Hearing recovery prediction and prognostic factors of idiopathic sudden sensorineural hearing loss: a retrospective analysis with a deep neural network model

Artificial intelligence in maxillofacial and facial plastic and reconstructive surgery

PURPOSE OF REVIEW

To provide a current review of artificial intelligence and its subtypes in maxillofacial and facial plastic surgery including a discussion of implications and ethical concerns.

RECENT FINDINGS

Artificial intelligence has gained popularity in recent years due to technological advancements. The current literature has begun to explore the use of artificial intelligence in various medical fields, but there is limited contribution to maxillofacial and facial plastic surgery due to the wide variance in anatomical facial features as well as subjective influences. In this review article, we found artificial intelligence's roles, so far, are to automatically update patient records, produce 3D models for preoperative planning, perform cephalometric analyses, and provide diagnostic evaluation of oropharyngeal malignancies.

SUMMARY

Artificial intelligence has solidified a role in maxillofacial and facial plastic surgery within the past few years. As high-quality databases expand with more patients, the role for artificial intelligence to assist in more complicated and unique cases becomes apparent. Despite its potential, ethical questions have been raised that should be noted as artificial intelligence continues to thrive. These questions include concerns such as compromise of the physician-patient relationship and healthcare justice.

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.

Three-dimensional heavily T2-weighted FLAIR in the detection of blood-labyrinthine barrier leakage in patients with sudden sensorineural hearing loss: comparison with T1 sequences and application of deep learning-based reconstruction

OBJECTIVE

Blood-labyrinthine barrier leakage has been reported in sudden sensorineural hearing loss (SSNHL). We compared immediate post-contrast 3D heavily T2-weighted fluid-attenuated inversion recovery (FLAIR), T1 spin echo (SE), and 3D T1 gradient echo (GRE) sequences, and heavily T2-weighted FLAIR (hvT2F) with and without deep learning-based reconstruction (DLR) in detecting perilymphatic enhancement.

METHODS

Fifty-four patients with unilateral SSNHL who underwent ear MRI with three sequences were included. We compared asymmetry scores, confidence scores, and detection rates of perilymphatic enhancement among the three sequences and obtained 3D hvT2F with DLR from 35 patients. The above parameters and subjective image quality between 3D hvT2F with and without DLR were compared.

RESULTS

Asymmetry scores and detection rate of 3D hvT2F were significantly higher than 3D GRE T1 and SE T1 (respectively, 1.37, 0.11, 0.19; p < 0.001). Asymmetry scores significantly increased with DLR compared to 3D hvT2F for experienced and inexperienced readers (respectively, 1.77 vs. 1.40, p = 0.036; 1.49 vs. 1.03, p = 0.012). The detection rate significantly increased only for the latter (57.1% vs. 31.4%, p = 0.022). Patients with perilymphatic enhancement had significantly higher air conduction thresholds on initial (77.96 vs. 57.79, p = 0.002) and 5 days after presentation (63.38 vs. 41.85, p = 0.019).

CONCLUSION

3D hvT2F significantly increased the detectability of perilymphatic enhancement compared to 3D GRE T1 and SE T1. DLR further improved the conspicuity of perilymphatic enhancement in 3D hvT2F. 3D hvT2F and DLR are useful for evaluating blood-labyrinthine barrier leakage; furthermore, they might provide prognostic value in the early post-treatment period.

CLINICAL RELEVANCE STATEMENT

Ten-minute post-contrast 3D heavily T2-weighed FLAIR imaging is a potentially efficacious sequence in demonstrating perilymphatic enhancement in patients with sudden sensorineural hearing loss and may be further improved by deep learning-based reconstruction.

KEY POINTS

• 3D heavily T2-weighted FLAIR (3D hvT2F) is a sequence sensitive in detecting low concentrations of contrast in the perilymphatic space. • 3D hvT2F sequences properly demonstrated perilymphatic enhancement in sudden sensorineural hearing loss compared to T1 sequences and were further improved by deep learning-based reconstruction (DLR). • 3D hvT2F and DLR are efficacious sequences in detecting blood-labyrinthine barrier leakage and with potential prognostic information.