RESUMEN
This work develops a robust classifier for a COVID-19 pre-screening model from crowdsourced cough sound data. The crowdsourced cough recordings contain a variable number of coughs, with some input sound files more informative than the others. Accurate detection of COVID-19 from the sound datasets requires overcoming two main challenges (i) the variable number of coughs in each recording and (ii) the low number of COVID-positive cases compared to healthy coughs in the data. We use two open datasets of crowdsourced cough recordings and segment each cough recording into non-overlapping coughs. The segmentation enriches the original data without oversampling by splitting the original cough sound files into non-overlapping segments. Splitting the sound files enables us to increase the samples of the minority class (COVID-19) without changing the feature distribution of the COVID-19 samples resulted from applying oversampling techniques. Each cough sound segment is transformed into six image representations for further analyses. We conduct extensive experiments with shallow machine learning, Convolutional Neural Network (CNN), and pre-trained CNN models. The results of our models were compared to other recently published papers that apply machine learning to cough sound data for COVID-19 detection. Our method demonstrated a high performance using an ensemble model on the testing dataset with area under receiver operating characteristics curve = 0.77, precision = 0.80, recall = 0.71, F1 measure = 0.75, and Kappa = 0.53. The results show an improvement in the prediction accuracy of our COVID-19 pre-screening model compared to the other models.
Asunto(s)
COVID-19/diagnóstico , Tos/clasificación , COVID-19/epidemiología , Tos/virología , Aprendizaje Profundo , Humanos , Aprendizaje Automático , Tamizaje Masivo/métodos , Redes Neurales de la Computación , Curva ROC , SARS-CoV-2/aislamiento & purificación , Sensibilidad y Especificidad , Sonido , Espectrografía del Sonido/métodos , Tomografía Computarizada por Rayos X/métodosRESUMEN
OBJECTIVES: Normal hearing system is an essential factor for accurate production of speech segments. It seems that cochlear implant prosthesis helps children with hearing impairment to speak more accurately than before receiving prosthesis. The current research aimed to compare the vowel duration in school-aged children with cochlear implants and that in children with normal hearing. Additionally, the performance of girls and boys in two groups were investigated. METHODS: A cross-sectional and descriptive-analytical study was carried out to compare the vowel duration in 9- to 12-year-old children with cochlear implant and those with normal hearing. Participants were 52 children who were matched by age and sex. We asked the children to read the target words with each word including one vowel and then participants' voice samples were recorded. Then, vowel duration was measured using Praat software. Finally, the vowel duration was compared between the two groups running independent sample t-test. The level of significance was (P < 0.05). RESULTS: There was no statistically significant difference observed between the two groups in the mean values of the vowel duration for the six Persian vowels (P > 0.05). Also, no significant difference was found between boys and girls in the mean value of the vowel duration between the two groups (P > 0.05). CONCLUSION: Persian vowels in school-aged children with cochlear implant and with typical hearing are produced with similar durations. This finding is probably related to the increased duration of using prosthesis in this age range and speech mode used to measure vowel duration in the present study.
Asunto(s)
Implantación Coclear , Pérdida Auditiva/cirugía , Fonética , Acústica del Lenguaje , Trastornos del Habla/etiología , Estudios de Casos y Controles , Niño , Implantación Coclear/instrumentación , Implantes Cocleares , Estudios Transversales , Femenino , Pérdida Auditiva/complicaciones , Pérdida Auditiva/psicología , Humanos , Masculino , Factores Sexuales , Trastornos del Habla/diagnóstico , Trastornos del Habla/cirugía , Medición de la Producción del Habla , Factores de Tiempo , Resultado del TratamientoRESUMEN
OBJECTIVES: Since the pragmatic skills of hearing-impaired Persian-speaking children have not yet been investigated particularly through story retelling, this study aimed to evaluate some pragmatic abilities of normal-hearing and hearing-impaired children using a story retelling test. METHODS: 15 normal-hearing and 15 profound hearing-impaired 7-year-old children were evaluated using the story retelling test with the content validity of 89%, construct validity of 85%, and reliability of 83%. Three macro structure criteria including topic maintenance, event sequencing, explicitness, and four macro structure criteria including referencing, conjunctive cohesion, syntax complexity, and utterance length were assessed. The test was performed with live voice in a quiet room where children were then asked to retell the story. The tasks of the children were recorded on a tape, transcribed, scored and analyzed. RESULTS: In the macro structure criteria, utterances of hearing-impaired students were less consistent, enough information was not given to listeners to have a full understanding of the subject, and the story events were less frequently expressed in a rational order than those of normal-hearing group (P < 0.0001). Regarding the macro structure criteria of the test, unlike the normal-hearing students who obtained high scores, hearing-impaired students failed to gain any scores on the items of this section. CONCLUSIONS: These results suggest that Hearing-impaired children were not able to use language as effectively as their hearing peers, and they utilized quite different pragmatic functions.
Asunto(s)
Pérdida Auditiva Sensorineural/fisiopatología , Desarrollo del Lenguaje , Niño , Comunicación , Estudios Transversales , Femenino , Audición , Humanos , Lenguaje , Pruebas del Lenguaje , Lingüística/métodos , Masculino , Persia , Personas con Deficiencia Auditiva , Reproducibilidad de los ResultadosRESUMEN
OBJECTIVES: The aim of this study was to evaluate the psychometric features of the Persian version of the Autism Behavior Checklist (ABC). METHOD: The International Quality of Life Assessment (IQOLA) approach was used to translate the English ABC into Persian. A total sample of 184 parents of children including 114 children with autism disorder (mean age =7.21, SD =1.65) and 70 typically developing children (mean age = 6.82, SD =1.75) completed the ABC. Internal consistency, test-retest reliability, concurrent and discriminant validity, and cut-off score were assessed. RESULTS: The results of this study revealed that the Persian version of the ABC has an acceptable degree of internal consistency (.73). Test-retest comparisons using interclass correlation confirmed the instrument's time stability (.83). The instrument's concurrent validity with Gilliam Autism Rating Scale (GARS) was verified; the correlation between total scores was .94. In the discriminant validity, the autism group had significantly higher scores compared to the normal group. Receiver Operating Characteristic (ROC) analysis revealed that individuals with total scores below 25 are less likely to be in the autism group. CONCLUSION: The Persian version of the ABC can be used as an initial screening tool in clinical contexts.
RESUMEN
Four new types of carboxylate-ferroxane nanoparticles, namely; maleate ferroxane (MF), fumarateferroxane (FF), para-amino benzoate ferroxane (PABF) and para-hydroxy benzoate ferroxane (PHBF) were synthesized, characterized and used for lead removal from aqueous solutions. Lepidocrocite nanoparticles were also synthesized and characterized asa precursorforcarboxylate-ferroxanes. FTIR, SEM and DLS analysis characterized the synthesized samplesand final Pb(II) concentration were analysed using inductively coupled plasma atomic emission spectrometer. Performance evaluation of the nanoparticlesin adsorption process was achieved using Taguchi experimental design. Variables in adsorption process were initial pH, contact time, adsorbent dose, adsorbent typeand initial concentration of Pb(2+) ions. The initial Pb(II) concentration was the most influential factor in the adsorption process among the five factors. Adsorption of lead was performed through two possible mechanisms; ion exchange and complex formation. Maleate ferroxane performed the best lead removal efficiency among the four types of ferroxane nanostructures studied. The adsorption kinetic data described well with a pseudo-second-order model and the equilibrium data fitted well to the Frendlich isotherm.
Asunto(s)
Compuestos de Hierro/química , Plomo/química , Nanopartículas/química , Contaminantes Químicos del Agua/química , Purificación del Agua/métodos , Adsorción , Intercambio Iónico , Cinética , Contaminación Química del Agua/estadística & datos numéricos , Purificación del Agua/estadística & datos numéricosRESUMEN
BACKGROUND: Biomechanical factors, such as spinal deformities can result in balance control disorders. OBJECTIVES: The purpose of this study was to examine the effect of bracing on static and dynamic balance control of hyperkyphotic female adolescents. STUDY DESIGN: Clinical trial. METHODS: A force platform was employed to record center of pressure (COP) parameters. Ten adolescents undergoing Milwaukee brace for hyperkyphosis and 14 normal subjects participated in the study. The COP data were collected with and without brace immediately on first day and after 120 days of continuous brace wear. RESULTS: No significant difference was found in dynamic and static balance tests with and without brace on the first day (P > 0.05). After 120 days, the values of COP displacement in functional reach to the right and left for the hyperkyphotic adolescents when performing without brace enhanced significantly compared to the first day. The forward reach distance was not significantly different between the normal and hyperkyphotic subjects (P = 0.361); however, hyperkyphotic participants had significantly smaller reach distance in the functional reach to the right (21.88 vs. 25.56 cm) and left (17.04 vs. 21.25 cm). CONCLUSION: It might be concluded that bracing had a possible effect on improvement of dynamic balance performance, because the subjects could reach the target in dynamic reach tests with higher displacement in sagittal plane without losing their balance control. Clinical relevance Little is known about the biomechanical aspects of brace wear in individuals with hyperkyphosis. This study investigated balance differences between the healthy and hyperkyphotic individuals, and outcomes of Milwaukee brace wear. It might provide some new insight into the conservative treatment of hyperkyphosis for clinicians and researchers.
Asunto(s)
Tirantes , Equilibrio Postural/fisiología , Enfermedad de Scheuermann/fisiopatología , Enfermedad de Scheuermann/terapia , Adolescente , Fenómenos Biomecánicos , Niño , Femenino , Humanos , Presión , Factores de Tiempo , Resultado del Tratamiento , Caminata/fisiología , Soporte de Peso/fisiologíaRESUMEN
UNLABELLED: Tinnitus is a debilitating condition that is widespread yet difficult to successfully diagnose and treat. This symptom can seriously affect the individual's life quality. OBJECTIVES: The aim of current study was to compose and validate a Persian version of the Tinnitus Handicap Inventory (THI-P). MATERIALS AND METHODS: The linguistic validation of the original version of THI into Persian version (THI-P) included translation, back translation and data gathering. The THI-P was administered to 112 tinnitus subjects. Age, gender, medical history and tinnitus characteristics were recorded as baseline information. All participants complained of chronic unilateral or bilateral subjective idiopathic tinnitus lasting for at least 6 months before consulting about their tinnitus. RESULTS: There was no significant difference between gender, age, hearing impairment and total score and subscales of THI-P. Pearson product-moment correlations revealed adequate test-retest reliability for the THI-P (r = 0.96). Cronbach's-alpha coefficient indicated adequate internal stability of the THI-P (r= 0.943), with a total item correction varying between r=0.939 and r=0.944, indicating its reproducibility. CONCLUSION: The present study proved the internal consistency/ coherency of the Persian version of THI (THI-P). This provides satisfactory application in clinical/research environments.
Asunto(s)
Evaluación de la Discapacidad , Lingüística , Calidad de Vida , Encuestas y Cuestionarios/normas , Acúfeno/diagnóstico , Acúfeno/psicología , Adolescente , Adulto , Anciano , Emociones , Femenino , Humanos , Irán , Lenguaje , Masculino , Persona de Mediana Edad , Reproducibilidad de los Resultados , Adulto JovenRESUMEN
The objective of this study was to compare the effects of wearing an insole with toe separator and night splint on hallux valgus and intermetatarsal angles and also on the intensity of pain in patients suffering from painful hallux valgus deformity. Subjects in this study consisted of 30 female patients aged 19 - 45 years (mean 27.83 +/- 8.91) who were divided into two groups. The first group received the insole and toe separator and the second group received night splint. Hallux valgus angle and intermetatarsal angle were radiographically measured before and after a 3-month study period. Foot pain intensity was assessed by 10 cm Visual Analogue Scale before and after intervention. After statistical analysis the reduction of pain was significant in the first group (p < 0.05) whereas in the second group no significant difference was obtained. The hallux valgus angle and intermetatarsal angle decreased in both groups; however, the reduction was not significant. According to the results of this study, using night splint seems to have no effect on painful hallux valgus deformity. On the other hand, although the insole with toe separator significantly decreased the pain intensity in these patients and was a good option for pain reduction, it was not effective in improvement of the great toe angles.