RESUMEN
Genes, expressed as sequences of nucleotides, are susceptible to mutations, some of which can lead to cancer. Machine learning and deep learning methods have emerged as vital tools in identifying mutations associated with cancer. Thyroid cancer ranks as the 5th most prevalent cancer in the USA, with thousands diagnosed annually. This paper presents an ensemble learning model leveraging deep learning techniques such as Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Bi-directional LSTM (Bi-LSTM) to detect thyroid cancer mutations early. The model is trained on a dataset sourced from asia.ensembl.org and IntOGen.org, consisting of 633 samples with 969 mutations across 41 genes, collected from individuals of various demographics. Feature extraction encompasses techniques including Hahn moments, central moments, raw moments, and various matrix-based methods. Evaluation employs three testing methods: self-consistency test (SCT), independent set test (IST), and 10-fold cross-validation test (10-FCVT). The proposed ensemble learning model demonstrates promising performance, achieving 96% accuracy in the independent set test (IST). Statistical measures such as training accuracy, testing accuracy, recall, sensitivity, specificity, Mathew's Correlation Coefficient (MCC), loss, training accuracy, F1 Score, and Cohen's kappa are utilized for comprehensive evaluation.
Asunto(s)
Aprendizaje Profundo , Mutación , Neoplasias de la Tiroides , Humanos , Neoplasias de la Tiroides/genética , Neoplasias de la Tiroides/diagnóstico , Progresión de la EnfermedadRESUMEN
BACKGROUND: Healthcare programs and insurance initiatives play a crucial role in ensuring that people have access to medical care. There are many benefits of healthcare insurance programs but fraud in healthcare continues to be a significant challenge in the insurance industry. Healthcare insurance fraud detection faces challenges from evolving and sophisticated fraud schemes that adapt to detection methods. Analyzing extensive healthcare data is hindered by complexity, data quality issues, and the need for real-time detection, while privacy concerns and false positives pose additional hurdles. The lack of standardization in coding and limited resources further complicate efforts to address fraudulent activities effectively. METHODOLGY: In this study, a fraud detection methodology is presented that utilizes association rule mining augmented with unsupervised learning techniques to detect healthcare insurance fraud. Dataset from the Centres for Medicare and Medicaid Services (CMS) 2008-2010 DE-SynPUF is used for analysis. The proposed methodology works in two stages. First, association rule mining is used to extract frequent rules from the transactions based on patient, service and service provider features. Second, the extracted rules are passed to unsupervised classifiers, such as IF, CBLOF, ECOD, and OCSVM, to identify fraudulent activity. RESULTS: Descriptive analysis shows patterns and trends in the data revealing interesting relationship among diagnosis codes, procedure codes and the physicians. The baseline anomaly detection algorithms generated results in 902.24 seconds. Another experiment retrieved frequent rules using association rule mining with apriori algorithm combined with unsupervised techniques in 868.18 seconds. The silhouette scoring method calculated the efficacy of four different anomaly detection techniques showing CBLOF with highest score of 0.114 followed by isolation forest with the score of 0.103. The ECOD and OCSVM techniques have lower scores of 0.063 and 0.060, respectively. CONCLUSION: The proposed methodology enhances healthcare insurance fraud detection by using association rule mining for pattern discovery and unsupervised classifiers for effective anomaly detection.
Asunto(s)
Minería de Datos , Fraude , Seguro de Salud , Humanos , Estados UnidosRESUMEN
This investigation aimed to synthesize poly(D,L-lactide) (PLA)-based fibrous scaffolds containing natural essential oils (i.e., linalool and citral) and determine their antimicrobial properties and cytocompatibility as a clinically viable cell-friendly disinfection strategy for regenerative endodontics. PLA-based fibrous scaffolds were fabricated via electrospinning with different concentrations of linalool and citral. The micromorphology and average diameter of the fibers was investigated through scanning electron microscopy (SEM). The chemical composition of the scaffolds was inferred by Fourier-transform infrared spectroscopy (FTIR). Antimicrobial efficacy against Enterococcus faecalis and Actinomyces naeslundii was also evaluated by agar diffusion and colony-forming units (CFU) assays. The scaffolds' cytocompatibility was determined using dental pulp stem cells (DPSCs). Statistical analyses were performed and the significance level was set at α = 5%. Linalool and citral's incorporation in the PLA fibrous scaffolds was confirmed in the FTIR spectra. SEM images indicate no morphological changes upon inclusion of the essential oils, except the reduced diameter of 40% linalool-laden fibers (p < 0.05). Importantly, significant antimicrobial properties were reported for citral-containing scaffolds for CFU/mL counts (p < 0.05), while only 20% and 40% linalool-laden scaffolds reduced CFU/mL (p < 0.05). Meanwhile, the inhibition halos were verified in a concentration-dependent manner for all monoterpenes-laden scaffolds. Citral- and linalool-laden PLA-based fibrous scaffolds showed acceptable cytocompatibility. The incorporation of natural monoterpenes did not alter the scaffolds' fibrous morphology, promoted antimicrobial action against endodontic pathogens, and preserved DPSCs viability. Linalool- and citral-laden electrospun scaffolds hold promise as naturally derived antimicrobial therapeutics for applications in regenerative endodontics.
Asunto(s)
Antiinfecciosos , Ciprofloxacina , Ciprofloxacina/química , Ciprofloxacina/farmacología , Monoterpenos/farmacología , Antiinfecciosos/farmacología , Poliésteres/farmacología , Andamios del Tejido/química , Ingeniería de Tejidos/métodosRESUMEN
[This corrects the article DOI: 10.1155/2022/3041811.].
RESUMEN
In the past few years, big data related to healthcare has become more important, due to the abundance of data, the increasing cost of healthcare, and the privacy of healthcare. Create, analyze, and process large and complex data that cannot be processed by traditional methods. The proposed method is based on classifying data into several classes using the data weight derived from the features extracted from the big data. Three important criteria were used to evaluate the study as well as to benchmark the current study with previous studies using a standard dataset.
Asunto(s)
Macrodatos , Atención a la Salud/estadística & datos numéricos , Aprendizaje Automático , Algoritmos , Biología Computacional , Bases de Datos Factuales/estadística & datos numéricos , Registros Electrónicos de Salud/estadística & datos numéricos , HumanosRESUMEN
We develop effective medical image classification techniques, with an emphasis on histopathology and magnetic resonance imaging (MRI). The trainer utilized the curriculum as a starting point for a set of data and a restricted number of samples, and we used it as a starting point for a set of data. As calibrating a machine learning model is difficult, we used alternative methods as unsupervised feature extracts or weight-conditioning factors for identifying pathological histology pictures. As a result, the pretrained models will be trained on 3-channel RGB pictures, while the MRI sample has more slices. To alter the working model using the MRI data, the convolutional neural network (CNN) must be fine-tuned. Pretrained models are placed and then used as feature snippets. However, there is a scarcity of well-done medical photos, making training machine learning models a difficult endeavor to begin with. In any case, data augmentation aids in the generation of sufficient training samples; however, it is unclear if data augmentation aids in the prediction of unknown data samples. As a result, we fine-tuned machine learning models without using any additional data. Furthermore, rather than utilizing a standard machine learning classifier for the MRI data, we created a unique CNN that uses both 3D shear descriptors and deep features as input. This custom network identifies the MRI sample after processing our representation of the characteristics from beginning to end. On the hidden MRI dataset, our bespoke CNN outperforms traditional machine learning. Our CNN model is less prone to overfitting as a result of this. Furthermore, we have given cutting-edge outcomes employing machine learning.
RESUMEN
OBJECTIVE: To explores cultural differences between generations of faculty and students in undergraduate medical education and to develop an educational framework for stakeholders involvement. METHODS: This is a prospective cross-sectional mixed method study. A survey was administered on students and faculty members to measure generational differences using Hofstede's dimensions of cultural orientation. The study took place at King Abdulaziz University-Faculty of Medicine, Jeddah, Saudi Arabia, on February 2015. Quantitative methods, descriptive statistics, and correlations and regression analyses were used in data analysis. In addition, qualitative data from focus groups were used to explain findings obtained from the survey. RESULTS: A total of 736 respondents were surveyed (129 faculty members and 607 medical students). Faculty members across all generations shared the same cultural values of low power distance and masculinity and high uncertainty avoidance, long-term orientation and collectivism. Advanced medical students showed higher power distance, collectivism, masculinity and long-term orientation than faculty members; junior medical students have higher masculinity and lower uncertainty avoidance and collectivism. CONCLUSION: This study explains both the cultural gap between Saudi and Western medical students as well as between Saudi generations, demonstrating the need for customized curricular revisions.
Asunto(s)
Cultura , Educación de Pregrado en Medicina , Docentes/psicología , Relaciones Intergeneracionales , Estudiantes de Medicina/psicología , Estudios Transversales/métodos , Humanos , Modelos Lineales , Estudios Prospectivos , Arabia Saudita , Encuestas y CuestionariosRESUMEN
OBJECTIVES: To evaluate the utility of eye exam simulators in the training and assessment of family medicine residents for screening diabetic retinopathy (DR) utilizing direct ophthalmoscopy (DO). METHODS: This prospective, single arm, cross-sectional study was conducted at King AbdulAziz University Hospital, Jeddah, Kingdom of Saudi Arabia in April 2013, wherein the final year family medicine residents of the Saudi Board family medicine training program, underwent a practical session on DO using an eye exam simulator. The cognitive and motor skills of the participating family residents in performing DO, and their competency at diagnosing DR was assessed before, and after a practical session with the eye simulator. RESULTS: A total of 14 out of total 20 final year residents consented to join the study. Of these, 57.1% were females. A total of 42.9% (6/14) showed initial motor skill competency, and 35.7% showed cognitive skill competency to diagnose DR. Before the session on the eye simulator, merely 7.1% of the residents expressed confidence in performing DO. After the practical session, 78.6% (11/14) showed motor, and 64.3% (9/13) showed cognitive skill competency, in diagnosing DR. A total of 50% were adequately confident in performing DO. A total of 71.4% (10/14) of the residents preferred learning DO via simulation practical sessions than clinical rotation in ophthalmology clinics. CONCLUSION: Eye exam simulators are good tools in learning and assessment of DO skills leading to significant improvement in the efficiency and confidence of family physicians in screening for DR.
Asunto(s)
Retinopatía Diabética/diagnóstico , Educación de Postgrado en Medicina/métodos , Medicina Familiar y Comunitaria/educación , Oftalmoscopía , Simulación de Paciente , Competencia Clínica , Estudios Transversales , Humanos , Tamizaje Masivo , Estudios ProspectivosRESUMEN
PURPOSE: To compare the efficacies of punctal plug insertion and Botulinum toxin injection in dry eye disease not responding to topical medications. MATERIALS AND METHODS: A non-controlled randomized clinical trial of two parallel groups of 60 dry eye patients seen in the clinic not responding to topical medications were divided into two groups. One group received punctal plugs and the other group received Botulinum toxin injections to prevent lacrimal tear drainage. RESULTS: Of a total of 36 patients with a mean age of 44.5 years who received punctal plugs, 50% of them experienced improvements in the clinical manifestations of their disease. 12/36 (33.3%) developed plug extrusion, and 6/36 (16.7%) patients developed conjunctival erosions with irritation that necessitated plug removal within one week of insertion. A total of 24 patients with a mean age of 47.5 years received injections of Botulinum toxin. Of these, 83.3% had improvement in all of the clinical manifestations of dry eye. 4/24 (16.7%) had no improvement in the degrees to which they experienced foreign body sensations, 33.3% reported shampoo entering the eye while showering. All of the patients who received Botulinum toxin injections were satisfied with the results of their treatment, whereas only 72.3% of the patients who received punctal plugs were satisfied with their results. CONCLUSION: Botulinum neurotoxin A injections can be a very good alternative to punctal plugs in improving the clinical manifestations of dry eye disease They are associated with the development of fewer and milder complications and with higher levels of patient satisfaction.
RESUMEN
PURPOSE: Aimed to evaluate normal volume of the lacrimal gland in patients of different age groups and race. METHODS: All MRI studies of the brain that were done between June 2012 and April 2013 were examined. Lacrimal glands were identified using fat-saturated fluid-attenuated inversion recovery (FLAIR) images, and the volumes were calculated using TeraRecon iNtuition viewer. Volumes for the right and left lacrimal glands were recorded for persons of different age groups and race, and the results were compared with those of a randomly selected group of patients who had undergone the same calculation method using CT of the brain, orbit, or paranasal sinuses. RESULTS: The authors included 998 lacrimal glands of 499 patients. The mean volumes for the right and left lacrimal glands were 0.770 and 0.684 cm, respectively. Lacrimal glands were larger in women; the largest volumes were observed during the second decade of life. Mean volumes also varied with race: 0.840 cm in Asians, 0.790 cm in Africans, 0.760 cm in Indians, and 0.710 cm in Middle Easterners. The consultant neuroradiologist and the intern showed excellent agreement for measurements of lacrimal gland volume. No significant difference was observed between lacrimal gland measurements method on MRI and CT. CONCLUSION: Lacrimal gland volume varies according to age, gender, race, and laterality. Measurements with MRI using fat-saturated FLAIR images and TeraRecon iNtuition viewer software are reliable, accurate, and can be used by junior staff with less radiation exposure to patients.
Asunto(s)
Envejecimiento/fisiología , Aparato Lagrimal/anatomía & histología , Imagen por Resonancia Magnética , Grupos Raciales , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Niño , Preescolar , Femenino , Humanos , Lactante , Masculino , Persona de Mediana Edad , Factores Sexuales , Adulto JovenRESUMEN
PURPOSE: We aimed to compare the outcomes of primary external dacryocystorhinostomy and silicone tube with anterior and posterior mucosal flap anastomosis, versus dacryocystorhinostomy and silicone intubation with anterior mucosal flap anastomosis. METHODS: We utilized the electronic databases PubMed, EMBASE, Ovid, Cochrane Central Register of Controlled Trials, and MEDLINE® to find articles related to external dacryocystorhinostomy. For inclusion in this meta-analysis, we isolated prospective and retrospective comparative studies of adult patients with acquired nasolacrimal duct obstruction, or chronic dacryocystitis, who had undergone primary external dacryocystorhinostomy and silicone intubation with anterior and posterior flap anastomosis; versus primary dacryocystorhinostomy and silicone intubation with anterior flap anastomosis. The minimum follow-up period for each study was 4 months. RESULTS: We identified and analyzed seven studies. Overall, dacryocystorhinostomy with anterior and posterior flap anastomosis was performed on 368 eyes, while primary external dacryocystorhinostomy with anterior flap anastomosis was performed on 397 eyes. There was no significant difference in the success rates of both techniques (risk ratio: 0.987; 95% confidence interval 0.946-1.030). CONCLUSION: For patients with acquired nasolacrimal duct obstruction or chronic dacryocystitis, there was no significant difference in the resolution of epiphora, and patency of the lacrimal system, between those who underwent external dacryocystorhinostomy with anterior and posterior mucosal flap anastomosis, and those who had dacryocystorhinostomy with anterior flap anastomosis.
RESUMEN
AIM: To determine the prevalence of various causes of tearing among patients referred to an oculoplastic clinic. MATERIALS AND METHODS: A prospective study on all patients seen in an oculoplastic clinic with a chief complaint of tearing. The cause of tearing was determined on the basis of the anatomical location of the primary etiology. RESULTS: This study included 357 patients with a mean age 53.9 years. Punctal stenosis was the most common etiology, affecting 37.8% of the patients. Among patients with punctual stenosis, 63.4% were women over 50-year-old (P = 0.001); 55.6% had tearing for less than 6 months (P = 0.038), and all of them had associated chronic blepharitis. The remaining study participants had dry eye with reflex tearing (27.7%), nasolacrimal duct obstruction (10.1%), canalicular obstruction (4.2%), entropion or ectropion (3.4%), pterygium (1.7%), megalo-caruncle (1.7%), and functional tearing (1.7%). CONCLUSION: The outcomes of this study indicate the most common cause of tearing is punctal pathology. Therefore, slit lamp evaluation with careful attention to the punctum is warranted in all patients with tearing.
Asunto(s)
Síndromes de Ojo Seco/complicaciones , Obstrucción del Conducto Lagrimal/complicaciones , Conducto Nasolagrimal/patología , Lágrimas/metabolismo , Adulto , Blefaritis/complicaciones , Femenino , Humanos , Masculino , Persona de Mediana Edad , Estudios Prospectivos , Adulto JovenRESUMEN
Punctal stenosis is a frequent source of patients referral to the otoplasty clinic and the search for a procedure that can permanently eliminate epiphora without disturbing the normal lacrimal system anatomy and physiology started centuries ago and continues today. The following article summarizes the reported procedures in the English literature in the acquired punctal stenosis with a description of techniques, success rates, and potential complications with the goal of identifying the most effective treatment strategy based on the current knowledge available.
Asunto(s)
Enfermedades del Aparato Lagrimal/terapia , Aparato Lagrimal/patología , Constricción Patológica/diagnóstico , Constricción Patológica/terapia , Humanos , Enfermedades del Aparato Lagrimal/diagnóstico , StentsRESUMEN
PURPOSE: To examine the relationship between dyslipidemia and the severity of meibomian gland dysfunction (MGD). METHODS: A prospective cohort study of 132 subjects with and 104 without MGD were recruited. A correlation between serum fasting lipids and MGD severity was performed. RESULTS: Mean age for all candidates was 49.4 years; and 57% were women. In all, 42.9% had no MGD, 14.8% had grade 1 MGD, 17.4% had grade 2 MGD, and 23.7% had grade 3 MGD. High cholesterol was found in 37.1% of grade 1 MGD, 43.9% of grade 2 MGD, and 50% of grade 3 MGD. High triglyceride was found in 5.7% of grade 1, 14.6% of grade 2, and 39.3% of grade 3 patients. High low-density lipoprotein was found in 17.1% of grade 1, 29.3% of grade 2, and 35.7% of grade 3 patients. The mean age of the control group was 41.2 years; and 55.4% were women. High cholesterol was found in 42.3%, triglyceride in 7.7%, low-density lipoprotein in 23.1%, low high-density lipoprotein in 3.8%, and high high-density lipoprotein in 3.8%. CONCLUSIONS: Although the presence of MGD does not have any correlation with dyslipidemia, the prevalence of high triglyceride and low-density lipoprotein levels increases with the increasing severity of MGD. This might highlight the significance of monitoring fasting serum lipids due to its association with the potential correlation with the progression of MGD.
Asunto(s)
Dislipidemias/fisiopatología , Enfermedades de los Párpados/clasificación , Enfermedades de los Párpados/fisiopatología , Glándulas Tarsales/fisiopatología , Adolescente , Adulto , Colesterol/sangre , Estudios de Cohortes , Femenino , Humanos , Lipoproteínas HDL/sangre , Lipoproteínas LDL/sangre , Masculino , Persona de Mediana Edad , Estudios Prospectivos , Triglicéridos/sangre , Adulto JovenRESUMEN
PURPOSE: Identifying the peri-ocular anthropometric measurements characteristic of Saudi Arabian eyes. METHODS: A prospective, cohort, hospital-based study. RESULTS: Measurements were made on 668 subjects (mean age 33.8 years; 58.7% female). The horizontal palpebral aperture was 30.1 ± 2.9 mm (mean ± SD), vertical palpebral aperture was 10.1 ± 0.85 mm, upper lid skin fold height was 3.6 ± 1.9 mm, upper lid crease height was 9.6 ± 0.8 mm, eyebrow height was 10.2 ± 2.7 mm, and intercanthal distance was 32 ± 2.7 mm. There was a statistically significant correlation between gender and eyebrow height (P = 0.001) and gender and horizontal palpebral aperture (P = 0.016), but no significant correlations were noted between any measurement and age. CONCLUSIONS: Saudi Arabian eyes are unique in exhibiting a higher upper lid skin fold, higher lid crease.
RESUMEN
PURPOSE: To estimate the prevalence of dry eye disease in the normal non-complaining population. METHODS: Prospective systematic random sampling study of 251 subjects who accompanied patients with appointments to the eye clinic. Interviewers administered a dry eye symptoms and risk factor questionnaire. Tear film break up time, fluorescein corneal staining and Schirmer's test were performed. Slit lamp examination to evaluate the lid margins, Meibomian glands and ocular surface structures was also performed. RESULTS: Dry eye was diagnosed in 234 (93.2%) subjects on the basis of presence of one or more symptoms occurring often or most of the time, together with one or more of the following signs: tear film break up time < or = 10 seconds, fluorescein corneal staining > or = grade 1 and Schirmer test score < or = 5 mm. There was no statistically significant association between dry eye with advancing age or gender. Blepharitis was detected in 215 (91.9%) of the dry eye cases. Smoking was found to be the second most common risk factor as 18.8% of the dry eye cases were smokers. Sicca syndrome was found in 24.4% of the subjects. CONCLUSION: Dry eye is very prevalent disease. Blepharitis was found to be very common among dry eye cases. There was no statistically significant association between dry eye and age or gender in our study population.
Asunto(s)
Síndromes de Ojo Seco/epidemiología , Adolescente , Adulto , Distribución por Edad , Anciano , Niño , Síndromes de Ojo Seco/diagnóstico , Femenino , Fluorofotometría , Humanos , Masculino , Persona de Mediana Edad , Prevalencia , Estudios Prospectivos , Factores de Riesgo , Arabia Saudita/epidemiología , Distribución por Sexo , Encuestas y Cuestionarios , Lágrimas/química , Adulto JovenRESUMEN
PURPOSE: To estimate the prevalence of punctal stenosis among patients visiting the general ophthalmology clinic for routine checkup. DESIGN: Prospective, observational case series. MATERIALS AND METHODS: A total of 682 patients were evaluated for evidence of punctal stenosis from May to November 2008. Any associated findings from clinical examination were recorded. RESULTS: As many as 54.3% (370/682) of the candidates had punctal stenosis. The prevalence is associated significantly with increasing age (p=.001), and no gender predilection was found. It was due to chronic blepharitis in 97% (359/370), entropion in 1.4% (5/370) and unknown causes in 1.6% (6/370) of the patients. As many as 58.1% (215/370) did not have subjective or objective evidence of epiphora, and all of them had a tear film breakup time of less than 10 seconds and positive corneal fluorescein staining. CONCLUSION: Punctal stenosis is a common finding among patients presenting for routine eye checkup. It increases with advancing age, and the most common predisposing factor is chronic blepharitis. A significant number of patients can be asymptomatic as they have concurrent dry eye disease. Surgical intervention is not recommended unless the patient is symptomatic after treating any associated blepharitis and dry eye disease.