Search

Background: Recently, we developed the machine learning (ML)-based Progressive CKD Risk Classifier (PCRC), which accurately predicts CKD progression within 5 years. While its performance is robust, it is unknown whether PCRC categorization is associated with CKD-mineral bone disorder (CKD-MBD), a critical, yet under-recognized, downstream consequence. Therefore, we aimed to 1) survey real-world testing utilization data for CKD-MBD and 2) evaluate ML-based PCRC categorization with CKD-MBD., Methods: The cohort study utilized deidentified data from a US laboratory outpatient network, composed of 330,238 outpatients, over 5 years. The main outcomes were: 1) Laboratory testing utilization of eGFR, urine albumin creatinine ratio (UACR), parathyroid hormone (PTH), calcium, phosphate; and 2) PCRC categorization and biochemical abnormalities associated with CKD-MBD over 5 years., Results: We identified significant under-utilization of laboratory testing for UACR, phosphate and PTH, which ranged from -40 % to -100 % against the minimum standard-of-care. At five years, the CKD progression group, as predicted by the PCRC, was associated with 15.5 % increase in phosphate ( P value <<0.01) and 94.9 % increase in PTH (P value <<0.01), consistent with CKD-MBD., Conclusions: We identified significant under-utilization of laboratory testing for CKD-MBD. Moreover, we demonstrated that CKD progression, as predicted by the PCRC, is associated with CKD-MBD, several years in advance of disease. To our knowledge, this investigation is the first to examine the role of predictive analytics for CKD progression on mineral bone disorder. While further studies are required, these findings have the potential to advance AI/ML-based risk stratification and treatment of CKD and CKD-MBD., Competing Interests: The authors declare they have no conflicts of interest to disclose., (© 2024 Sonic Healthcare USA. Published by Elsevier Inc.)

Rationale & Objective: Chronic kidney disease (CKD) is a major cause of morbidity and mortality. To date, there are no widely used machine-learning models that can predict progressive CKD across the entire disease spectrum, including the earliest stages. The objective of this study was to use readily available demographic and laboratory data from Sonic Healthcare USA laboratories to train and test the performance of machine learning-based predictive risk models for CKD progression., Study Design: Retrospective observational study., Setting & Participants: The study population was composed of deidentified laboratory information services data procured from a large US outpatient laboratory network. The retrospective data set included 110,264 adult patients over a 5-year period with initial estimated glomerular filtration rate (eGFR) values between 15-89 mL/min/1.73 m 2 ., Predictors: Patient demographic and laboratory characteristics., Outcomes: Accelerated (ie, >30%) eGFR decline associated with CKD progression within 5 years., Analytical Approach: Machine-learning models were developed using random forest survival methods, with laboratory-based risk factors analyzed as potential predictors of significant eGFR decline., Results: The 7-variable risk classifier model accurately predicted an eGFR decline of >30% within 5 years and achieved an area under the curve receiver-operator characteristic of 0.85. The most important predictor of progressive decline in kidney function was the eGFR slope. Other key contributors to the model included initial eGFR, urine albumin-creatinine ratio, serum albumin (initial and slope), age, and sex., Limitations: The cohort study did not evaluate the role of clinical variables (eg, blood pressure) on the performance of the model., Conclusions: Our progressive CKD classifier accurately predicts significant eGFR decline in patients with early, mid, and advanced disease using readily obtainable laboratory data. Although prospective studies are warranted, our results support the clinical utility of the model to improve timely recognition and optimal management for patients at risk for CKD progression., Plain-Language Summary: Defined by a significant decrease in estimated glomerular filtration rate (eGFR), chronic kidney disease (CKD) progression is strongly associated with kidney failure. However, to date, there are no broadly used resources that can predict this clinically significant event. Using machine-learning techniques on a diverse US population, this cohort study aimed to address this deficiency and found that a 5-year risk prediction model for CKD progression was accurate. The most important predictor of progressive decline in kidney function was the eGFR slope, followed by the urine albumin-creatinine ratio and serum albumin slope. Although further study is warranted, the results showed that a machine-learning model using readily obtainable laboratory information accurately predicts CKD progression, which may inform clinical diagnosis and management for this at-risk population., (© 2023 The Authors.)

Diffuse large B-cell lymphoma (DLBCL) is a common morphologic term for a biologically diverse group of lymphomas. The chromosome translocation, t(14;18)(q32;q21), and its associated bcl-2 gene rearrangement are generally associated with follicular lymphomas. Some investigators, however, proposed that the presence of the t(14;18) in DLBCL suggests a possible follicle center cell origin and might correlate with a higher relapse rate after therapy. The CD10 antigen is expressed in a majority of follicular lymphomas but is also seen occasionally in DLBCLs. In this study, we examined 26 DLBCLs for CD10 expression by flow cytometric analysis and tested them for the t(14;18)(q32;q21) major breakpoint region by a polymerase chain reaction-based method. bcl-2 protein expression was analyzed by an immunoperoxidase method. Of the 26 DLBCLs, 9 (35%) were CD10 positive. bcl-2 protein was expressed in 7 (78%) of 9 CD10-positive cases and in 9 (53%) of 17 CD10-negative cases (P = .4). The t(14; 18) translocation was present in 6 (67%) of 9 CD10-positive cases but in only 2 (17%) of 12 CD10-negative cases (P = .03). Five cases did not yield amplifiable DNA for analysis. In summary, no difference in bcl-2 protein expression was seen in CD10-positive versus CD10-negative DLBCLs, but CD10-positive DLBCLs were significantly more likely than CD10-negative DLBCLs to harbor the t(14;18) translocation. This suggests that CD10 might be a marker of follicle center cell origin in DLBCL.

Inflammatory myofibroblastic tumors (IMTs) are uncommon spindle cell proliferations that occur in the viscera and soft tissue of children and young adults. Their biologic potential is indeterminate: 25% of IMTs recur, and rare examples undergo malignant transformation (MT). This study investigates histologic features, DNA ploidy, and expression of apoptotic regulatory and oncogenic proteins in IMTs in an attempt to identify those deviances that might correlate with aggressive behavior or MT. Twenty-four formalin-fixed, paraffin-embedded IMTs for which clinical outcome was known were evaluated for cellularity, cytologic atypia, mitoses, ganglion-like cells, inflammatory infiltrate, DNA ploidy by flow cytometric examination, and bax, bcl-2, p53, and c-myc expression by immunohistochemical analysis. Sixteen (67%) of the IMTs did not recur, 6 (25%) recurred, and 2 (8%) underwent MT. Cellular atypia was observed in 69% of the cases without recurrence, 100% with recurrence, and 100% with MT. Ganglion-like cells were present in 56, 100, and 100% of the IMTs without recurrence, with recurrence, and with MT, respectively. There was no difference in the degree of cellularity, mitoses, or inflammatory infiltrate among the outcome groups. All of the tumors expressed bax, and none expressed c-myc. Two (8%) were immunoreactive for p53, one of which recurred and one of which underwent MT. bcl-2 expression was observed in 9 (37%) of the IMTs, with no difference among the three groups. Two IMTs were aneuploid, one of which underwent MT. Neither morphologic evaluation for cellularity, mitosis, or inflammatory infiltrate nor expression of bax or c-myc were useful for prediction of clinical outcome. The combination of atypia, ganglion-like cells, p53 expression and DNA ploidy analysis, however, might be useful to identify IMTs that might undergo MT or pursue a more aggressive clinical course with recurrences.

Gonadoblastomas are rare tumors composed of both germ cells and sex-cord cells. In this study, we investigated two such tumors for the expression of the Wilms' tumor gene (WT1), which has a key role in urogenital development, and the expression of markers associated with sex-cord differentiation, i.e., Müllerian-inhibiting substance (MIS) and inhibin (I). We also studied p53 expression. Archival, paraffin-embedded tissue from two patients with gonadoblastoma, one bilateral and both with concurrent germinomatous areas, were evaluated immunohistochemically with antibodies directed against I, MIS, WT1, and p53. I was noted in the sex-cord component of the gonadoblastoma and not in germinoma cells. MIS was noted in both, although it was more strongly expressed in the sex-cord component. p53 expression was noted in the germ cells of the gonadoblastoma, as well as in the frankly germinomatous areas, whereas WT1 was found only in the sex-cord region and not at all in the germ cells of either of our two cases. These findings lead us to propose that WT1 and I are present in the initiation of gonadoblastomas, but are lost with the progression of these tumors. Similarly, MIS may be involved in its tumorigenesis. The expression of p53 seems to support the concept that gonadoblastoma represents in situ germ cell neoplasia with malignant potential. Additional studies, however, are needed to validate this concept.