Correlation between blood urea nitrogen level and cochlear outer hair cell function in non-dialysis chronic kidney disease patients

Predicting Sudden Sensorineural Hearing Loss Recovery with Patient-Personalized Seigel's Criteria Using Machine Learning

BACKGROUND

Accurate prognostic prediction is crucial for managing Idiopathic Sudden Sensorineural Hearing Loss (ISSHL). Previous studies developing ISSHL prognosis models often overlooked individual variability in hearing damage by relying on fixed frequency domains. This study aims to develop models predicting ISSHL prognosis one month after treatment, focusing on patient-specific hearing impairments.

METHODS

Patient-Personalized Seigel's Criteria (PPSC) were developed considering patient-specific hearing impairment related to ISSHL criteria. We performed a statistical test to assess the shift in the recovery assessment when applying PPSC. The utilized dataset of 581 patients comprised demographic information, health records, laboratory testing, onset and treatment, and hearing levels. To reduce the model's reliance on hearing level features, we used only the averages of hearing levels of the impaired frequencies. Then, model development, evaluation, and interpretation proceeded.

RESULTS

The chi-square test (p-value: 0.106) indicated that the shift in recovery assessment is not statistically significant. The soft-voting ensemble model was most effective, achieving an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.864 (95% CI: 0.801-0.927), with model interpretation based on the SHapley Additive exPlanations value.

CONCLUSIONS

With PPSC, providing a hearing assessment comparable to traditional Seigel's criteria, the developed models successfully predicted ISSHL recovery one month post-treatment by considering patient-specific impairments.

Changes of FGF23 and hearing in chronic renal failure and their correlation analysis

BACKGROUND

To explore the association between fibroblast growth factor 23 (FGF23) and hearing in chronic renal failure (CRF).

METHODS

Pure tone audiometry was used to detect the hearing of patients with CRF; the level of serum FGF23, creatinine, blood urea nitrogen (BUN), parathyroid hormone (PTH), and mean binaural hearing threshold were compared to the control group (people without kidney disease). The rat model of renal failure was established by 5/6 nephrectomy, and the auditory brainstem response (ABR) of rats after modeling was detected by the Tucker Davis Technologies (TDT) system; the expression level of FGF23 in the peripheral blood, renal and cochlear tissue was also detected.

RESULTS

The incidence of hearing loss (HL) and serum FGF23 were higher in CRF patients than the control group; the sFGF23 was positively correlated with the mean binaural hearing threshold. Animal studies showed that the ABR threshold, creatinine, FGF23, BUN, and PTH increased after modeling; although, an increase in FGF23 was observed earlier than other indicators. The HL of rats with renal failure was significantly correlated with BUN, phosphate, PTH, sFGF23, kFGF23/β-actin, eFGF23/β-actin, weight, and modeling cycle.

CONCLUSIONS

Both CRF patients and rat models showed high-frequency HL. FGF23 was highly expressed in the serum of HL renal failure patients and rats, as well as in the renal tissue and cochlea of renal failure rats. Therefore, FGF23 may be involved in the occurrence and development of HL caused by CRF.