RESUMEN
PURPOSE: To investigate the capability of ChatGPT for forecasting the conversion from ocular hypertension (OHT) to glaucoma based on the Ocular Hypertension Treatment Study (OHTS). DESIGN: Retrospective case-control study. PARTICIPANTS: A total of 3008 eyes of 1504 subjects from the OHTS were included in the study. METHODS: We selected demographic, clinical, ocular, optic nerve head, and visual field (VF) parameters 1 year before glaucoma development from the OHTS participants. Subsequently, we developed queries by converting tabular parameters into textual format based on both eyes of all participants. We used the ChatGPT application program interface (API) to automatically perform ChatGPT prompting for all subjects. We then investigated whether ChatGPT can accurately forecast conversion from OHT to glaucoma based on various objective metrics. MAIN OUTCOME MEASURE: Accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and weighted F1 score. RESULTS: ChatGPT4.0 demonstrated an accuracy of 75%, AUC of 0.67, sensitivity of 56%, specificity of 78%, and weighted F1 score of 0.77 in predicting conversion to glaucoma 1 year before onset. ChatGPT3.5 provided an accuracy of 61%, AUC of 0.62, sensitivity of 64%, specificity of 59%, and weighted F1 score of 0.63 in predicting conversion to glaucoma 1 year before onset. CONCLUSIONS: The performance of ChatGPT4.0 in forecasting development of glaucoma 1 year before onset was reasonable. The overall performance of ChatGPT4.0 was consistently higher than ChatGPT3.5. Large language models (LLMs) hold great promise for augmenting glaucoma research capabilities and enhancing clinical care. Future efforts in creating ophthalmology-specific LLMs that leverage multimodal data in combination with active learning may lead to more useful integration with clinical practice and deserve further investigations.
RESUMEN
BACKGROUND: In this paper, we present an automated method for article classification, leveraging the power of large language models (LLMs). OBJECTIVE: The aim of this study is to evaluate the applicability of various LLMs based on textual content of scientific ophthalmology papers. METHODS: We developed a model based on natural language processing techniques, including advanced LLMs, to process and analyze the textual content of scientific papers. Specifically, we used zero-shot learning LLMs and compared Bidirectional and Auto-Regressive Transformers (BART) and its variants with Bidirectional Encoder Representations from Transformers (BERT) and its variants, such as distilBERT, SciBERT, PubmedBERT, and BioBERT. To evaluate the LLMs, we compiled a data set (retinal diseases [RenD] ) of 1000 ocular disease-related articles, which were expertly annotated by a panel of 6 specialists into 19 distinct categories. In addition to the classification of articles, we also performed analysis on different classified groups to find the patterns and trends in the field. RESULTS: The classification results demonstrate the effectiveness of LLMs in categorizing a large number of ophthalmology papers without human intervention. The model achieved a mean accuracy of 0.86 and a mean F1-score of 0.85 based on the RenD data set. CONCLUSIONS: The proposed framework achieves notable improvements in both accuracy and efficiency. Its application in the domain of ophthalmology showcases its potential for knowledge organization and retrieval. We performed a trend analysis that enables researchers and clinicians to easily categorize and retrieve relevant papers, saving time and effort in literature review and information gathering as well as identification of emerging scientific trends within different disciplines. Moreover, the extendibility of the model to other scientific fields broadens its impact in facilitating research and trend analysis across diverse disciplines.
RESUMEN
PURPOSE: The aim of this study was to assess the capabilities of ChatGPT-4.0 and ChatGPT-3.5 for diagnosing corneal eye diseases based on case reports and compare with human experts. METHODS: We randomly selected 20 cases of corneal diseases including corneal infections, dystrophies, and degenerations from a publicly accessible online database from the University of Iowa. We then input the text of each case description into ChatGPT-4.0 and ChatGPT-3.5 and asked for a provisional diagnosis. We finally evaluated the responses based on the correct diagnoses, compared them with the diagnoses made by 3 corneal specialists (human experts), and evaluated interobserver agreements. RESULTS: The provisional diagnosis accuracy based on ChatGPT-4.0 was 85% (17 correct of 20 cases), whereas the accuracy of ChatGPT-3.5 was 60% (12 correct cases of 20). The accuracy of 3 corneal specialists compared with ChatGPT-4.0 and ChatGPT-3.5 was 100% (20 cases, P = 0.23, P = 0.0033), 90% (18 cases, P = 0.99, P = 0.6), and 90% (18 cases, P = 0.99, P = 0.6), respectively. The interobserver agreement between ChatGPT-4.0 and ChatGPT-3.5 was 65% (13 cases), whereas the interobserver agreement between ChatGPT-4.0 and 3 corneal specialists was 85% (17 cases), 80% (16 cases), and 75% (15 cases), respectively. However, the interobserver agreement between ChatGPT-3.5 and each of 3 corneal specialists was 60% (12 cases). CONCLUSIONS: The accuracy of ChatGPT-4.0 in diagnosing patients with various corneal conditions was markedly improved than ChatGPT-3.5 and promising for potential clinical integration. A balanced approach that combines artificial intelligence-generated insights with clinical expertise holds a key role for unveiling its full potential in eye care.
Asunto(s)
Inteligencia Artificial , Enfermedades de la Córnea , Humanos , Córnea , Enfermedades de la Córnea/diagnóstico , Bases de Datos FactualesRESUMEN
INTRODUCTION: The purpose of this study was to evaluate the capabilities of large language models such as Chat Generative Pretrained Transformer (ChatGPT) to diagnose glaucoma based on specific clinical case descriptions with comparison to the performance of senior ophthalmology resident trainees. METHODS: We selected 11 cases with primary and secondary glaucoma from a publicly accessible online database of case reports. A total of four cases had primary glaucoma including open-angle, juvenile, normal-tension, and angle-closure glaucoma, while seven cases had secondary glaucoma including pseudo-exfoliation, pigment dispersion glaucoma, glaucomatocyclitic crisis, aphakic, neovascular, aqueous misdirection, and inflammatory glaucoma. We input the text of each case detail into ChatGPT and asked for provisional and differential diagnoses. We then presented the details of 11 cases to three senior ophthalmology residents and recorded their provisional and differential diagnoses. We finally evaluated the responses based on the correct diagnoses and evaluated agreements. RESULTS: The provisional diagnosis based on ChatGPT was correct in eight out of 11 (72.7%) cases and three ophthalmology residents were correct in six (54.5%), eight (72.7%), and eight (72.7%) cases, respectively. The agreement between ChatGPT and the first, second, and third ophthalmology residents were 9, 7, and 7, respectively. CONCLUSIONS: The accuracy of ChatGPT in diagnosing patients with primary and secondary glaucoma, using specific case examples, was similar or better than senior ophthalmology residents. With further development, ChatGPT may have the potential to be used in clinical care settings, such as primary care offices, for triaging and in eye care clinical practices to provide objective and quick diagnoses of patients with glaucoma.
RESUMEN
One of the most common oral diseases affecting people wearing dentures is chronic atrophic candidiasis or denture stomatitis (DS). The aim of the paper is to provide an update on the pathogenesis, presentation, and management of DS in general dental practice settings. A comprehensive review of the literature published in the last ten years was undertaken using multiple databases, including PubMed via MEDLINE, EMBASE, and Scopus. The eligible articles were analyzed to identify evidence-based strategies for the management of DS. Despite its multifactorial nature, the leading cause of DS is the development of oral Candida albicans biofilm, which is facilitated by poor oral and denture hygiene, long-term denture wear, ill-fitting dentures, and the porosity of the acrylic resin in the dentures. DS affects between 17 and 75% of the population wearing dentures, with a slight predominance in elderly females. The mucosal denture surfaces and posterior tongue are the common sites of DS, and the affected areas exhibit erythema, the swelling of the palatal mucosa and edema. Oral and denture hygiene protocols, adjusting or re-fabricating poorly adapting dentures, smoking cessation, avoiding nocturnal denture wear, and the administration of topical or systemic antifungals are the mainstay of management. Alternate treatments such as microwave disinfection, phytomedicine, photodynamic therapy, and incorporation of antifungals and nanoparticles into denture resins are being evaluated for the treatment of DS but require further evidence before routine use in clinical practice. In summary, DS is the most common oral inflammatory lesion experienced by denture wearers. Most patients with DS can be managed in general dental practice settings. Effective management by general dental practitioners may be supported by a thorough understanding of the pathogenesis, the recognition of the clinical presentation, and an awareness of contemporary treatment strategies.
Asunto(s)
Candidiasis Bucal , Estomatitis Subprotética , Estomatitis , Femenino , Humanos , Anciano , Estomatitis Subprotética/epidemiología , Estomatitis Subprotética/etiología , Estomatitis Subprotética/patología , Dentaduras/efectos adversos , Antifúngicos , Odontólogos , Rol Profesional , Candidiasis Bucal/complicaciones , Candida albicansRESUMEN
Health sector institutes of Pakistan can play a pivotal part in improving the status of health sciences. This can be achieved by facilitating research and innovation facilities. It is a need of the day to emphasize academicians and institutional administrations to take keen interest in this regard. Knowledge of the present research and development conditions within higher education institutions may help in policy development and fund allocations at the required levels. Therefore, the objective of this study is to evaluate the status of research and development within dental Institutes of Pakistan. A 30 itemed questionnaire was e mailed/posted to all institutional heads of all registered and recognized dental institutes of Pakistan. Response rate was 62% showing lack of administrational interest. Insufficient infrastructure, inadequate research planning, execution and intellectual property management was recorded. It can be concluded that higher education dental institutions of Pakistan are in need of deeper administrational and educational input to gear up the progress of health sector in this direction.
Asunto(s)
Administración Financiera , Educación en Odontología , Humanos , Pakistán , Investigación , Facultades de Odontología , Encuestas y CuestionariosRESUMEN
Domestic violence is a complex social issue worldwide that includes a wide range of physical, sexual, psychological, economic, or emotional trauma to a child or adult. A large proportion of domestic violence cases remain unreported or undocumented. Dentists can play an important role in identifying and reporting these cases, but no such local study is available assessing the dental practitioners' attitudes and knowledge of evaluating physical abuse in Pakistan. The objective of this study was to assess the knowledge and practices of dental practitioners of Pakistan about domestic violence. This cross-sectional study was carried out over 2 months, among 330 dentists across Pakistan, selected by convenience sampling technique. Data was collected via a pre-validated online questionnaire, filled anonymously after taking informed consent. The survey questionnaire collected data about dentists' demographics, awareness, and experiences about domestic violence cases via close-ended questions. Only 10.6% of participating dentists received formal training in the management of domestic violence cases. Approximately 55% of participants knew that physical abuse should be reported in all circumstances; however, half of them could not accurately identify the legal authorities where suspected cases should be reported. Only 20% of the participating dentists had ever suspected a case of physical abuse and 30% of those actually reported it to legal authorities. Participants characterized fear of anger from relatives as the most significant barrier toward reporting suspected cases. The analysis revealed that Pakistan's dentists lack adequate knowledge regarding domestic violence in terms of identification, relevant physical signs/symptoms, and social indicators. Dentists of Pakistan had insufficient knowledge about the identification, management, and reporting of domestic violence cases. However, formal training and dentists' qualification were positively associated with overall awareness and practices regarding domestic violence case management.
Asunto(s)
Maltrato a los Niños , Violencia Doméstica , Adulto , Actitud del Personal de Salud , Niño , Estudios Transversales , Odontólogos , Conocimientos, Actitudes y Práctica en Salud , Humanos , Pakistán , Rol Profesional , Encuestas y CuestionariosRESUMEN
Nasal septal defects may present with no clinical symptoms to dryness, nasal obstruction, pain, mucosal injury, crusting, epistaxis, rhinorrhea, nasal twang in speech, hyposmia, and breathing difficulties. Prosthetic rehabilitation of these defects may lead to improvement in these conditions. This case report describes the construction of a custom-made two-piece, magnet-retained nasal prosthesis fabricated in heat-cured acrylic resin. Intra-nasal and extra-nasal alginate impressions were splinted with soft plaster. Sequential model pouring was done for convenient access to the complicated intra-nasal anatomy. Two individual nasal stent waxups, containing two magnets with opposing poles facing each other, were well adapted to their respective medial nasal walls and anterior retentive rounded tips. Waxups were processed in heat-cured acrylic resin and delivered after finishing and polishing. Patient's symptoms were relieved, while maintaining the nasal patency. Such inexpensive method with a tissue-friendly material may prove beneficial for rehabilitation of larger nasal septal defects. Key Words: Nasal septal defects, Rehabilitation, Acrylic resin, Prosthesis.
Asunto(s)
Imanes , Tabique Nasal , Humanos , Tabique Nasal/cirugía , Diseño de Prótesis , Implantación de Prótesis , StentsRESUMEN
OBJECTIVE: Glaucoma is the second leading cause of blindness worldwide. Glaucomatous progression can be easily monitored by analyzing the degeneration of retinal ganglion cells (RGCs). Many researchers have screened glaucoma by measuring cup-to-disc ratios from fundus and optical coherence tomography scans. However, this paper presents a novel strategy that pays attention to the RGC atrophy for screening glaucomatous pathologies and grading their severity. METHODS: The proposed framework encompasses a hybrid convolutional network that extracts the retinal nerve fiber layer, ganglion cell with the inner plexiform layer and ganglion cell complex regions, allowing thus a quantitative screening of glaucomatous subjects. Furthermore, the severity of glaucoma in screened cases is objectively graded by analyzing the thickness of these regions. RESULTS: The proposed framework is rigorously tested on publicly available Armed Forces Institute of Ophthalmology (AFIO) dataset, where it achieved the F1 score of 0.9577 for diagnosing glaucoma, a mean dice coefficient score of 0.8697 for extracting the RGC regions and an accuracy of 0.9117 for grading glaucomatous progression. Furthermore, the performance of the proposed framework is clinically verified with the markings of four expert ophthalmologists, achieving a statistically significant Pearson correlation coefficient of 0.9236. CONCLUSION: An automated assessment of RGC degeneration yields better glaucomatous screening and grading as compared to the state-of-the-art solutions. SIGNIFICANCE: An RGC-aware system not only screens glaucoma but can also grade its severity and here we present an end-to-end solution that is thoroughly evaluated on a standardized dataset and is clinically validated for analyzing glaucomatous pathologies.
Asunto(s)
Aprendizaje Profundo , Glaucoma , Técnicas de Diagnóstico Oftalmológico , Glaucoma/diagnóstico por imagen , Humanos , Presión Intraocular , Células Ganglionares de la Retina , Tomografía de Coherencia ÓpticaRESUMEN
Glaucoma is a progressive and deteriorating optic neuropathy that leads to visual field defects. The damage occurs as glaucoma is irreversible, so early and timely diagnosis is of significant importance. The proposed system employs the convolution neural network (CNN) for automatic segmentation of the retinal layers. The inner limiting membrane (ILM) and retinal pigmented epithelium (RPE) are used to calculate cup-to-disc ratio (CDR) for glaucoma diagnosis. The proposed system uses structure tensors to extract candidate layer pixels, and a patch across each candidate layer pixel is extracted, which is classified using CNN. The proposed framework is based upon VGG-16 architecture for feature extraction and classification of retinal layer pixels. The output feature map is merged into SoftMax layer for classification and produces probability map for central pixel of each patch and decides whether it is ILM, RPE, or background pixels. Graph search theory refines the extracted layers by interpolating the missing points, and these extracted ILM and RPE are finally used to compute CDR value and diagnose glaucoma. The proposed system is validated using a local dataset of optical coherence tomography images from 196 patients, including normal and glaucoma subjects. The dataset contains manually annotated ILM and RPE layers; manually extracted patches for ILM, RPE, and background pixels; CDR values; and eventually final finding related to glaucoma. The proposed system is able to extract ILM and RPE with a small absolute mean error of 6.03 and 5.56, respectively, and it finds CDR value within average range of ± 0.09 as compared with glaucoma expert. The proposed system achieves average sensitivity, specificity, and accuracies of 94.6, 94.07, and 94.68, respectively.
Asunto(s)
Glaucoma , Glaucoma/diagnóstico por imagen , Humanos , Redes Neurales de la Computación , Disco Óptico , Retina/diagnóstico por imagen , Tomografía de Coherencia ÓpticaRESUMEN
Faculty feedback program (FFP) at CMH Multan Institute of Medical Sciences (CIMS) was conducted for obtaining feedback for basic medical sciences faculty and evaluated to highlight its weaknesses for future improvement. The evaluation design was utilization-focused evaluation (UFE) keeping in mind its two essential elements. First element is the primary intended users (PIU) of the evaluation, namely the college faculty and students which were clearly identified and personally engaged to investigate intended use of the evaluation. Second element required the evaluator to ensure that the intended use of evaluation by PIU guide all other decisions made about the evaluation process. It was a mixed method study (qualitative and quantitative methods both) conducted from August 2018 to August 2019 in CIMS Multan with IRB approval following the steps of UFE. The whole program evaluation was conducted in two parts - first part constituted the 2018 manual FFP evaluation that provided suggestions for a FFP conducted in 2019 online. In step 2 the 2019 online FFP was evaluated again forming basis for future recommendations. Hence the PIUs response was recorded twice in the evaluation cycle - initially after the manual 2018 basic science FFP (response rate: 53%) - after which based on our findings a report was generated and recommendations suggested which were implemented in the 2019 online FFP and response observed again (response rate: 85.7%) to complete the evaluation cycle. Open-end questions were asked from faculty (qualitative analysis) with three themes emerging regarding FFP procedure, questionnaire and timing. An acknowledgement of shift of FFP procedure from manual (2018) to online system (2019) was observed in which faculty praised the ease (72.2%), confidentiality (66.6%), anonymity (50%) and transparency (33.3%) of the online system compared to manual FFP, which was reported to be a rather tense experience (83%). Regarding questionnaire, 38% faculty members reported feedback questions asked from students to be vague and 66.6% claimed that the timing was inappropriate and should have been end of academic year. When asked for suggestions for improvement in 2018 FFP, 72% faculty suggested training students on providing feedback and making the procedure user friendly (83%). Student response regarding both feedback was obtained online by a survey with closed ended questions (quantitative study). Fifty-three percent college students were satisfied with the online FFP giving an average rating of 3.2 to the software user interface and 85% affirmed that using the online software aided in providing anonymous responses helping them provide candid feedback. Seventy-five percent students agreed that online feedback system in 2019 had streamlined the feedback process and made it more efficient compared to the paper-based manual survey of 2018. After evaluating 2019 online FFP, few suggestions were recommended for future FFP including obtaining formative as well as summative faculty feedback, supplementing feedback with teacher's self-assessment/pen picture and incorporating 360 multi-source feedback.
RESUMEN
This paper presents the data set of Optic coherence tomography (OCT) and fundus Images of human eye. The OCT machine TOPCON'S 3D OCT-1000 camera is employed to acquire the images. The dataset is comprised of 50 images which includes control and glaucomatous images. For each OCT Image there is a corresponding fundus Image with annotation. Cup to disc ratio (CDR) values annotated by glaucoma specialists through fundus Images are provided in excel file. OCT images are optic nerve head (ONH) centred. Manually annotation is performed for the delineation of the Inner Limiting Membrane (ILM) Layer and Retinal pigmented epithelium (RPE) layer with the help of ophthalmologist. The data is valuable for the development of automated algorithm for glaucoma diagnosis.
RESUMEN
Construction of a maxillectomy obturator for any surgical defect requires optimum retention, stability and obturation of defect. In the following case a closed hollow bulb obturator was constructed while utilizing surveying and neutral zone impression technique. After insertion, soft liner was applied to record functional impression of the surgical defect. The obturator was resurfaced with heat cure acrylic to improve the outcome. Patient was able to masticate adequately and speak comprehensively. Patient's resonance, speech, retention and stability were markedly improved. Follow-up was done weekly in first month, fortnightly for the next 2 months then after every 3 months. In succeeding years it will be once every year.
Asunto(s)
Retención de Prótesis Dentales , Maxilar/cirugía , Enfermedades Maxilares/cirugía , Prótesis Maxilofacial , Osteomielitis/cirugía , Obturadores Palatinos , Humanos , Masculino , Persona de Mediana EdadRESUMEN
OBJECTIVE: To estimate the amount of shift in position of the neutral zone and the centre of alveolar ridge crest in different edentulous periods. STUDY DESIGN: Observational study. PLACE AND DURATION OF STUDY: The study was carried out on edentulous patients reporting in Prosthodontics Department of Lahore Medical and Dental College, Lahore, from August 2006 to December 2008. METHODOLOGY: Patients with edentulous period for at least 6 months exhibiting normal range of maximal mouth opening (40-50 mm) and normal temporomandibular joint movements were included and allocated into two groups, according to period of edentulism. Patient with any intra oral soft tissue or bony pathology and reduced intermaxillary space were excluded. The neutral zone was clinically recorded for all patients with impression compound. The shift between neutral zone and ridge crest in different edentulous periods was analyzed radio graphically and compared statistically. RESULTS: In longer edentulous period (> 2 years), neutral zone was lingually shifted by an average of 1.06 mm in anterior, premolar and molar regions. CONCLUSION: Neutral zone may be lingually shifted in relation to alveolar ridge crest in patients with prolonged edentulous period. This may help in arranging the teeth according to the clinical situation.