Association of hypoglossal nerve stimulator response with machine learning identified negative effort dependence patterns.

BACKGROUND: Hypoglossal nerve stimulator (HGNS) is a therapeutic option for moderate to severe obstructive sleep apnea (OSA). Improved patient selection criteria are needed to target those most likely to benefit. We hypothesized that the pattern of negative effort dependence (NED) on inspiratory flow limited waveforms recorded during sleep, which has been correlated with the site of upper airway collapse, would contribute to the prediction of HGNS outcome. We developed a machine learning (ML) algorithm to identify NED patterns in pre-treatment sleep studies. We hypothesized that the predominant NED pattern would differ between HGNS responders and non-responders. METHODS: An ML algorithm to identify NED patterns on the inspiratory portion of the nasal pressure waveform was derived from 5 development set polysomnograms. The algorithm was applied to pre-treatment sleep studies of subjects who underwent HGNS implantation to determine the percentage of each NED pattern. HGNS response was defined by STAR trial criteria for success (apnea-hypopnea index (AHI) reduced by > 50% and < 20/h) as well as by a change in AHI and oxygenation metrics. The predominant NED pattern in HGNS responders and non-responders was determined. Other variables including demographics and oxygenation metrics were also assessed between responders and non-responders. RESULTS: Of 45 subjects, 4 were excluded due to technically inadequate polysomnograms. In the remaining 41 subjects, ML accurately distinguished three NED patterns (minimal, non-discontinuous, and discontinuous). The percentage of NED minimal breaths was significantly greater in responders compared with non-responders (p = 0.01) when the response was defined based on STAR trial criteria, change in AHI, and oxygenation metrics. CONCLUSION: ML can accurately identify NED patterns in pre-treatment sleep studies. There was a statistically significant difference in the predominant NED pattern between HGNS responders and non-responders with a greater NED minimal pattern in responders. Prospective studies incorporating NED patterns into predictive modeling of factors determining HGNS outcomes are needed.

Optimization of Hypoglossal Nerve Stimulation for Obstructive Sleep Apnea With Ultrasound Assessment of Tongue Movement.

BACKGROUND: Hypoglossal nerve stimulation (HGNS) is an Food and Drug Administration-approved therapy for obstructive sleep apnea. Initial programming of HGNS is based on the observation of anterior tongue movement, which may not reflect opening at the retroglossal airway. We developed an ultrasonographic technique to assess the base of tongue movement with HGNS to be used to optimize the initial voltage settings. STUDY QUESTION: This study aimed to investigate the use of ultrasound to assess tongue movement with HGNS and related this measure to the apnea hypopnea index (AHI) on subsequent home sleep apnea testing or in-laboratory polysomnography with therapy. STUDY DESIGN: Seventeen subjects (n = 17) implanted with HGNS were enrolled at least 1 month postimplantation. Ultrasonographic measures were then used to optimize HGNS voltage to produce observable base of tongue protrusion without producing discomfort. Responders were defined as a reduction in AHI > 50% and an AHI of <20 events/h. RESULTS: There were 17 subjects, 11 men and 6 women, with age = 64.6 ± 9.8 years, body mass index = 27.9 ± 2.7 kg/m2, and pretreatment AHI = 36.5 ± 14.4/h, T-90% = 10.7 ± 14.8%. The mean hyoid bone excursion (HBE) in responders = 1.0 ± 0.13 cm versus 0.82 ± 0.12 cm in nonresponders (P = 0.017). HBE was correlated with AHI during HGNS treatment (coef. -0.54, P = 0.03). Best subsets regression analysis using treatment-based AHI as the dependent variable and age, body mass index, baseline AHI, HBE, and HGNS voltage as independent variables showed that HBE (coef. -44.6, P = 0.044) was the only independent predictor of response. Receiver operator curve analysis showed that HBE > 0.85 cm had a sensitivity of 83.3% and specificity of 80.0% with a positive likelihood ratio of 4.17 to predict responder status. CONCLUSION: We demonstrated that ultrasound assessment of HBE during HGNS programming is a useful tool to optimize therapy.

Space invader: pleural penetration of a hypoglossal nerve stimulator sensor lead.

The mainstay of treatment for obstructive sleep apnea is positive airway pressure therapy, which may be difficult for some patients to tolerate leading to compromised adherence and requiring alternative therapies. Hypoglossal nerve stimulation has become an option for those who meet implantation criteria. Implantation of the device is an ambulatory surgical procedure and is generally well-tolerated, though rare adverse events have been reported. We report an unusual complication of hypoglossal nerve stimulation in a patient who had initial success with this therapy. After 3 years of treatment, the sensor lead penetrated into the pleural space. Components of the hypoglossal nerve stimulation were explanted, and a new sensor lead and generator were reimplanted. The new device was activated, and therapy was successfully resumed. This case demonstrates that there is a potential for a delayed complication of sensor lead penetration into the pleural space, which has only rarely been reported. CITATION: Lou B, Hahn S, Korotun M, Quintero L, Shikowitz M, Greenberg H. Space invader: pleural penetration of a hypoglossal nerve stimulator sensor lead. J Clin Sleep Med. 2021;17(11):2329-2332.