Multiportal Retrograde Endoscopy to Enhance Surgical Target Visualization: A Pilot Study.

Objective Current transnasal endoscopic techniques for sinus and skull base surgery use a single endoscope to provide visualization from one perspective curtailing depth perception and compromising visualization of the instrument-target interface. The view can be blocked by instruments, and collisions between instruments often occur. The objective of this study was to investigate the use of multiportal retrograde endoscopy to provide more accurate manipulation of the surgical target. Design Maxillary antrostomy and frontal sinusotomy were performed on three different cadavers by three different surgeons. A zero-degree rigid endoscope was introduced through the nose for the standard transnasal approach. A flexible endoscope was introduced transorally, directed past the palate superiorly, and then flexed 180 degrees for the retrograde view. Videos of the standard transnasal view from the rigid endoscope and retrograde view from the flexible endoscope were recorded simultaneously. Results All surgeries were able to be performed with dual-screen viewing of the standard and retrograde view. The surgeons noted that they utilized the retrograde view to adjust the location of ends/tips of their instruments. Four surgeons reviewed the videos and individually agreed that the visualization achieved provided a perspective otherwise not attainable with rigid transnasal endoscopy alone. Conclusion High-quality visualization of surgical targets such as the frontal or maxillary ostia can be challenging with rigid endoscopes alone. Multiportal retrograde endoscopy provides proof of concept that additional views of a surgical target can be achieved. Additional work is needed to further develop indications, techniques, and generalizability to targets beyond those investigated here.

Reducing annotating load: Active learning with synthetic images in surgical instrument segmentation.

Accurate instrument segmentation in the endoscopic vision of minimally invasive surgery is challenging due to complex instruments and environments. Deep learning techniques have shown competitive performance in recent years. However, deep learning usually requires a large amount of labeled data to achieve accurate prediction, which poses a significant workload. To alleviate this workload, we propose an active learning-based framework to generate synthetic images for efficient neural network training. In each active learning iteration, a small number of informative unlabeled images are first queried by active learning and manually labeled. Next, synthetic images are generated based on these selected images. The instruments and backgrounds are cropped out and randomly combined with blending and fusion near the boundary. The proposed method leverages the advantage of both active learning and synthetic images. The effectiveness of the proposed method is validated on two sinus surgery datasets and one intraabdominal surgery dataset. The results indicate a considerable performance improvement, especially when the size of the annotated dataset is small. All the code is open-sourced at: https://github.com/HaonanPeng/active_syn_generator.

Head and Neck Vascular Anomalies in Children.

Craniomaxillofacial vascular anomalies encompass a diverse and complex set of pathologies that may have a profound impact on pediatric patients. They are subdivided into vascular tumors and vascular malformations depending on biological properties, clinical course, and distribution patterns. Given the complexity and potential for leading to significant functional morbidity and esthetic concerns, a multidisciplinary approach is generally necessary to optimize patient outcomes. This article reviews the etiology, clinical course, diagnosis, and current management practices related to vascular anomalies in the head and neck.

Multidisciplinary Advanced Surgical Planning for Slide Tracheoplasty Using 3D-Printed Models.

OBJECTIVE: The objective of this study was to develop and assess multidisciplinary advanced surgical planning (ASP) sessions using three dimensional (3D) printed models for cervicothoracic slide tracheoplasty (CST). We hypothesized that these sessions would improve surgeon confidence, streamline intraoperative planning, and highlight the utility of 3D modeling. METHODS: 3D-printed patient-specific trachea models were used in pre-operative ASP sessions consisting of a multidisciplinary case discussion and hands-on slide tracheoplasty simulation. Participants completed a survey rating realism, utility, impact on the final surgical plan, and pre- and post-session confidence. Statistical analysis was performed via Wilcoxon and Kruskal-Wallis tests. RESULTS: Forty-eight surveys were collected across nine sessions and 27 different physicians. On a 5-point Likert scale, models were rated as "very realistic", "very useful" (both median of 4, IQR 3-4 and 4-5, respectively). Overall confidence increased by 1.4 points (+/- 0.7, p < 0.0001), with the largest change seen in those with minimal prior slide tracheoplasty experience (p = 0.005). Participants felt that the sessions "strongly" impacted their surgical plan or anticipated performance (median 4, IQR 4-5), regardless of training level or experience. CONCLUSION: 3D-printed patient-specific models were successfully implemented in ASP sessions for CST. Models were deemed very realistic and very useful by surgeons across multiple specialties and training levels. Surgical planning sessions also strongly impacted the final surgical plan and increased surgeon confidence for CST. LEVEL OF EVIDENCE: 4 Laryngoscope, 134:3395-3401, 2024.

Surface Reconstruction of the Pediatric Larynx via Structure from Motion Photogrammetry: A Pilot Study.

Endoscopy is the gold standard for characterizing pediatric airway disorders, however, it is limited for quantitative analysis due to lack of three-dimensional (3D) vision and poor stereotactic depth perception. We utilize structure from motion (SfM) photogrammetry, to reconstruct 3D surfaces of pathologic and healthy pediatric larynges from monocular two-dimensional (2D) endoscopy. Models of pediatric subglottic stenosis were 3D printed and airway endoscopies were simulated. 3D surfaces were successfully reconstructed from endoscopic videos of all models using an SfM analysis toolkit. Average subglottic surface error between SfM reconstructed surfaces and 3D printed models was 0.65 mm as measured by Modified Hausdorff Distance. Average volumetric similarity between SfM surfaces and printed models was 0.82 as measured by Jaccard Index. SfM can be used to accurately reconstruct 3D surface renderings of the larynx from 2D endoscopy video. This technique has immense potential for use in quantitative analysis of airway geometry and virtual surgical planning.

Preoperative Imaging and Surgical Findings in Pediatric Frontonasal Dermoids.

OBJECTIVE: To review cases of congenital frontonasal dermoids to gain insight into the accuracy of preoperative computed tomography (CT) and magnetic resonance imaging (MRI) in predicting intracranial extension. METHODS: This retrospective study included all patients who underwent primary excision of frontonasal dermoids at an academic children's hospital over a 23-year period. Preoperative presentation, imaging, and operative findings were reviewed. Receiver operating characteristic (ROC) statistics were generated to determine CT and MRI accuracy in detecting intracranial extension. RESULTS: Search queries yielded 129 patients who underwent surgical removal of frontonasal dermoids over the study period with an average age of presentation of 12 months. Preoperative imaging was performed on 122 patients, with 19 patients receiving both CT and MRI. CT and MRI were concordant in the prediction of intracranial extension in 18 out of 19 patients. Intraoperatively, intracranial extension requiring craniotomy was seen in 11 patients (8.5%). CT was 87.5% sensitive and 97.4% specific for predicting intracranial extension with an ROC of 0.925 (95% CI [0.801, 1]), whereas MRI was 60.0% sensitive and 97.8% specific with an ROC of 0.789 (95% CI [0.627, 0.950]). CONCLUSION: This is the largest case series in the literature describing a single institution's experience with frontonasal dermoids. Intracranial extension is rare and few patients required craniotomy in our series. CT and MRI have comparable accuracy at detecting intracranial extension. Single-modality imaging is recommended preoperatively in the absence of other clinical indications. LEVEL OF EVIDENCE: 4 Laryngoscope, 134:1961-1966, 2024.

Surgery for Velopharyngeal Insufficiency Following Cleft Palate Repair: An Audit of Contemporary Practice and Proposed Schema of Techniques and Variations.

OBJECTIVE: Surgical treatment of velopharyngeal insufficiency (VPI) includes a wide array of procedures. The purpose of this study was to develop a classification for VPI procedures and to describe variations in how they are performed.Design/participants/setting/outcomes: We completed an in-depth review of the literature to develop a preliminary schema that encompassed existing VPI procedures. Forty-one cleft surgeons from twelve hospitals across the USA and Canada reviewed the schema and either confirmed that it encompassed all VPI procedures they performed or requested additions. Two surgeons then observed the conduct of the procedures by surgeons at each hospital. Standardized reports were completed with each visit to further explore the literature, refine the schema, and delineate the common and unique aspects of each surgeon's technique. RESULTS: Procedures were divided into three groups: palate-based surgery; pharynx-based surgery; and augmentation. Palate-based operations included straight line mucosal incision with intravelar veloplasty, double-opposing Z-plasty, and palate lengthening with buccal myomucosal flaps. Many surgeons blended maneuvers from these three techniques, so a more descriptive schema was developed classifying the maneuvers employed on the oral mucosa, nasal mucosa, and muscle. Pharynx-based surgery included pharyngeal flap and sphincter pharyngoplasty, with variations in design for each. Augmentation procedures included palate and posterior wall augmentation. CONCLUSIONS: A comprehensive schema for VPI procedures was developed incorporating intentional adaptations in technique. There was substantial variation amongst surgeons in how each procedure was performed. The schema may enable more specific evaluations of surgical outcomes and exploration of the mechanisms through which these procedures improve speech.

Pediatric Nasal and Septal Fractures.

Pediatric nasal bone and septal fractures represent a large number of craniofacial injuries in children each year. Due to their differences in anatomy and potential for growth and development, the management of these injuries varies slightly from that of the adult population. As with most pediatric fractures, there is a bias toward less-invasive management to limit disruption to future growth. Often this includes closed reduction and splinting in the acute setting followed by open septorhinoplasty at skeletal maturity as needed. The overall goal of treatment is to restore the nose to its preinjury shape, structure, and function.

Automatic summarization of endoscopic skull base surgical videos through object detection and hidden Markov modeling.

Endoscopic endonasal surgery is a medical procedure that utilizes an endoscopic video camera to view and manipulate a surgical site accessed through the nose. Despite these surgeries being video recorded, these videos are seldom reviewed or even saved in patient files due to the size and length of the video file. Editing to a manageable size may necessitate viewing 3 h or more of surgical video and manually splicing together the desired segments. We suggest a novel multi-stage video summarization procedure utilizing deep semantic features, tool detections, and video frame temporal correspondences to create a representative summarization. Summarization by our method resulted in a 98.2% reduction in overall video length while preserving 84% of key medical scenes. Furthermore, resulting summaries contained only 1% of scenes with irrelevant detail such as endoscope lens cleaning, blurry frames, or frames external to the patient. This outperformed leading commercial and open source summarization tools not designed for surgery, which only preserved 57% and 46% of key medical scenes in similar length summaries, and included 36% and 59% of scenes containing irrelevant detail. Experts agreed that on average (Likert Scale = 4) that the overall quality of the video was adequate to share with peers in its current state.

Hallermann-Streiff Syndrome in Concordant Monozygotic Twins With Congenital Cataracts, Exudative Retinal Detachments, and One Case of Corneal Perforation Requiring Keratoplasty.

PURPOSE: We describe the management of Hallermann-Streiff syndrome in monozygotic female twins with congenital cataracts, exudative retinal detachments, and 1 case of corneal descemetocele with associated dellen and subsequent perforation. METHODS: This study was a case report and review of the literature. RESULTS: Twins 1 and 2 exhibited all 7 cardinal characteristics of Hallermann-Streiff syndrome, presenting with spontaneous lenticular resorption, anterior uveitis, and glaucoma. They underwent bilateral cataract extraction with near total capsulectomy. Both twins experienced recurrent glaucoma, for which twin 1 underwent successful endocyclophotocoagulation in both eyes and twin 2 in the left eye alone. The fellow eye developed 2 sites of perilimbal corneal descemetoceles with associated dellen at the inferotemporal limbal corneal junction leading to spontaneous perforation of 1 site, requiring a full-thickness corneal graft. Both twins developed recurrent bilateral exudative retinal detachments unresponsive to oral prednisolone. Twin 1's last best-corrected visual acuity with aphakic spectacles was 20/260 in the right eye and 20/130 in the left eye at age 4 years and 8 months. Twin 2's last best-corrected visual acuity was 20/130 in each eye at age 4 years and 11 months, over a year after right eye penetrating keratoplasty. CONCLUSIONS: We describe 2 rare cases of Hallermann-Streiff syndrome in monozygotic twins complicated by corneal perforation requiring penetrating keratoplasty in 1 eye of 1 twin. Although corneal opacities have been described in this condition, this is the first case of corneal descemetocele in Hallermann-Streiff syndrome. The cornea was stabilized with a relatively favorable visual outcome over 1 year later.

Residency Selection in Otolaryngology: Past, Present, & Future.

OBJECTIVES: To examine the otolaryngology residency selection process, including past experiences based on the medical literature and survey analysis of our present practices to generate recommendations for future selection system design. METHODS: A mixed-methods study, including a scoping review and a cross-sectional survey, was completed. Four databases were assessed for articles on otolaryngology residency selection published from January 1, 2016 through December 31, 2020. A 36-question survey was developed and distributed to 114 otolaryngology program directors. Descriptive and thematic analysis was performed. RESULTS: Ultimately, 67 of 168 articles underwent data abstraction and assessment. Three themes surfaced during the analysis: effectiveness, efficiency, and equity. Regarding the survey, there were 62 participants (54.4% response rate). The three most important goals for the selection process were: (1) to fit the program culture, (2) to make good colleagues, and (3) to contribute to the program's diversity. The three biggest 'pain points' were as follows: (1) Large volume of applications, (2) Lack of reliable information about personal characteristics, and (3) Lack of reliable information about a genuine interest in the program. CONCLUSIONS: Within this study, the depth and breadth of the literature on otolaryngology residency selection have been synthesized. Additionally, baseline data on selection practices within our specialty has been captured. With an informed understanding of our past and present, we can look to the future. Built upon the principles of person-environment fit theory, our proposed framework can guide research and policy discussions regarding the design of selection systems in otolaryngology, as we work to achieve more effective, efficient, and equitable outcomes. LEVEL OF EVIDENCE: N/A Laryngoscope, 133:2929-2941, 2023.

Intersectionality of Race, Ethnicity, and Gender in the Otolaryngology Match From 2013 to 2019.

OBJECTIVES: Racial, ethnic, and gender disparities in the otolaryngology-head and neck surgery (OHNS) match have been described individually, but not intersectionally. Intersectionality recognizes how multiple forms of discrimination (e.g., sexism, racism) can have a combined effect. The objective of this study was to analyze racial, ethnic, and gender disparities in the OHNS match using an intersectional approach. METHODS: Cross-sectional evaluation of data from otolaryngology applicants from the Electronic Residency Application Service (ERAS) and of corresponding otolaryngology residents from the Accreditation Council for Graduate Medical Education (ACGME) from 2013 to 2019. Data were stratified by race, ethnicity, and gender. The Cochran-Armitage tests assessed trends over time in the proportions of applicants and corresponding residents. Chi-square tests with Yates' continuity correction were performed to evaluate differences between the aggregate proportions of applicants and corresponding residents. RESULTS: The proportion of White men in the resident pool was increased compared to the applicant pool (ACGME 0.417, ERAS 0.375; Δ + 0.042; 95% CI 0.012 to 0.071; p = 0.03). This was also the case for White women (ACGME 0.206, ERAS 0.175; Δ + 0.031; 95% CI 0.007 to 0.055; p = 0.05). In contrast, there was a smaller proportion of residents compared to applicants among Multiracial men (ACGME 0.014, ERAS 0.047; Δ - 0.033; 95% CI -0.043 to -0.023; p < 0.001) and Multiracial women (ACGME 0.010, ERAS 0.026; Δ - 0.016; 95% CI -0.024 to -0.008; p < 0.001). CONCLUSION: The findings of this study imply that White men have a persistent advantage, while several racial, ethnic, and gender minorities are disadvantaged in the OHNS match. Further research is necessary to examine why these differences exist in residency selection, including evaluation during the screening, reviewing, interviewing, and ranking stages. Laryngoscope, 133:2558-2563, 2023.

Sphincter Pharyngoplasty for Velopharyngeal Dysfunction: Impact of 22q11.2 Deletion Syndrome.

OBJECTIVE: Patients with 22q11.2 deletion syndrome (22q11DelS) often present with velopharyngeal dysfunction (VPD). VPD in patients with 22q11DelS is multifactorial beyond velopharyngeal insufficiency (VPI) alone, and differences in surgical outcomes are poorly understood. Our objective was to determine whether patients with 22q11DelS have an increased risk for persistent VPI after sphincter pharyngoplasty compared to patients without 22q11DelS. METHODS: We completed a retrospective cohort study of patients with 22q11DelS undergoing sphincter pharyngoplasty between 1995 and 2019 using a VPD clinic database. Patients with 22q11DelS were compared to a cohort of 2:1 frequency-matched (age, degree of velopharyngeal closure) patients without 22q11DelS. Variables included patient characteristics, surgical history, perceptual speech evaluation, and degree of closure on nasopharyngoscopic evaluations. Primary outcomes included postoperative VPI severity and hypernasality. Speech and nasopharyngoscopic characteristics were compared using Fisher's exact test. Postoperative VPI severity and hypernasality were compared between groups via relative risks (RR) from mixed effects Poisson regression models, with random effects of age and velopharyngeal closure. RESULTS: 134 patients (51 22q11DelS, 83 matched) were included, with mean age of 7.3 years (standard deviation 3.0) and 50% male. Cohorts had similar preoperative speech characteristics and nasopharyngoscopic findings. Patients with 22q11DelS had similar postoperative VP function as patients without 22q11DelS (RR 0.85, CI 0.46-1.57 for VPI severity, RR 0.83, CI 0.45-1.53 for hypernasality). Even after adjusting by preoperative variables, no differences were seen between both groups. CONCLUSION: Matched for age and pre-operative velopharyngeal closure, patients with and without 22q11DelS and VPI had similar benefits after sphincter pharyngoplasty. LEVEL OF EVIDENCE: Non-randomized controlled cohort study, 3 Laryngoscope, 133:2813-2820, 2023.

Delaying Invasive Treatment in Unilateral Head and Neck Lymphatic Malformation Improves Outcomes.

OBJECTIVES: Large (De Serres stage [IV-V]) head and neck lymphatic malformations (HNLMs) often have multiple, high-risk, invasive treatments (ITs) to address functional compromise. Logically reducing HNLM ITs should reduce treatment risk. We tested whether delaying HNLM ITs reduces total IT number. MATERIALS: Consecutive HNLM patients (n = 199) between 2010 and 2017, aged 0-18 years. METHODS: ITs (surgery or sclerotherapy) were offered for persistent or dysfunction causing HNLMs. Treatment effectiveness categorized by IT number: optimal (0-1), acceptable (2-5), or suboptimal (>5). Clinical data were summarized, and outcome associations tested (χ2 ). Relative risk (RR) with a Poisson working model tested whether HNLM observation or IT delay (>6 months post-diagnosis) predicts treatment success (i.e., ≤1 IT). RESULTS: Median age at HNLM diagnosis was 1.3 months (interquartile range [IQR] 0-45 m) with 107/199(54%) male. HNLM were stage I-III (174 [88%]), IV-V (25 [13%]). Initial treatment was observation (70 [35%]), invasive (129 [65%]). Treatment outcomes were optimal (137 [69%]), acceptable (36 [18%]), and suboptimal (26 [13%]). Suboptimal outcome associations: EXIT procedure, stage IV-V, oral location, and tracheotomy (p < 0.001). Stage I-III HNLMs were initially observed compared with stage I-III having ITs within 6 months of HNLM diagnosis, had a 82% lower relative treatment failure risk ([i.e., >1 IT], RR = 0.09, 95% CI 0.02-0.36, p < 0.001). Stage I-III HNLMs with non-delayed ITs had reduced treatment failure risk compared with IV-V (RR = 0.47, 95% CI 0.33-0.66, p < 0.001). CONCLUSION: Observation and delayed IT in stage I-III HNLM ("Grade 1") is safe and reduces IT (i.e., ≤1 IT). Stage IV-V HNLMs ("Grade 2") with early IT have a greater risk of multiple ITs. LEVEL OF EVIDENCE: 4 Laryngoscope, 133:956-962, 2023.

Virtually Assisted Personalized Tracheostomy Tube Design in Pediatric Complex Airway Anomalies.

We sought to assess the feasibility of virtually assisted personalized tracheostomy tube (vapTT) implementation for patients with congenital airway anomalies (CAAs) and persistent tracheostomy tube (TT)-related respiratory failure at a tertiary pediatric hospital. Three patients (0-18 years) with CAAs and recurrent TT-related respiratory complications were managed with vapTT over 5 years. Patients underwent airway computed tomography acquisition with 3-dimensional reconstruction and TT virtual modeling for shape customization. Models were transferred to Bivona for fabrication based on industry-standard materials and processes. Clinical information and tracheoscopies assessing position, obstruction, and granulation were reviewed. Patients demonstrated resolution of visualized TT-related obstruction, granulation, or ulceration and de-escalation of respiratory support. Clinical events requiring urgent tracheoscopy decreased in all 3 patients. Sufficient relief of critical airway obstruction allowed progression of medical care and/or discharge. VapTTs are feasible for patients with CAA. This new frontier in personalized devices may serve uniquely challenging patient populations for whom standard treatments have failed.

Primary targeted medical therapy for management of bilateral head and neck lymphatic malformations in infants.

OBJECTIVES: Patients born with bilateral head and neck lymphatic malformations (BHNLMs) often require multiple invasive treatments, including tracheostomy. We hypothesized that primary targeted medical therapy (pTMT) with diagnostic needle aspiration reduces the need for invasive therapy such as surgical resection and/or sclerotherapy. METHODS: Retrospective case review was performed of infants with BHNLMs (Grade 2 or De Serres stage IV and V) treated only at our institution from 2000 to 2021. Patients were divided into two cohorts: those managed with pTMT and those managed with observation, sclerotherapy, or surgical intervention (non-pTMT). Data regarding interventions, clinical outcomes, morbidity, and mortality were analyzed with descriptive statistics. RESULTS: Nine children with BHNLMs met inclusion criteria. Three (33%) were in the pTMT cohort and six (66%) were non-pTMT. Eight (89%) malformations were genotyped, and all demonstrated hotspot PIK3CA variants. All pTMT patients had sirolimus initiated in the first month of life and underwent needle aspiration of malformation cyst fluid for cell-free DNA samples. All pTMT patients tolerated medical therapy. For the non-pTMT cohort, primary treatment included none (deceased, n = 1, 17%), observation with needle aspiration (n = 1, 17%), surgical resection (n = 2, 33%), or combination surgery and sclerotherapy (n = 2, 33%). Intubation duration, intensive care and initial hospital length of stay were not different between cohorts. Four non-pTMT patients (67%) required tracheostomy, and two (33%) died prior to discharge. All pTMT patients survived and none required tracheostomy. Non-pTMT patients required a median of two invasive therapies prior to discharge (IQR 1-4) and a mean total of 13 over the course of their lifetime (IQR 1-16), compared to the pTMT group who did not require any lifetime invasive therapy, even after initial pTMT and discharge home. CONCLUSION: This study compares patients with BHNLMs (Grade 2) treated with pTMT versus those treated with observation or invasive therapy. Patients treated with pTMT required no surgical or invasive procedural treatment of their malformations, no tracheostomy placement, no unplanned readmissions after discharge, and had no mortalities. Needle aspiration was useful as a therapeutic adjunct for cell-free DNA diagnosis of PIK3CA variants, which guided TMT.

Analysis of Upper Airway Flow Dynamics in Robin Sequence Infants Using 4-D Computed Tomography and Computational Fluid Dynamics.

Robin Sequence (RS) is a potentially fatal craniofacial condition characterized by undersized jaw, posteriorly displaced tongue, and resultant upper airway obstruction (UAO). Accurate assessment of UAO severity is crucial for management and diagnosis of RS, yet current evaluation modalities have significant limitations and no quantitative measures of airway resistance exist. In this study, we combine 4-dimensional computed tomography and computational fluid dynamics (CFD) to assess, for the first time, UAO severity using fluid dynamic metrics in RS patients. Dramatic intrapopulation differences are found, with the ratio between most and least severe patients in breathing resistance, energy loss, and peak velocity equal to 40:1, 20:1, and 6:1, respectively. Analysis of local airflow dynamics characterized patients as presenting with primary obstructions either at the location of the tongue base, or at the larynx, with tongue base obstructions resulting in a more energetic stenotic jet and greater breathing resistance. Finally, CFD-derived flow metrics are found to correlate with the level of clinical respiratory support. Our results highlight the large intrapopulation variability, both in quantitative metrics of UAO severity (resistance, energy loss, velocity) and in the location and intensity of stenotic jets for RS patients. These results suggest that computed airflow metrics may significantly improve our understanding of UAO and its management in RS.

An off-the-shelf otoacoustic-emission probe for hearing screening via a smartphone.

Otoacoustic emissions (OAEs) provide information about the function of the outer hair cells of the cochlea. In high-income countries, infants undergo OAE tests as part of the screening protocols for hearing. However, the cost of the necessary equipment hinders early screening for hearing in low- and middle-income countries, which disproportionately bear the brunt of disabling hearing loss. Here we report the design and clinical testing of a low-cost probe for OAEs. The device, which has a material cost of approximately US$10, uses an off-the-shelf microphone and off-the-shelf earphones connected to a smartphone through a headphone jack. It sends two pure tones through each of the headphone's earbuds and algorithmically detects the distortion-product OAEs generated by the cochlea and recorded via the microphone. In a clinical study involving 201 paediatric ears across three healthcare sites, the device detected hearing loss with 100% sensitivity and 88.9% specificity, comparable to the performance of a commercial device. Low-cost devices for OAE testing may aid the early detection of hearing loss in resource-constrained settings.