Purpose
With the increasing adoption of artificial intelligence (AI) in various domains, including healthcare, there is growing acceptance and interest in consulting AI models to provide medical ...information and advice. This study aimed to evaluate the accuracy of ChatGPT’s responses to practice quiz questions designed for otolaryngology board certification and decipher potential performance disparities across different otolaryngology subspecialties.
Methods
A dataset covering 15 otolaryngology subspecialties was collected from an online learning platform funded by the German Society of Oto-Rhino-Laryngology, Head and Neck Surgery, designed for board certification examination preparation. These questions were entered into ChatGPT, with its responses being analyzed for accuracy and variance in performance.
Results
The dataset included 2576 questions (479 multiple-choice and 2097 single-choice), of which 57% (
n
= 1475) were answered correctly by ChatGPT. An in-depth analysis of question style revealed that single-choice questions were associated with a significantly higher rate (
p
< 0.001) of correct responses (
n
= 1313; 63%) compared to multiple-choice questions (
n
= 162; 34%). Stratified by question categories, ChatGPT yielded the highest rate of correct responses (
n
= 151; 72%) in the field of allergology, whereas 7 out of 10 questions (
n
= 65; 71%) on legal otolaryngology aspects were answered incorrectly.
Conclusion
The study reveals ChatGPT’s potential as a supplementary tool for otolaryngology board certification preparation. However, its propensity for errors in certain otolaryngology areas calls for further refinement. Future research should address these limitations to improve ChatGPT’s educational use. An approach, with expert collaboration, is recommended for the reliable and accurate integration of such AI models.
Lagophthalmos is the incomplete closure of the eyelids posing the risk of corneal ulceration and blindness. Lagophthalmos is a common symptom of various pathologies. We aimed to program a ...convolutional neural network to automatize lagophthalmos diagnosis. From June 2019 to May 2021, prospective data acquisition was performed on 30 patients seen at the Department of Plastic, Hand, and Reconstructive Surgery at the University Hospital Regensburg, Germany (IRB reference number: 20-2081-101). In addition, comparative data were gathered from 10 healthy patients as the control group. The training set comprised 826 images, while the validation and testing sets consisted of 91 patient images each. Validation accuracy was 97.8% over the span of 64 epochs. The model was trained for 17.3 min. For training and validation, an average loss of 0.304 and 0.358 and a final loss of 0.276 and 0.157 were noted. The testing accuracy was observed to be 93.41% with a loss of 0.221. This study proposes a novel application for rapid and reliable lagophthalmos diagnosis. Our CNN-based approach combines effective anti-overfitting strategies, short training times, and high accuracy levels. Ultimately, this tool carries high translational potential to facilitate the physician's workflow and improve overall lagophthalmos patient care.
Abstract ChatGPT has garnered attention as a multifaceted AI chatbot with potential applications in medicine. Despite intriguing preliminary findings in areas such as clinical management and patient ...education, there remains a substantial knowledge gap in comprehensively understanding the chances and limitations of ChatGPT’s capabilities, especially in medical test-taking and education. A total of n = 2,729 USMLE Step 1 practice questions were extracted from the Amboss question bank. After excluding 352 image-based questions, a total of 2,377 text-based questions were further categorized and entered manually into ChatGPT, and its responses were recorded. ChatGPT’s overall performance was analyzed based on question difficulty, category, and content with regards to specific signal words and phrases. ChatGPT achieved an overall accuracy rate of 55.8% in a total number of n = 2,377 USMLE Step 1 preparation questions obtained from the Amboss online question bank. It demonstrated a significant inverse correlation between question difficulty and performance with r s = -0.306; p < 0.001, maintaining comparable accuracy to the human user peer group across different levels of question difficulty. Notably, ChatGPT outperformed in serology-related questions (61.1% vs. 53.8%; p = 0.005) but struggled with ECG-related content (42.9% vs. 55.6%; p = 0.021). ChatGPT achieved statistically significant worse performances in pathophysiology-related question stems. (Signal phrase = “what is the most likely/probable cause”). ChatGPT performed consistent across various question categories and difficulty levels. These findings emphasize the need for further investigations to explore the potential and limitations of ChatGPT in medical examination and education.
Injuries to our skin trigger a cascade of spatially- and temporally-synchronized healing processes. During such endogenous wound repair, the role of fibroblasts is multifaceted, ranging from the ...activation and recruitment of innate immune cells through the synthesis and deposition of scar tissue to the conveyor belt-like transport of fascial connective tissue into wounds. A comprehensive understanding of fibroblast diversity and versatility in the healing machinery may help to decipher wound pathologies whilst laying the foundation for novel treatment modalities. In this review, we portray the diversity of fibroblasts and delineate their unique wound healing functions. In addition, we discuss future directions through a clinical-translational lens.
Background The search for an ideal bone substitute in reconstructive surgery has led to the exploration of various materials, with hydroxyapatite (HaP) emerging as a promising candidate due to its ...biocompatibility, osteoconductive properties, and structural similarity to human bone. Despite its potential, there is a paucity of data on the long-term safety and efficacy of HaP in facial skeletal reconstruction and augmentation. Methods We conducted a systematic review following PRISMA 2020 guidelines, searching PubMed/MEDLINE, Google Scholar, CENTRAL, and Web of Science databases for studies on hydroxyapatite facial implants in reconstruction and augmentation. Results Our search yielded 12 studies that met our inclusion criteria, encompassing 74 patients treated with HaP implants for various indications including facial fractures/defects, aesthetic facial balancing, and after tumor resection. The studies reported on outcomes such as implant integration, complications, aesthetic results, and patient satisfaction, with a general trend indicating positive outcomes for the use of HaP in facial reconstruction. Conclusion Hydroxyapatite appears to be a viable and effective material for facial skeletal reconstruction and augmentation, offering benefits in terms of biocompatibility, osteoconductivity, and patient outcomes. However, limitations such as low mechanical strength and the need for further research on long-term safety and efficacy were identified. This review underscores the potential of HaP in craniofacial surgery while highlighting areas for future investigation.
Abstract
Objective
The goal of this study was to evaluate the efficacy of machine learning (ML) techniques in predicting survival for chordoma patients in comparison with the standard Cox ...proportional hazards (CoxPH) model.
Methods
Using a Surveillance, Epidemiology, and End Results database of consecutive newly diagnosed chordoma cases between January 2000 and December 2018, we created and validated three ML survival models as well as a traditional CoxPH model in this population-based cohort study. Randomly, the dataset was divided into training and validation datasets. Tuning hyperparameters on the training dataset involved a 1000-iteration random search with fivefold cross-validation. Concordance index (C-index), Brier score, and integrated Brier score were used to evaluate the performance of the model. The receiver operating characteristic (ROC) curves, calibration curves, and area under the ROC curves (AUC) were used to assess the reliability of the models by predicting 5- and 10-year survival probabilities.
Results
A total of 724 chordoma patients were divided into training (
n
= 508) and validation (
n
= 216) cohorts. Cox regression identified nine significant prognostic factors (
p
< 0.05). ML models showed superior performance over CoxPH model, with DeepSurv having the highest C-index (0.795) and the best discrimination for 5- and 10-year survival (AUC 0.84 and 0.88). Calibration curves revealed strong correlation between DeepSurv predictions and actual survival. Risk stratification by DeepSurv model effectively discriminated high- and low-risk groups (
p
< 0.01). The optimized DeepSurv model was implemented into a web application for clinical use that can be found at
https://hust-chengp-ml-chordoma-app-19rjyr.streamlitapp.com/
.
Conclusion
ML algorithms based on time-to-event results are effective in chordoma prediction, with DeepSurv having the best discrimination performance and calibration.
Malignancies represent a persisting worldwide health burden. Tumor treatment is commonly based on surgical and/or non-surgical therapies. In the recent decade, novel non-surgical treatment strategies ...involving monoclonal antibodies (mAB) and immune checkpoint inhibitors (ICI) have been successfully incorporated into standard treatment algorithms. Such emerging therapy concepts have demonstrated improved complete remission rates and prolonged progression-free survival compared to conventional chemotherapies. However, the in-toto surgical tumor resection followed by reconstructive surgery oftentimes remains the only curative therapy. Breast cancer (BC), skin cancer (SC), head and neck cancer (HNC), and sarcoma amongst other cancer entities commonly require reconstructive surgery to restore form, aesthetics, and functionality. Understanding the basic principles, strengths, and limitations of mAB and ICI as (neo-) adjuvant therapies and treatment alternatives for resectable or unresectable tumors is paramount for optimized surgical therapy planning. Yet, there is a scarcity of studies that condense the current body of literature on mAB and ICI for BC, SC, HNC, and sarcoma. This knowledge gap may result in suboptimal treatment planning, ultimately impairing patient outcomes. Herein, we aim to summarize the current translational endeavors focusing on mAB and ICI. This line of research may serve as an evidence-based fundament to guide targeted therapy and optimize interdisciplinary anti-cancer strategies.
The transient receptor potential vanilloid 4 (TRPV4) specifically functions as a mechanosensitive ion channel and is responsible for conveying changes in physical stimuli such as mechanical stress, ...osmotic pressure, and temperature. TRPV4 enables the entry of cation ions, particularly calcium ions, into the cell. Activation of TRPV4 channels initiates calcium oscillations, which trigger intracellular signaling pathways involved in a plethora of cellular processes, including tissue repair. Widely expressed throughout the body, TRPV4 can be activated by a wide array of physicochemical stimuli, thus contributing to sensory and physiological functions in multiple organs. This review focuses on how TRPV4 senses environmental cues and thereby initiates and maintains calcium oscillations, critical for responses to organ injury, tissue repair, and fibrosis. We provide a summary of TRPV4-induced calcium oscillations in distinct organ systems, along with the upstream and downstream signaling pathways involved. In addition, we delineate current animal and disease models supporting TRPV4 research and shed light on potential therapeutic targets for modulating TRPV4-induced calcium oscillation to promote tissue repair while reducing tissue fibrosis.
Facial reconstruction and augmentation, integral in facial plastic surgery, address defects related to trauma, tumors infections, and congenital skeletal deficiencies. Aesthetic considerations, ...including age-related facial changes, involve volume loss and diminished projection, often associated with predictable changes in the facial skeleton. Autologous, allogeneic, and alloplastic implants are used to address these concerns. Autologous materials such as bone, cartilage, and fat, while longstanding options, have limitations, including unpredictability and resorption rates. Alloplastic materials, including metals, polymers, and ceramics, offer alternatives. Metals like titanium are biocompatible and used primarily in fracture fixation. Polymers, such as silicone and polyethylene, are widely used, with silicone presenting migration, bony resorption, and visibility issues. Polyethylene, particularly porous polyethylene (MedPor), was reported to have one of the lowest infection rates while it becomes incorporated into the host. Polyether-ether-ketone (PEEK) exhibits mechanical strength and compatibility with imaging modalities, with custom PEEK implants providing stable results. Acrylic materials, like poly-methylmethacrylate (PMMA), offer strength and is thus mostly used in the case of cranioplasty. Bioceramics, notably hydroxyapatite (HaP), offer osteoconductive and inductive properties, and HaP granules demonstrate stable volume retention in facial aesthetic augmentation. Combining HaP with other materials, such as PLA, may enhance mechanical stability. 3D bioprinting with HaP-based bioinks presents a promising avenue for customizable and biocompatible implants. In conclusion, various materials have been used for craniofacial augmentation, but none have definitively demonstrated superiority. Larger randomized controlled trials are essential to evaluate short- and long-term complications comprehensively, potentially revolutionizing facial balancing surgery.