Machine Learning Approach for Screening Cochlear Implant Candidates: Comparing With the 60/60 Guideline.

OBJECTIVE: To develop a machine learning-based referral guideline for patients undergoing cochlear implant candidacy evaluation (CICE) and to compare with the widely used 60/60 guideline. STUDY DESIGN: Retrospective cohort. SETTING: Tertiary referral center. PATIENTS: 772 adults undergoing CICE from 2015 to 2020. INTERVENTIONS: Variables included demographics, unaided thresholds, and word recognition score. A random forest classification model was trained on patients undergoing CICE, and bootstrap cross-validation was used to assess the modeling approach's performance. MAIN OUTCOME MEASURES: The machine learning-based referral tool was evaluated against the 60/60 guideline based on ability to identify CI candidates under traditional and expanded criteria. RESULTS: Of 587 patients with complete data, 563 (96%) met candidacy at our center, and the 60/60 guideline identified 512 (87%) patients. In the random forest model, word recognition score; thresholds at 3000, 2000, and 125; and age at CICE had the largest impact on candidacy (mean decrease in Gini coefficient, 2.83, 1.60, 1.20, 1.17, and 1.16, respectively). The 60/60 guideline had a sensitivity of 0.91, a specificity of 0.42, and an accuracy of 0.89 (95% confidence interval, 0.86-0.91). The random forest model obtained higher sensitivity (0.96), specificity (1.00), and accuracy (0.96; 95% confidence interval, 0.95-0.98). Across 1,000 bootstrapped iterations, the model yielded a median sensitivity of 0.92 (interquartile range [IQR], 0.85-0.98), specificity of 1.00 (IQR, 0.88-1.00), accuracy of 0.93 (IQR, 0.85-0.97), and area under the curve of 0.96 (IQR, 0.93-0.98). CONCLUSIONS: A novel machine learning-based screening model is highly sensitive, specific, and accurate in predicting CI candidacy. Bootstrapping confirmed that this approach is potentially generalizable with consistent results.

Leveraging the virtual landscape to promote diversity, equity, and inclusion in Otolaryngology-Head & Neck Surgery.

The pandemic era has wrought disruptive changes across all aspects of academic medicine, transforming clinical care systems, research enterprises, and educational practices. Among these sweeping changes, some of the most significant for Otolaryngology-Head & Neck Surgery (OHNS) relate to innovative use of virtual communication. The virtual landscape has not only redefined the delivery of patient care but also expanded educational interactions across the career continuum. As the architecture of relationships has been reimagined, the traditional Halstedian teaching paradigm has evolved, now integrating in-person, virtual, and hybrid learning. Once formidable barriers to distance learning have diminished, giving way to social networks that support mentorship, coaching, and sponsorship. Creative use of technology supports collaboration, feedback, spaced learning, scaffolding, and interleaving. These advances have immediate significance for OHNS, a highly collaborative specialty that leads in technological innovation and aspires to improve diversity. Whereas traditional efforts to grow the ranks of underrepresented in medicine (URiM) individuals in OHNS yielded only incremental progress, the virtual landscape is unveiling new strategies for reengineering narrow or leaky pipelines. Strategies that can help attract URiM applicants include inclusive departmental web presence, interactive online clinical experiences, virtual interviews, and remote research opportunities. As students, surgeons, and scientists collectively embrace technology, accelerated progress toward diversity, equity, and inclusion (DEI) becomes possible. Maximizing these opportunities requires aligning national and institutional imperatives for diversity with departmental priorities and mission. Finally, intentional outreach and holistic assessment support growth of structured virtual communities that foster equitable access for those who need it most.

Stevens-Johnson syndrome and toxic epidermal necrolysis: A systematic review of PubMed/MEDLINE case reports from 1980 to 2020.

Background: Stevens-Johnson syndrome (SJS) and toxic epidermal necrolysis (TEN) are rare, life-threatening immunologic reactions. Prior studies using electronic health records, registries or reporting databases are often limited in sample size or lack clinical details. We reviewed diverse detailed case reports published over four decades. Methods: Stevens-Johnson syndrome and toxic epidermal necrolysis-related case reports were identified from the MEDLINE database between 1980 and 2020. Each report was classified by severity (i.e., SJS, TEN, or SJS-TEN overlap) after being considered a "probable" or "definite" SJS/TEN case. The demographics, preconditions, culprit agents, clinical course, and mortality of the cases were analyzed across the disease severity. Results: Among 1,059 "probable" or "definite" cases, there were 381 (36.0%) SJS, 602 (56.8%) TEN, and 76 (7.2%) SJS-TEN overlap cases, with a mortality rate of 6.3%, 24.4%, and 21.1%, respectively. Over one-third of cases had immunocompromised conditions preceding onset, including cancer (n = 194,18.3%), autoimmune diseases (n = 97, 9.2%), and human immunodeficiency virus (HIV) (n = 52, 4.9%). During the acute phase of the reaction, 843 (79.5%) cases reported mucous membrane involvement and 210 (19.8%) involved visceral organs. Most cases were drug-induced (n = 957, 90.3%). A total of 379 drug culprits were reported; the most frequently reported drug were antibiotics (n = 285, 26.9%), followed by anticonvulsants (n = 196, 18.5%), analgesics/anesthetics (n = 126, 11.9%), and antineoplastics (n = 120, 11.3%). 127 (12.0%) cases reported non-drug culprits, including infections (n = 68, 6.4%), of which 44 were associated with a mycoplasma pneumoniae infection and radiotherapy (n = 27, 2.5%). Conclusion: An expansive list of potential causative agents were identified from a large set of literature-reported SJS/TEN cases, which warrant future investigation to understand risk factors and clinical manifestations of SJS/TEN in different populations.

Sacral Insufficiency Fractures.

¼: Primary osteoporosis is the most common cause of sacral insufficiency fractures (SIFs). Therefore, a multidisciplinary team approach is necessary for treatment of the fracture and the underlying biologic pathology, as well as prevention of future fragility fractures. ¼: The presentation of SIFs typically includes lower back or buttock pain after a ground-level fall or without an identified trauma. Symptoms often have an insidious onset and are nonspecific; consequently, a delay in diagnosis and treatment is common. Clinicians need to have a high index of suspicion, particularly in high-risk patients. ¼: Postmenopausal women who are >55 years of age are the most common demographic affected by SIFs. Other risk factors include osteoporosis, history of a prior fragility fracture, local irradiation, long-term corticosteroid use, rheumatoid arthritis, metabolic bone disorders, vitamin D deficiency, pregnancy, history of prior multilevel spinal fusion, and malignancy. ¼: Typical imaging on computed tomography (CT) shows sclerosis of cancellous bone in the sacral ala, with or without a discrete fracture line or displacement. Magnetic resonance imaging is more sensitive than CT and shows hypointense signal on T1-weighted sequences and hyperintensity on T2-weighted or short tau inversion recovery sequences. ¼: The treatment of SIFs is dependent on the severity of symptoms, fracture displacement, and instability of the pelvis. Accepted treatments include nonoperative rehabilitation, sacroplasty, iliosacral screw fixation, transsacral bar or screw fixation, transiliac internal fixation, and lumbopelvic fixation.

Identifying and Reconciling Patients' Allergy Information Within the Electronic Health Record.

Allergy information is often documented in diverse sections of the electronic health record (EHR). Systematically reconciling allergy information across the EHR is critical to improve the accuracy and completeness of patients' allergy lists and ensure patient safety. In this retrospective cohort study, we examined the prevalence of incompleteness, inaccuracy, and redundancy of allergy information for patients with a clinical encounter at any Mass General Brigham facility between January 1, 2018 and December 31, 2018. We identified 4 key places in the EHR containing reconcilable allergy information: 1) allergy modules (including free text comments and duplicate allergen entries), 2) medication laboratory tests results, 3) oral medication allergy challenge tests, and 4) medication orders that have been discontinued due to adverse drug reactions (ADRs). Within our cohort, 718,315 (45.2% of the total 1,588,979) patients had an active allergy entry; of which, 266,275 (37.1%) patient's records indicated a need for reconciliation.

Evaluation of the Molecular Landscape of Pediatric Thyroid Nodules and Use of a Multigene Genomic Classifier in Children.

Importance: Definitive diagnosis of a thyroid nodule in a child is obtained through diagnostic surgery. This is problematic because pediatric thyroid surgery is associated with higher rates of complications. In adults, preoperative molecular testing improves the management of thyroid nodules, but this has not been validated in children. Objective: To determine whether the molecular landscape of pediatric thyroid nodules is amenable to detection by a multigene genomic classifier (GC) test (ThyroSeq v3; Sonic Healthcare USA). Design, Setting, and Participants: This was a retrospective consecutive case series and GC testing of fine-needle aspiration (FNA) and formalin-fixed paraffin-embedded (FFPE) tissues from sequential pediatric thyroidectomies performed between January 2003 and December 2019 at a single tertiary academic medical center. The study included 95 patients (median [range] age, 16.3 [4.8 to 21.1] years; 75 [79%] female) who underwent surgery for a thyroid nodule. Interventions: A total of 118 thyroid nodule samples (95 FFPE, 23 companion FNAs) yielded informative next-generation sequencing data and multigene GC. Main Outcomes and Measures: The primary outcome was the determination of the pediatric thyroid molecular landscape. The secondary outcome was the diagnostic accuracy of the GC test for pediatric thyroid nodules. Results: Of the 95 patients, 75 (79%) were female, and the median (IQR) age was 16.3 (14.0-17.3) years. Next-generation sequencing confirmed the unique molecular landscape of malignant pediatric thyroid nodules (compared with adults), which is dominated by gene fusions (most commonly RET and NTRK), rare BRAF/RAS alterations, and no TP53 or TERT promoter pathogenic variants. Several poorly differentiated thyroid cancers harbored DICER1 variants. Benign nodules appeared to be almost exclusively associated with TSHR and DICER1 alterations. The test demonstrated a 96% sensitivity (95% CI, 87%-99%) and 78% specificity (95% CI, 64%-88%). The negative predictive value was 95% (95% CI, 88%-98%) and the positive predictive value was 83% (95% CI, 74-89%). The concordance of GC between 23 pairs of matched FFPE and FNA tissues was 96%. Conclusions and Relevance: The study results of this retrospective consecutive case series suggest that the molecular landscape of pediatric nodules is unique but remains amenable to molecular classification. The multigene GC test, with high sensitivity and reasonably high specificity, represents a potential addition to the diagnostic workup of children with thyroid nodules and may decrease the use of diagnostic surgery.

Heterogeneity of Drug Allergies and Reaction Lists in Two U.S. Health Care Systems' Electronic Health Records.

BACKGROUND: Health care institutions have their own "picklist" for clinicians to document adverse drug reactions (ADRs) into the electronic health record (EHR) allergy list. Whether the lack of a nationally standardized picklist impacts clinician data entries is unknown. OBJECTIVES: The objective of this study was to assess the impact of defined reaction picklists on clinical documentation and, therefore, downstream analytics and clinical research using these data at two institutions. METHODS: ADR data were obtained from the EHRs of patients who visited the emergency department or outpatient clinics at Brigham and Women's Hospital (BWH) and University of Colorado Hospital (UCH) from 2013 to 2018. Reported drug class ADR prevalences were calculated. We investigated the reactions on each picklist and compared the top 40 reactions at each institution, as well as the top 10 reactions within each drug class. RESULTS: Of 2,160,116 patients, 640,444 (30%) had 928,973 active drug allergies. The most commonly reported drug class allergens were similar between BWH and UCH. BWH's picklist had 48 reactions, and UCH's had 160 reactions; 29 reactions were shared by both picklists. While the top four reactions overall (rash, GI upset/nausea/vomiting, hives, itching) were identical between sites, reactions by drug class exhibited greater documentation diversity. For example, while the summed prevalence of swelling-related reactions to angiotensin-converting-enzyme inhibitors was comparable across sites, swelling was represented by two terms ("swelling," "angioedema") at BWH but 11 terms at UCH (e.g., "swelling," "edema," by body locality). CONCLUSION: The availability and granularity of reaction picklists impact ADR documentation in the EHR by health care providers; picklists may partially explain variations in reported ADRs across health care systems.

Global Epidemiology of Craniosynostosis: A Systematic Review and Meta-Analysis.

OBJECTIVE: Craniosynostosis leads to craniofacial deformity and may result in raised intracranial pressure, neurocognitive deficits, and psychosocial issues if left untreated. The global epidemiology of craniosynostosis is unknown. We conducted a meta-analysis to estimate global birth prevalence. METHODS: PubMed, Embase, and Scopus were searched. Articles were screened by title and abstract and then full text. Meta-analysis of birth prevalence was conducted. Birth prevalence figures were combined with metrics detailing the number of births in 2019 to estimate the number of children worldwide born with craniosynostosis annually. RESULTS: Of 1378 resultant articles, 24 studies were included, including 20 providing data for craniosynostosis overall and 9 for nonsyndromic craniosynostosis. World Health Organization regions of included studies were 9 (37.5%) European Region, 8 (33.3%) Region of the Americas, 4 (16.7%) Western Pacific region, 2 (8.3%) African Region, and 1 (4.2%) Eastern Mediterranean Region. Lower middle-income countries represented only 4% of study manuscripts. The overall birth prevalence of craniosynostosis was 5.9 per 10,000 live births (20 studies; 95% confidence interval [CI]: 3.9, 8.4; I2 = 100%). The birth prevalence of nonsyndromic craniosynostosis was 5.2 per 10,000 live births (9 studies; 95% CI: 3.4, 7.3; I2 = 98%). The number of children born globally with craniosynostosis in 2019 was estimated to be 84,665 (95% CI: 55,965, 120,540), including 72,857 (95% CI: 47,637, 120,280) with nonsyndromic craniosynostosis. CONCLUSIONS: Craniosynostosis is a common condition that affects the neurocognitive and craniofacial skeletal development of children worldwide. Initiatives to scale up capacity for craniosynostosis epidemiologic research and clinical care are warranted, particularly in low- and middle-income countries.

Nasal Mucosal Desmoplastic Melanoma: A Case Report with Review of the Literature.

Mucosal melanoma is a rare subtype of melanoma that accounts for 1% of all melanomas. The incidence of nasal mucosal melanomas is 0.3 per million. Desmoplastic melanomas are a subtype of melanoma with a reported incidence of 2.0 per million. Although 50% of desmoplastic melanomas are found in the head and neck region, mucosal desmoplastic melanoma is exceedingly rare. In the present study, we report a case of nasal mucosal desmoplastic melanoma and review the literature. A 79-year-old female presented to an outside otolaryngologist with nasal discomfort accompanied by rhinorrhea and was found to have a nasal vestibule mass. An endonasal incisional biopsy was performed yielding a diagnosis of a SOX-10 positive tumor. The patient was referred to our institution for further management. A blue-tinged lesion was identified at the prior biopsy site, and the mass was resected via an open rhinoplasty approach. Final pathology demonstrated an infiltrative spindle cell neoplasm with immunohistochemical patterns supportive of desmoplastic melanoma arising from the nasal vestibule. Due to positive margins, the patient underwent a re-resection with no tumor identified on the re-resected specimen. To our knowledge, this is the third case of nasal mucosal desmoplastic melanoma. We review the clinicopathologic features and management of this rare entity.

Effects of Mobile Phone Use on Driving Performance: An Experimental Study of Workload and Traffic Violations.

The use of communication technologies, e.g., mobile phones, has increased dramatically in recent years, and their use among drivers has become a great risk to traffic safety. The present study assessed the workload and road ordinary violations, utilizing driving data collected from 39 young participants who underwent a dual-task while driving a simulator, i.e., respond to a call, text on WhatsApp, and check Instagram. Findings confirmed that there are significant differences in the driving performance of young drivers in terms of vehicle control (i.e., lateral distance and hard shoulder line violations) between distracted and non-distracted drivers. Furthermore, the overall workload score of young drivers increases with the use of their mobile phones while driving. The obtained results contribute to a better understanding of the driving performance of distracted young drivers and thus they could be useful for further improvements to traffic safety strategies.

Observer-Based Time-Variant Spacing Policy for a Platoon of Non-Holonomic Mobile Robots.

This paper presents a navigation strategy for a platoon of n non-holonomic mobile robots with a time-varying spacing policy between each pair of successive robots at the platoon, such that a safe trailing distance is maintained at any speed, avoiding the robots getting too close to each other. It is intended that all the vehicles in the formation follow the trajectory described by the leader robot, which is generated by bounded input velocities. To establish a chain formation among the vehicles, it is required that, for each pair of successive vehicles, the (i+1)-th one follows the trajectory executed by the former i-th one, with a delay of τ(t) units of time. An observer is proposed to estimate the trajectory, velocities, and positions of the i-th vehicle, delayed τ(t) units of time, consequently generating the desired path for the (i+1)-th vehicle, avoiding numerical approximations of the velocities, rendering robustness against noise and corrupted or missing data as well as to external disturbances. Besides the time-varying gap, a constant-time gap is used to get a secure trailing distance between each two successive robots. The presented platoon formation strategy is analyzed and proven by using Lyapunov theory, concluding asymptotic convergence for the posture tracking between the (i+1)-th robot and the virtual reference provided by the observer that corresponds to the i-th robot. The strategy is evaluated by numerical simulations and real-time experiments.

A dynamic reaction picklist for improving allergy reaction documentation in the electronic health record.

OBJECTIVE: Incomplete and static reaction picklists in the allergy module led to free-text and missing entries that inhibit the clinical decision support intended to prevent adverse drug reactions. We developed a novel, data-driven, "dynamic" reaction picklist to improve allergy documentation in the electronic health record (EHR). MATERIALS AND METHODS: We split 3 decades of allergy entries in the EHR of a large Massachusetts healthcare system into development and validation datasets. We consolidated duplicate allergens and those with the same ingredients or allergen groups. We created a reaction value set via expert review of a previously developed value set and then applied natural language processing to reconcile reactions from structured and free-text entries. Three association rule-mining measures were used to develop a comprehensive reaction picklist dynamically ranked by allergen. The dynamic picklist was assessed using recall at top k suggested reactions, comparing performance to the static picklist. RESULTS: The modified reaction value set contained 490 reaction concepts. Among 4 234 327 allergy entries collected, 7463 unique consolidated allergens and 469 unique reactions were identified. Of the 3 dynamic reaction picklists developed, the 1 with the optimal ranking achieved recalls of 0.632, 0.763, and 0.822 at the top 5, 10, and 15, respectively, significantly outperforming the static reaction picklist ranked by reaction frequency. CONCLUSION: The dynamic reaction picklist developed using EHR data and a statistical measure was superior to the static picklist and suggested proper reactions for allergy documentation. Further studies might evaluate the usability and impact on allergy documentation in the EHR.

A clinician survey of using speech recognition for clinical documentation in the electronic health record.

OBJECTIVE: To assess the role of speech recognition (SR) technology in clinicians' documentation workflows by examining use of, experience with and opinions about this technology. MATERIALS AND METHODS: We distributed a survey in 2016-2017 to 1731 clinician SR users at two large medical centers in Boston, Massachusetts and Aurora, Colorado. The survey asked about demographic and clinical characteristics, SR use and preferences, perceived accuracy, efficiency, and usability of SR, and overall satisfaction. Associations between outcomes (e.g., satisfaction) and factors (e.g., error prevalence) were measured using ordinal logistic regression. RESULTS: Most respondents (65.3%) had used their SR system for under one year. 75.5% of respondents estimated seeing 10 or fewer errors per dictation, but 19.6% estimated half or more of errors were clinically significant. Although 29.4% of respondents did not include SR among their preferred documentation methods, 78.8% were satisfied with SR, and 77.2% agreed that SR improves efficiency. Satisfaction was associated positively with efficiency and negatively with error prevalence and editing time. Respondents were interested in further training about using SR effectively but expressed concerns regarding software reliability, editing and workflow. DISCUSSION: Compared to other documentation methods (e.g., scribes, templates, typing, traditional dictation), SR has emerged as an effective solution, overcoming limitations inherent in other options and potentially improving efficiency while preserving documentation quality. CONCLUSION: While concerns about SR usability and accuracy persist, clinicians expressed positive opinions about its impact on workflow and efficiency. Faster and better approaches are needed for clinical documentation, and SR is likely to play an important role going forward.

Decoding unconstrained arm movements in primates using high-density electrocorticography signals for brain-machine interface use.

Motor deficit is among the most debilitating aspects of injury to the central nervous system. Despite ongoing progress in brain-machine interface (BMI) development and in the functional electrical stimulation of muscles and nerves, little is understood about how neural signals in the brain may be used to potentially control movement in one's own unconstrained paralyzed limb. We recorded from high-density electrocorticography (ECoG) electrode arrays in the ventral premotor cortex (PMv) of a rhesus macaque and used real-time motion tracking techniques to correlate spatial-temporal changes in neural activity with arm movements made towards objects in three-dimensional space at millisecond precision. We found that neural activity from a small number of electrodes within the PMv can be used to accurately predict reach-return movement onset and directionality. Also, whereas higher gamma frequency field activity was more predictive about movement direction during performance, mid-band (beta and low gamma) activity was more predictive of movement prior to onset. We speculate these dual spatiotemporal signals may be used to optimize both planning and execution of movement during natural reaching, with prospective relevance to the future development of neural prosthetics aimed at restoring motor control over one's own paralyzed limb.