members was limited.