ChatGPT's adherence to otolaryngology clinical practice guidelines.

OBJECTIVES: Large language models, including ChatGPT, has the potential to transform the way we approach medical knowledge, yet accuracy in clinical topics is critical. Here we assessed ChatGPT's performance in adhering to the American Academy of Otolaryngology-Head and Neck Surgery guidelines. METHODS: We presented ChatGPT with 24 clinical otolaryngology questions based on the guidelines of the American Academy of Otolaryngology. This was done three times (N = 72) to test the model's consistency. Two otolaryngologists evaluated the responses for accuracy and relevance to the guidelines. Cohen's Kappa was used to measure evaluator agreement, and Cronbach's alpha assessed the consistency of ChatGPT's responses. RESULTS: The study revealed mixed results; 59.7% (43/72) of ChatGPT's responses were highly accurate, while only 2.8% (2/72) directly contradicted the guidelines. The model showed 100% accuracy in Head and Neck, but lower accuracy in Rhinology and Otology/Neurotology (66%), Laryngology (50%), and Pediatrics (8%). The model's responses were consistent in 17/24 (70.8%), with a Cronbach's alpha value of 0.87, indicating a reasonable consistency across tests. CONCLUSIONS: Using a guideline-based set of structured questions, ChatGPT demonstrates consistency but variable accuracy in otolaryngology. Its lower performance in some areas, especially Pediatrics, suggests that further rigorous evaluation is needed before considering real-world clinical use.

Navigating the vestibular maze: text-mining analysis of publication trends over five decades.

Introduction: The field of vestibular science, encompassing the study of the vestibular system and associated disorders, has experienced notable growth and evolving trends over the past five decades. Here, we explore the changing landscape in vestibular science, focusing on epidemiology, peripheral pathologies, diagnosis methods, treatment, and technological advancements. Methods: Publication data was obtained from the US National Center for Biotechnology Information (NCBI) PubMed database. The analysis included epidemiological, etiological, diagnostic, and treatment-focused studies on peripheral vestibular disorders, with a particular emphasis on changes in topics and trends of publications over time. Results: Our dataset of 39,238 publications revealed a rising trend in research across all age groups. Etiologically, benign paroxysmal positional vertigo (BPPV) and Meniere's disease were the most researched conditions, but the prevalence of studies on vestibular migraine showed a marked increase in recent years. Electronystagmography (ENG)/ Videonystagmography (VNG) and Vestibular Evoked Myogenic Potential (VEMP) were the most commonly discussed diagnostic tools, while physiotherapy stood out as the primary treatment modality. Conclusion: Our study presents a unique opportunity and point of view, exploring the evolving landscape of vestibular science publications over the past five decades. The analysis underscored the dynamic nature of the field, highlighting shifts in focus and emerging publication trends in diagnosis and treatment over time.

Advancing Medical Practice with Artificial Intelligence: ChatGPT in Healthcare.

BACKGROUND: Advancements in artificial intelligence (AI) and natural language processing (NLP) have led to the development of language models such as ChatGPT. These models have the potential to transform healthcare and medical research. However, understanding their applications and limitations is essential. OBJECTIVES: To present a view of ChatGPT research and to critically assess ChatGPT's role in medical writing and clinical environments. METHODS: We performed a literature review via the PubMed search engine from 20 November 2022, to 23 April 2023. The search terms included ChatGPT, OpenAI, and large language models. We included studies that focused on ChatGPT, explored its use or implications in medicine, and were original research articles. The selected studies were analyzed considering study design, NLP tasks, main findings, and limitations. RESULTS: Our study included 27 articles that examined ChatGPT's performance in various tasks and medical fields. These studies covered knowledge assessment, writing, and analysis tasks. While ChatGPT was found to be useful in tasks such as generating research ideas, aiding clinical reasoning, and streamlining workflows, limitations were also identified. These limitations included inaccuracies, inconsistencies, fictitious information, and limited knowledge, highlighting the need for further improvements. CONCLUSIONS: The review underscores ChatGPT's potential in various medical applications. Yet, it also points to limitations that require careful human oversight and responsible use to improve patient care, education, and decision-making.

Deep learning in voice analysis for diagnosing vocal cord pathologies: a systematic review.

OBJECTIVES: With smartphones and wearable devices becoming ubiquitous, they offer an opportunity for large-scale voice sampling. This systematic review explores the application of deep learning models for the automated analysis of voice samples to detect vocal cord pathologies. METHODS: We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting guidelines. We searched MEDLINE and Embase databases for original publications on deep learning applications for diagnosing vocal cord pathologies between 2002 and 2022. Risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). RESULTS: Out of the 14 studies that met the inclusion criteria, data from a total of 3037 patients were analyzed. All studies were retrospective. Deep learning applications targeted Reinke's edema, nodules, polyps, cysts, unilateral cord paralysis, and vocal fold cancer detection. Most pathologies had detection accuracy above 90%. Thirteen studies (93%) exhibited a high risk of bias and concerns about applicability. CONCLUSIONS: Technology holds promise for enhancing the screening and diagnosis of vocal cord pathologies. While current research is limited, the presented studies offer proof of concept for developing larger-scale solutions.

Paradigm Change for Intraoperative Surgical Margin Assessment for Oral Squamous Cell Carcinoma.

OBJECTIVE: Achieving clear surgical margins is one of the primary surgical goals in treating oral squamous cell carcinoma (OSCC) and thus aiming to improve overall and disease-specific survival. Therefore, we developed the Goal-Oriented Assessment for Intraoperative Margin ('GAIM') protocol, a novel intraoperative approach for margin assessment, and present here our 5-year experience and outcomes. METHODS: 'GAIM' is a 7-step procedure comprising systematic ruler-aided resection of labeled tumor-bed margins, frozen section (FS) co-produced by both pathologists and operating surgeons, and immediate extension of resection according to FS findings. Data from all patients operated using the 'GAIM' protocol at a single tertiary center between 2018 to 2022 were analyzed, including margin status on FS and final pathology (FP) records, recurrence, and mortality. RESULTS: A total of 196 patients were included, 56.6% (n = 111) stages I-II, and 43.4% (n = 85) stages III-IV. Using the 'GAIM' protocol, we achieved an overall 94.4% of clean and revised clean surgical margins. Patients with a 2-year and longer follow-up (n = 141) had local recurrence in 3.5% when both FS and final margins were clean, 8.1% when FP margins were clean, and 16.7% with close/positive final margins. CONCLUSIONS: The proposed 'GAIM' protocol is a novel, effective, reproducible, and safe approach for margin evaluation that can be systematically applied. It can increase the rate of final clean surgical margins and potentially improve patients' outcomes. LEVEL OF EVIDENCE: 3 Laryngoscope, 134:1725-1732, 2024.

A Five-Decade Text Mining Analysis of Cochlear Implant Research: Where We Started and Where We Are Heading.

Background and Objectives: Since its invention in the 1970s, the cochlear implant (CI) has been substantially developed. We aimed to assess the trends in the published literature to characterize CI. Materials and Methods: We queried PubMed for all CI-related entries published during 1970-2022. The following data were extracted: year of publication, publishing journal, title, keywords, and abstract text. Search terms belonged to the patient's age group, etiology for hearing loss, indications for CI, and surgical methodological advancement. Annual trends of publications were plotted. The slopes of publication trends were calculated by fitting regression lines to the yearly number of publications. Results: Overall, 19,428 CIs articles were identified. Pediatric-related CI was the most dominant sub-population among the age groups, with the highest rate and slope during the years (slope 5.2 ± 0.3, p < 0.001), while elderly-related CIs had significantly fewer publications. Entries concerning hearing preservation showed the sharpest rise among the methods, from no entries in 1980 to 46 entries in 2021 (slope 1.7 ± 0.2, p < 0.001). Entries concerning robotic surgery emerged in 2000, with a sharp increase in recent years (slope 0.5 ± 0.1, p < 0.001). Drug-eluting electrodes and CI under local-anesthesia have been reported only in the past five years, with a gradual rise. Conclusions: Publications regarding CI among pediatrics outnumbered all other indications, supporting the rising, pivotal role of CI in the rehabilitation of children with sensorineural hearing loss. Hearing-preservation publications have recently rapidly risen, identified as the primary trend of the current era, followed by a sharp rise of robotic surgery that is evolving and could define the next revolution.

Investigation of genetic sex-specific molecular profile in well-differentiated thyroid cancer: Is there a difference between females and males?

BACKGROUND: Although more common in females, thyroid cancer is deemed to be more aggressive in males. The reasons for sex disparities in thyroid cancer are not well understood. We hypothesised that differences in molecular mutations between females and males contribute to this phenomenon. METHODS: Retrospective multicentre multinational study of thyroid nodules that underwent preoperative molecular profiling between 2015 and 2022. The clinical characteristics and mutational profiles of tumours in female and male patients were compared. Collected data included demographics, cytology results, surgical pathology, and molecular alterations. RESULTS: A total of 738 patients were included of which 571 (77.4%) were females. The extrathyroidal extension was more common in malignancies in males (chi-squared, p = 0.028). The rate of point mutations and gene fusions were similar in both sex groups (p > 0.05 for all mutations). Patients with nodules with BRAFV600E mutations were significantly younger than BRAF wild-type nodule patients (t-test, p = 0.0001). Conversely, patients with TERT promoter mutations were significantly older than patients with wild-type TERT (t-test, p < 0.0001). For patients harbouring both BRAFV600E and TERT mutations, the difference in age at presentation was significantly different in females (t-test, p = 0.009) but not in males (t-test, p = 0.433). Among females, patients with BRAFV600E and TERT mutations were significantly older than their wild-type or single-mutation counterpart (t-test, p = 0.003). CONCLUSION: The absolute rate of molecular mutations was similar in females and males. We found that extrathyroidal extension was more common in males. Moreover, BRAFV600E and TERT mutations occur at a younger age in males than in females. These two findings are factors that may explain the tendency of more aggressive disease in males.

Outcomes of pregnancy and delivery in women with cardiac disease compared to matched healthy controls.

OBJECTIVE: We compared pregnancy and delivery outcomes between women with cardiac disease versus matched healthy controls. The primary outcome was the frequency of unplanned cesarean delivery. METHODS: In this single-center retrospective case-control study, women with cardiac disease were identified and matched (1:2 ratio, according to maternal age, parity, number of prior cesareans, gestational age, delivery onset and fetal presentation) to healthy controls who delivered within the same year. Outcomes were frequency of unplanned cesarean delivery, complications during pregnancy and postpartum course, intensive care unit (ICU) admissions, and length of hospitalization. RESULTS: One hundred and twelve women with cardiac disease (exposed group, 225 deliveries) were identified and matched with 450 healthy women (controls, 2003-2014). The cohort comprised of 103 women (204 deliveries) with acquired heart disease (valve disease [n = 69], arrhythmia [n = 31], 3 with cardiomyopathy and peri/myocarditis, and 9 women (21 deliveries) with congenital heart disease. The frequency of unplanned cesarean was 14 (7.9%) for the exposed group as compared with 12 (3.4%) in controls with an odds ratio of 2.33 (95% CI = 1.0.2-5.32, p = .045). This difference was accentuated in a sub-group of women with severe cardiac disease (15% vs. 4.2% in matched control group, p = .028). Seventy-one (31.6%) exposed women exhibited obstetric and cardiovascular complications during pregnancy as compared with 65 (14.4%) controls, p < .001. Twenty-five (13.9%) exposed women experienced postpartum complications versus 26 (7.5%) in the control group (p = .019). Maternal ICU admission occurred in 13 (7.3%) of the exposed group as compared with only 2 (0.6%) in controls (p < .001). CONCLUSIONS: Women with a background cardiac condition, particularly those with severe disease, are at a higher risk for an unplanned cesarean delivery and other peripartum complications as compared with matched healthy controls.

Erythrocyte volumetric measurements in imaging flow cytometry using simultaneous three-wavelength digital holographic microscopy.

We report a cross-talk free simultaneous three-wavelength digital holographic microscopy setup for spectroscopic imaging of biological cells during flow. The feasibility of the proposed measurement technique is demonstrated on erythrocytes, due to their unique morphology and dependency of hemoglobin (Hb) molecule absorption on wavelength. From the spectroscopic quantitative phase profiles of cells acquired during flow in a microfluidic device, we decoupled the refractive index and the physical thickness. We then used our quantitative phase imaging results to dynamically calculate the mean cell volume (MCV), mean corpuscular Hb concentration (MCHC), mean corpuscular Hb content (MCH) and sphericity index.

Holographic virtual staining of individual biological cells.

Many medical and biological protocols for analyzing individual biological cells involve morphological evaluation based on cell staining, designed to enhance imaging contrast and enable clinicians and biologists to differentiate between various cell organelles. However, cell staining is not always allowed in certain medical procedures. In other cases, staining may be time-consuming or expensive to implement. Staining protocols may be operator-sensitive, and hence may lead to varying analytical results, as well as cause artificial imaging artifacts or false heterogeneity. We present a deep-learning approach, called HoloStain, which converts images of isolated biological cells acquired without staining by holographic microscopy to their virtually stained images. We demonstrate this approach for human sperm cells, as there is a well-established protocol and global standardization for characterizing the morphology of stained human sperm cells for fertility evaluation, but, on the other hand, staining might be cytotoxic and thus is not allowed during human in vitro fertilization (IVF). After a training process, the deep neural network can take images of unseen sperm cells retrieved from holograms acquired without staining and convert them to their stainlike images. We obtained a fivefold recall improvement in the analysis results, demonstrating the advantage of using virtual staining for sperm cell analysis. With the introduction of simple holographic imaging methods in clinical settings, the proposed method has a great potential to become a common practice in human IVF procedures, as well as to significantly simplify and radically change other cell analyses and techniques such as imaging flow cytometry.

PhUn-Net: ready-to-use neural network for unwrapping quantitative phase images of biological cells.

We present a deep-learning approach for solving the problem of 2π phase ambiguities in two-dimensional quantitative phase maps of biological cells, using a multi-layer encoder-decoder residual convolutional neural network. We test the trained network, PhUn-Net, on various types of biological cells, captured with various interferometric setups, as well as on simulated phantoms. These tests demonstrate the robustness and generality of the network, even for cells of different morphologies or different illumination conditions than PhUn-Net has been trained on. In this paper, for the first time, we make the trained network publicly available in a global format, such that it can be easily deployed on every platform, to yield fast and robust phase unwrapping, not requiring prior knowledge or complex implementation. By this, we expect our phase unwrapping approach to be widely used, substituting conventional and more time-consuming phase unwrapping algorithms.

Comparison of clinical outcomes of influenza A and B at the 2017-2018 influenza season: a cohort study.

Influenza has significant morbidity and mortality. Some experts consider infection with influenza B as milder than that with influenza A. The objective of this study is to evaluate the outcomes of hospitalized patients with laboratory-confirmed influenza A or B in 2017-2018 influenza season. All hospitalized patients between October 2017 and April 2018 with laboratory-confirmed influenza A and B were included. The primary composite outcomes were pneumonia/myocarditis/encephalitis, mechanical ventilation, ICU admission, and 30-day mortality. Secondary outcomes were 30-/90-day mortality, length of hospital stay, and readmission rates. The study included 201 influenza A and 325 influenza B. For the primary composite outcome, no significant difference was demonstrated between influenza A and B. Rates of mortality were similar at 30 and 90 days. Influenza A had higher pneumonia rates and mechanical ventilation. On multivariate analysis, higher Charlson's score, hypoalbuminemia, and vasopressor use were associated with 30-day mortality, while infection with either influenza A or B was not. Influenza A was associated with higher pneumonia and mechanical ventilation rates. However, influenza B resulted with similar 30-day mortality rate as influenza A.

TOP-GAN: Stain-free cancer cell classification using deep learning with a small training set.

We propose a new deep learning approach for medical imaging that copes with the problem of a small training set, the main bottleneck of deep learning, and apply it for classification of healthy and cancer cell lines acquired by quantitative phase imaging. The proposed method, called transferring of pre-trained generative adversarial network (TOP-GAN), is hybridization between transfer learning and generative adversarial networks (GANs). Healthy cells and cancer cells of different metastatic potential have been imaged by low-coherence off-axis holography. After the acquisition, the optical path delay maps of the cells are extracted and directly used as inputs to the networks. In order to cope with the small number of classified images, we use GANs to train a large number of unclassified images from another cell type (sperm cells). After this preliminary training, we change the last layers of the network and design automatic classifiers for the correct cell type (healthy/primary cancer/metastatic cancer) with 90-99% accuracies, although small training sets of down to several images are used. These results are better in comparison to other classic methods that aim at coping with the same problem of a small training set. We believe that our approach makes the combination of holographic microscopy and deep learning networks more accessible to the medical field by enabling a rapid, automatic and accurate classification in stain-free imaging flow cytometry. Furthermore, our approach is expected to be applicable to many other medical image classification tasks, suffering from a small training set.

Flipping interferometry with doubled imaging area.

We present a new external off-axis holographic module that doubles the acquired complex wavefront field of view, based on using both holographic flipping and multiplexing. In contrast to previous designs, this design does not require spatial filtering (no pinhole or lenses) to create the reference beam externally. In addition, the overlap area between the fields of view, as well as the off-axis angle between the sample and reference beams, can be fully controlled. As we demonstrate experimentally, this approach is useful for quantitative phase microscopy of extended stationary and dynamic samples, such as cancer cells during rapid flow and beating cardiomyocytes.

Optimal spatial bandwidth capacity in multiplexed off-axis holography for rapid quantitative phase reconstruction and visualization: erratum.

We correct a typo that repeated itself in several equations. Our previous results and conclusions are unchanged.

Single-exposure full-field multi-depth imaging using low-coherence holographic multiplexing.

We present a new interferometric imaging approach that allows for multiple-depth imaging in a single acquisition, using off-axis low-coherence holographic multiplexing. This technique enables sectioned imaging of multiple slices within a thick sample, in a single image acquisition. Each slice has a distinct off-axis interference fringe orientation indicative of its axial location, and the camera acquires the multiplexed hologram containing the different slices at once. We demonstrate the proposed technique for amplitude and phase imaging of optically thick samples.

Simultaneous three-wavelength unwrapping using external digital holographic multiplexing module.

We present an external interferometric setup that is able to simultaneously acquire three wavelengths of the same sample instance without scanning or multiple exposures. This setup projects onto the monochrome digital camera three off-axis holograms with rotated fringe orientations, each from a different wavelength channel, without overlap in the spatial-frequency domain, and thus allows the full reconstruction of the three complex wavefronts from the three wavelength channels. We use this new setup for three-wavelength phase unwrapping, allowing phase imaging of thicker objects than possible with a single wavelength, but without the increased level of noise. We demonstrate the proposed technique for micro-channel profiling and label-free cell imaging.

Integral refractive index imaging of flowing cell nuclei using quantitative phase microscopy combined with fluorescence microscopy.

We suggest a new multimodal imaging technique for quantitatively measuring the integral (thickness-average) refractive index of the nuclei of live biological cells in suspension. For this aim, we combined quantitative phase microscopy with simultaneous 2-D fluorescence microscopy. We used 2-D fluorescence microscopy to localize the nucleus inside the quantitative phase map of the cell, as well as for measuring the nucleus radii. As verified offline by both 3-D confocal fluorescence microscopy and 2-D fluorescence microscopy while rotating the cells during flow, the nucleus of cells in suspension that are not during division can be assumed to be an ellipsoid. The entire shape of a cell in suspension can be assumed to be a sphere. Then, the cell and nucleus 3-D shapes can be evaluated based on their in-plain radii available from the 2-D phase and fluorescent measurements, respectively. Finally, the nucleus integral refractive index profile is calculated. We demonstrate the new technique on cancer cells, obtaining nucleus refractive index values that are lower than those of the cytoplasm, coinciding with recent findings. We believe that the proposed technique has the potential to be used for flow cytometry, where full 3-D refractive index tomography is too slow to be implemented during flow.

Six-pack off-axis holography.

We present a new holographic concept, named six-pack holography (6PH), in which we compress six off-axis holograms into a single multiplexed off-axis hologram without loss of magnification or resolution. The multiplexed hologram contains straight off-axis fringes with six different orientations, and can be generated optically or digitally. We show that since the six different complex wavefronts do not overlap in the spatial frequency domain, they can be fully reconstructed. 6PH allows more than 50% improvement in the spatial bandwidth consumption when compared to the best multiplexing method proposed so far. We expect the 6PH concept to be useful for a variety of applications, such as field-of-view multiplexing, wavelength multiplexing, temporal multiplexing, multiplexing for super-resolution imaging, and others.

Dynamic measurements of flowing cells labeled by gold nanoparticles using full-field photothermal interferometric imaging.

We present highly dynamic photothermal interferometric phase microscopy for quantitative, selective contrast imaging of live cells during flow. Gold nanoparticles can be biofunctionalized to bind to specific cells, and stimulated for local temperature increase due to plasmon resonance, causing a rapid change of the optical phase. These phase changes can be recorded by interferometric phase microscopy and analyzed to form an image of the binding sites of the nanoparticles in the cells, gaining molecular specificity. Since the nanoparticle excitation frequency might overlap with the sample dynamics frequencies, photothermal phase imaging was performed on stationary or slowly dynamic samples. Furthermore, the computational analysis of the photothermal signals is time consuming. This makes photothermal imaging unsuitable for applications requiring dynamic imaging or real-time analysis, such as analyzing and sorting cells during fast flow. To overcome these drawbacks, we utilized an external interferometric module and developed new algorithms, based on discrete Fourier transform variants, enabling fast analysis of photothermal signals in highly dynamic live cells. Due to the self-interference module, the cells are imaged with and without excitation in video-rate, effectively increasing signal-to-noise ratio. Our approach holds potential for using photothermal cell imaging and depletion in flow cytometry.