Machine Learning Prediction of Objective Hearing Loss With Demographics, Clinical Factors, and Subjective Hearing Status.

OBJECTIVE: Hearing loss (HL) is highly prevalent, yet underrecognized and underdiagnosed. Lack of standardized screening, awareness, cost, and access to hearing testing present barriers to HL identification. To facilitate prescreening and selection of patients who warrant audiometric evaluation, we developed a machine learning (ML) model to predict speech-frequency pure-tone average (PTA). STUDY DESIGN: Cross-sectional study. SETTING: National Health and Nutrition Examination Survey (NHANES). METHODS: The cohort included 8918 adults (≥20 years) who completed audiometric testing with NHANES (2012-2018). The primary outcome measure was the prediction of better hearing ear speech-frequency PTA. Relevant predictors included demographics, medical conditions, and subjective assessment of hearing. Supervised ML with a tree-based architecture was used. Regression performance was determined by the mean absolute error (MAE) with binary classification assessed with area under the receiver operating characteristic curve (AUC). RESULTS: Using the full set of predictors, the test set MAE between the ML-predicted and actual PTA was 5.29 dB HL (95% confidence interval [CI]: 4.97-5.61). The 5 most influential predictors of higher PTA were increased age, worse subjective hearing, male gender, increased body mass index, and history of smoking. The 5-factor abbreviated model performed comparably to the extended feature set with MAE 5.36 (95% CI: 5.03-5.69) and AUC for PTA > 25 dB HL of 0.92 (95% CI: 0.90-0.94). CONCLUSION: The ML model was able to predict PTA with patient demographics, clinical factors, and subjective hearing status. ML-based prediction may be used to identify individuals who could benefit most from audiometric evaluation.

Objective Quantification of Detrusor Overactivity Using Spectral Measures of Cystometry Data.

OBJECTIVE: To develop scalable objective methods for differentiating patients with and without detrusor overactivity (DO) using quantitative Fast Fourier Transform (FFT)-based measures and routinely captured cystometry data. METHODS: Retrospective cystometry data were collected as prevoid vesical and abdominal pressure signals from 18 DO and 10 SUI (non-DO) cystometry recordings. Data were filtered and divided into two equal-duration segments, Early and Late Fill, representing the first and second halves of filling. FFT was applied, followed by subtraction of abdominal spectra from vesical spectra. Spectral Power (SP) and Weighted Average Frequency (WAF) measures were calculated for each segment spectra within 1-6 cycles min-1. RESULTS: Compared to non-DO, the mean SP was significantly higher in DO patients for both Early and Late Fill segments. WAF was significantly lower in DO patients for both segments. Changes in spectral pressures appeared to be linked to the presence of detrusor contractions (DCs) and were especially visible when DCs were present in the Early Fill segments of cystometry. CONCLUSION: FFT-based spectral measures derived from routinely captured cystometry data are significantly different between DO and non-DO patients. This preliminary method is clinically scalable and can be further developed to facilitate the detection of DO, classify disease phenotype, and capture therapeutic efficacy.

Joint engineering-medical school programs prepare physicians for clinical challenges: An observational study.

Background and Aims: Modern health care faces a plethora of challenges including the delivery of quality and cost-efficient care. Physicians are first-hand observers of clinical problems but may lack the requisite training and education to develop innovations that improve patient care. Few medical education programs address innovation, leadership, and transdisciplinary collaboration despite being highlighted by national medical and education organizations including the American Medical Association. The University of Minnesota has implemented the Augustine program over the last 10-years to produce physicians that are leaders in medical innovation. Methods: As a novel joint engineering-medical school curriculum to educate medical students, residents, and fellows, the Augustine program incorporates engineering coursework, biomedical research, and a multidisciplinary design and business development experience to produce physicians capable of designing and marketing "disruptive technologies." The Augustine program takes 1-year to complete in addition to the 4-year medical education and provides a Master of Biomedical Engineering upon completion. Results: Augustine program graduates (n = 6) have reported significant contributions related to the joint engineering-medical education including peer-reviewed publications (Median: 13), deployable assets (Median: 2), and intellectual property (Median: 1). Most surveyed graduates (n = 5, 83%) continue to be active contributors to medical innovation and all (n = 6, 100%) utilize their transdisciplinary education to improve patient care. Conclusion: Augustine program graduates impact the entire spectrum of innovation and continue to improve patient care. The program will seek to emphasize the inclusion of physician residents and fellows with position expansion. The addition of a multi-week medical innovation clerkship will provide a more focused experience for students unable to dedicate an entire year to a transdisciplinary experience.

Measurement and Quantification of Cystometric Bladder Pressure Spectra in an in-vivo Sheep Model: A Feasibility Study.

Cystometry is a standard procedure for the clinical evaluation of lower urinary tract disorders such as detrusor overactivity (DO). The utility of this procedure for DO diagnosis, however, is limited by the use of physician observations of bladder contractions and patient reported filling sensations. Although a number of preclinical and clinical studies have observed and developed methods to characterize bladder pressure dynamics, these techniques have not been scaled for routine clinical application. The goal of this study was to evaluate the feasibility of using an awake large animal model to characterize bladder pressure signals from cystometry as bladder pressure spectra and quantify changes in spectra during bladder filling. Two adult female sheep were trained for quiet catheterization in a minimally supportive sling and underwent multiple awake and limited anesthetized cystometry tests. In each test, bladder pressure was measured during continuous filling or with filling that included periods of no filling (constant volume). A Fast-Fourier Transform (FFT)-based algorithm was then used to quantify changes in pre-voiding bladder pressure spectra. Changes in Spectral Power (SP) and Weighted Average Frequency (WAF) were calculated during filling. To visualize temporal changes in bladder pressure frequencies during filling, Continuous Wavelet Transform (CWT) was also applied to cystometry data. Results showed that a significant increase in SP and decrease in WAF were both associated with bladder filling. However, during awake constant volume tests, SP significantly increased while changes in WAF were nonsignificant. Anesthetized tests demonstrated comparable values to awake tests for WAF while SP was considerably reduced. CWT facilitated visualization of spectral changes associated with SP and WAF as well as apparent non-voiding contractions during awake and anesthetized volume tests.Clinical Relevance-Bladder pressure spectra during cystometry are detectable in sheep and the changes during filling are similar to those observed in human retrospective clinical data. Sheep cystometry may be a valuable testbed for establishing and testing quantitative pressure spectra for use as a clinical diagnostic tool.

Adenosine A2a receptors modulate TrkB receptor-dependent respiratory plasticity in neonatal rats.

Neuroplasticity is a fundamental property of the respiratory control system, enabling critical adaptations in breathing to meet the challenges, but little is known whether neonates express neuroplasticity similar to adults. We tested the hypothesis that, similar to adults, tyrosine receptor kinase B (TrkB) or adenosine A2a receptor activation in neonates are independently sufficient to elicit respiratory motor facilitation, and that co-induction of TrkB and A2a receptor-dependent plasticity undermines respiratory motor facilitation. TrkB receptor activation with 7,8-dihydroxyflavone (DHF) in neonatal brainstem-spinal cord preparations induced a long-lasting increase in respiratory motor output in 55 % of preparations, whereas adenosine A2a receptor activation with CGS21680 only sporadically induced respiratory motor plasticity. CGS21680 and DHF co-application prevented DHF-dependent respiratory motor facilitation, whereas co-application of MSX-3 (adenosine A2a receptor antagonist) and DHF more rapidly induced respiratory motor plasticity. Collectively, these data suggest that mechanisms underlying respiratory neuroplasticity may be only partially operational in early neonatal life, and that adenosine A2a receptor activation undermines TrkB-induced respiratory plasticity.