Falsely Elevated Postvoid Residual Urine Volume in Uterine Myoma

Portable Ultrasound Bladder Volume Measurement Over Entire Volume Range Using a Deep Learning Artificial Intelligence Model in a Selected Cohort: A Proof of Principle Study

OBJECTIVE

We aimed to prospectively investigate whether bladder volume measured using deep learning artificial intelligence (AI) algorithms (AI-BV) is more accurate than that measured using conventional methods (C-BV) if using a portable ultrasound bladder scanner (PUBS).

PATIENTS AND METHODS

Patients who underwent filling cystometry because of lower urinary tract symptoms between January 2021 and July 2022 were enrolled. Every time the bladder was filled serially with normal saline from 0 mL to maximum cystometric capacity in 50 mL increments, C-BV was measured using PUBS. Ultrasound images obtained during this process were manually annotated to define the bladder contour, which was used to build a deep learning AI model. The true bladder volume (T-BV) for each bladder volume range was compared with C-BV and AI-BV for analysis.

RESULTS

We enrolled 250 patients (213 men and 37 women), and a deep learning AI model was established using 1912 bladder images. There was a significant difference between C-BV (205.5 ± 170.8 mL) and T-BV (190.5 ± 165.7 mL) (p = 0.001), but no significant difference between AI-BV (197.0 ± 161.1 mL) and T-BV (190.5 ± 165.7 mL) (p = 0.081). In bladder volume ranges of 101-150, 151-200, and 201-300 mL, there were significant differences in the percentage of volume differences between [C-BV and T-BV] and [AI-BV and T-BV] (p < 0.05), but no significant difference if converted to absolute values (p > 0.05). C-BV (R2 = 0.91, p < 0.001) and AI-BV (R2 = 0.90, p < 0.001) were highly correlated with T-BV. The mean difference between AI-BV and T-BV (6.5 ± 50.4) was significantly smaller than that between C-BV and T-BV (15.0 ± 50.9) (p = 0.001).

CONCLUSION

Following image pre-processing, deep learning AI-BV more accurately estimated true BV than conventional methods in this selected cohort on internal validation. Determination of the clinical relevance of these findings and performance in external cohorts requires further study.

TRIAL REGISTRATION

The clinical trial was conducted using an approved product for its approved indication, so approval from the Ministry of Food and Drug Safety (MFDS) was not required. Therefore, there is no clinical trial registration number.

Prediction of early bladder outcomes after spinal cord injury: The HALT score

AIMS

Neurogenic bladder (NB) is a prevalent and debilitating consequence of spinal cord injury (SCI). Indeed, the accurate prognostication of early bladder outcomes is crucial for patient counseling, rehabilitation goal setting, and personalized intervention planning.

METHODS

A retrospective exploratory analysis was conducted on a cohort of consecutive SCI patients admitted to a rehabilitation facility in China from May 2016 to December 2022. Demographic, clinical, and electrophysiological data were collected within 40 days post-SCI, with bladder outcomes assessed at 3 months following SCI onset.

RESULTS

The present study enrolled 202 SCI patients with a mean age of 40.3 ± 12.3 years. At 3 months post-SCI, 79 participants exhibited complete bladder emptying. Least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression analyses identified the H-reflex of the soleus muscle, the American Spinal Injury Association Lower Extremity Motor Score (ASIA-LEMS), and the time from lesion to rehabilitation facility (TLRF) as significant independent predictors for bladder emptying. A scoring system named HALT was developed, yielding a strong discriminatory performance with an area under the receiver operating characteristics curve (aROC) of 0.878 (95% CI: 0.823-0.933). A simplified model utilizing only the H-reflex exhibited excellent discriminatory ability with an aROC of 0.824 (95% CI: 0.766-0.881). Both models demonstrated good calibration via the Hosmer-Lemeshow test and favorable clinical net benefits through decision curve analysis (DCA). In comparison to ASIA-LEMS, both the HALT score and H-reflex showed superior predictive accuracy for bladder outcome. Notably, in individuals with incomplete injuries, the HALT score (aROC = 0.973, 95% CI: 0.940-1.000) and the H-reflex (aROC = 0.888, 95% CI: 0.807-0.970) displayed enhanced performance.

CONCLUSION

Two reliable models, the HALT score and the H-reflex, were developed to predict bladder outcomes as early as 3 months after SCI onset. Importantly, this study provides hitherto undocumented evidence regarding the predictive significance of the soleus H-reflex in relation to bladder outcomes in SCI patients.

A 66-Year-Old Woman with Achondroplasia and Quadriparesis with an Ovarian Cyst Erroneously Diagnosed as Urinary Retention by an Automated Bladder Scan

BACKGROUND Automated bladder scanning has become a principal tool in the assessment and management of chronically debilitated patients residing in skilled nursing facilities, hospices, and acute inpatient settings. To a large extent, the bladder scan, generally performed by nursing staff, has replaced physical examination while addressing the differential diagnoses of anuria or voiding disturbances that require consideration of urinary catheterization. Health care providers can quickly master this easily performed technique, and currently, due to confidence in the bladder scan finding, physical examination with suprapubic palpation and percussion may be carelessly omitted. The case description presented here illustrates how not performing a physical examination can lead to misdiagnosis caused by misinterpretation of bladder scan findings. CASE REPORT A 66-year-old, quadriparetic, chronically ventilated female patient with achondroplasia underwent repeated hospital referrals and bladder catheterizations for presumed flaccid, neurogenic bladder with urinary retention. This postulated diagnosis was based on occasional reports of urinary catheter obstruction as well as on automated bladder scanning indicating a markedly distended bladder. However, the bladder could not be drained by insertion of urinary catheters. Eventually, a proper physical examination excluded the presence of suprapubic fullness compatible with distended bladder and contradicting bladder scan findings, prompting re-examining an overlooked evaluation of computed tomography that reported a huge ovarian cyst. The patient was found to have intact voiding capabilities and is now weaned from the catheter. CONCLUSIONS This case and the literature review underscore drawbacks in automated bladder scanning. This technique should be used as an adjunctive measure rather than a replacement for a physical examination in the evaluation of voiding disturbances, especially when there are discrepancies between bladder scan findings and the volume of urine drained by catheterization.

False Elevation of Volume Determined by Bladder Scanner Secondary to Bowel Obstruction

Bladder scanners allow for quick determination of bladder volumes (BV) with minimal training. BV measured by a machine is generally accurate; however, circumstances exist in which falsely elevated BVs are reported. This case details a patient with a significant small bowel obstruction (SBO) due to superior mesenteric artery syndrome causing a falsely elevated BV. We believe this is the first case report of a SBO causing an elevated BV by bladder scanner. Emergency physicians should be aware of the pitfalls of using bladder scanners, and use their point-of-care ultrasound skills when possible to expand their differential.