ABSTRACT
Machine learning-based Parkinson's disease (PD) speech diagnosis is a current research hotspot. However, existing methods use each corpus sample as the base unit for modeling. Since different corpus samples within the same subject have different sensitive speech features, it is difficult to obtain unified and stable sensitive speech features (diagnostic markers) that reflect the pathology of the whole subject. Therefore, this study aims at compressing the corpus samples within the subject to facilitate the search for diagnostic markers with high diagnostic accuracy. A two-step sample compression module (TSCM) can solve the problem above. It includes two major parts: sample pruning module (SPM) and sample fuzzy clustering mechanism (SFCMD). Based on stacking multiple TSCMs, a multilayer sample compression module (MSCM) is formed to obtain multilayer compression samples. After that, simultaneous sample/feature selection mechanism (SS/FSM) is designed for feature selection. Based on the multilayer compression samples processed by MSCM and SS/FSM, a novel ensemble learning algorithm (EMSFE) is designed with sparse fusion ensemble learning mechanism (SFELM). The proposed EMSFE is validated by visualization of extracted features and performance comparison with related algorithms. The experimental results show that the proposed algorithm can effectively extract the stable diagnostic markers by compressing the corpus samples within the subject. Furthermore, based on LOSO cross validation, the proposed algorithm with extreme learning machine (ELM) classifier can achieve the accuracy of 92.5%, 93.75% and 91.67% on three datasets, respectively. The proposed EMSFE can extract unified and stable sensitive features that accurately reflect the overall pathology of the subject, which can better meet the requirements of clinical applications.The code and datasets can be found in: https://github.com/wywwwww/EMSFE-supplementary-material.git.
Subject(s)
Data Compression , Parkinson Disease , Humans , Parkinson Disease/diagnosis , Speech , Algorithms , Machine LearningABSTRACT
The convergence of China's digital economy and green finance holds great significance for fostering a sustainable and high-quality developmental path. However, existing studies have not explored the coupling coordination development between these two crucial subsystems. To bridge this gap, this paper employs a modified coupling coordination degree (CCD) model to assess and affirm the coupling coordination degree between the digital economy and green finance across 30 provinces in China from 2015-2021. Based on degree results, provinces are classified into three clusters by using K-means and hierarchical clustering algorithm. Our findings unveil that the current level of coupling coordination development in China is at a primary coordination stage. Although regional disparities significantly exist, the overall level of coordination remains steadily increasing, with the eastern region outperforming the western region. Additionally, we determine that the COVID-19 pandemic's disruption on the coupling coordination development of these systems has been limited. This research sheds light on the evolution of coupling systems and offers practical recommendations for strengthening the coordinated development of the digital economy and green finance.
Subject(s)
COVID-19 , Humans , COVID-19/epidemiology , Pandemics , China , Algorithms , Cluster Analysis , Economic DevelopmentABSTRACT
A sustainable and pleasant environment is deemed to offer various positive externalities such as scenic, visual and behavioral archetypes and patterns exhibiting in various forms. Such a scenario can significantly relieve households from many psychological and personal complications such as depression. Depression has aroused great concerns in recent years due to its personal and social burdens and unforeseeable damage. Many studies have explored the effects of air pollution caused by traditional fuel consumption on depression. However, limited evidence is available on how household non-traditional fuel choices affect depression. Based on a nationally representative dataset collected from China Family Panel Studies (CFPS) in 2012, this paper employs an endogenous switching regression (ESR) model and an endogenous switching probit (ESP) model to address the endogenous issue and to estimate the treatment effects of non-traditional fuel choices on depression in rural China. The empirical results show that non-traditional fuel users have significantly lower Epidemiologic Studies Depression Scale (CES-D) scores, indicating non-traditional fuel users face a lower risk of depression. Compared to solid fuels, employing non-traditional fuels will lead to a 3.659 reduction in depression score or decrease the probability of depression by 8.2%. In addition, the results of the mechanism analysis show that household non-traditional fuel choices affect depression by reducing the probability of physical discomfort and chronic disease. This study provides new insight into understanding the impact of air pollution in the house on depression and how to avoid the risk of depression in rural China effectively.
Subject(s)
Air Pollution, Indoor , Air Pollution , Humans , Air Pollution, Indoor/analysis , Cooking , Family Characteristics , China/epidemiologyABSTRACT
In recent years, fast and precise lumbar vertebrae segmentation technology have been one of the important topics in practical medical diagnosis and assisted medical surgery scenarios. However, most of the existing vertebral segmentation methods are based on the whole vertebral scanning space, which, up to some extent, is difficult to meet the clinical needs because of its large time complexity and space complexity. Different from the existing methods, for better exploiting the real time of lumbar segmentation, meanwhile ensuring its accuracy, a novel 3D lumbar vertebrae location and segmentation method based on the fusion envelope of 2D hybrid visual projection images (LVLS-HVPFE) is proposed in this paper. Firstly, a 2D projection location network of lumbar vertebrae based on fusion envelope of hybrid visual projection images is proposed to obtain the accurate location of each intact lumbar vertebra in the coronal and sagittal planes respectively. Among them, the envelope dataset of hybrid visual projection images (EDHVPs) is established to enhance feature representation and suppress interference in the process of dimensionality reduction projection. An envelope deep neural network (EDNN) for EDHVPs is established to effectively obtain depth envelope structure features with three different sizes, and a dimension reduction fusion mechanism is proposed to increase the sampling density of features and ensure the mutual independence of multi-scale features. Secondly, the concept of 3D localization criterion with spatial dimensionality reduction (SDRLC) is first proposed as a measure to verify the distribution consistency of vertebral targets in coronal and sagittal planes of a CT scan, and it can directionally guide for the subsequent 3D lumbar segmentation. Thirdly, under the condition of 3D positioning subspace of each intact lumbar vertebra, the 3D segmentation network based on spatial orientation guidance is used to realize an accurate segmentation of corresponding lumbar vertebra. The proposed method is evaluated with three representative datasets, and experimental results show that it is superior to the state-of-the-art methods.
Subject(s)
Lumbar Vertebrae , Neural Networks, Computer , Lumbar Vertebrae/diagnostic imaging , Tomography, X-Ray Computed/methods , Image Processing, Computer-Assisted/methodsABSTRACT
Arable land abandonment has been occurring in China in recent years. Although an emerging number of studies have investigated the impacts of urbanization and labor migration on arable land abandonment, little is known about what roles agricultural outsourcing services play in reducing arable land abandonment. Based on the data from the China Labor-force Dynamics Survey (CLDS) in both 2014 and 2016, this study employs a two-stage least squares method to address the potential endogeneity issue and sheds some light on the impact of agricultural outsourcing services for controlling disease and pests in arable land abandonment in China. The empirical results show that disease and pest control outsourcing services (DPCOS) significantly decrease the size of household-level arable land abandonment by 6.59% on average. More specifically, DPCOS mainly reduce the arable land abandonment in regions with the labor shortages, while this does not lead to a significant decrease in arable land abandonment in regions characterized by poor soil quality and steep slopes. Therefore, we may conclude that DPCOS could contribute to the reuse of farmlands suitable for cultivation and the exit of farmlands unsuitable for cultivation.
Subject(s)
Outsourced Services , Agriculture , China , Pest Control , Soil , UrbanizationABSTRACT
OBJECTIVES: To identify the differences in hearing, anatomical success rate, functional success rate, and complications between over-under tympanoplasty and medial tympanoplasty procedures. METHODS: The clinical data of patients with tympanic membrane perforation repaired by medial tympanoplasty between January 2011 and December 2016 and by over-under tympanoplasty between January 2017 and December 2020 were retrospectively analyzed. We evaluated the differences between medial tympanoplasty and over-under tympanoplasty. RESULTS: The overall success rate of over-under tympanoplasty was higher than that of medial tympanoplasty (90.76% vs 81.31%). In large perforations, the success rate of over-under tympanoplasty was higher than that of medial tympanoplasty (89.80% vs 71.43%). There was no statistically significant difference in the success rate between the two treatment groups for moderate perforations. Furthermore, there was no statistically significant difference in the incidence of complications between the two groups (P = .2637). CONCLUSIONS: Over-under tympanoplasty is more suitable for large perforations of the tympanic membrane and has a higher success rate as compared to medial tympanoplasty.
ABSTRACT
A comprehensive survey of the development trends, trend evolution, and spatial non-equilibrium characteristics of the intelligent smart medical industry in the Yangtze River Economic Belt could provide significant policy implications for optimizing the spatial layout of the integrated development of the smart medical industry in this region. Using the Criteria Importance Though Intercriteria Correlation objective evaluation method for a study period from 2016 to 2020, 11 provinces and cities along the Yangtze River Economic Belt were quantitatively evaluated in relation to the development of the smart medical industry. Accordingly, the application of exploratory spatial data analysis, the kernel density estimation, and the Dagum Gini coefficient and its decomposition method were used to comprehensively evaluate the trends in the Yangtze River Economic Belt's smart medical industry regarding trend evolution and unbalanced spatial characteristics. The overall level of development of the smart medical industry in the Yangtze River Economic Belt was not good. It showed an increasing spatial pattern from the western inland to eastern coastal regions. The development of the artificial intelligence industry in the Yangtze River Economic Belt showed a positive spatial autocorrelation with significant "spatial spillover effects." The local agglomeration mode was mainly high (a high cluster). In addition, industrial development showed a multi-polarization trend. Although the degree of spatial disequilibrium in the artificial intelligence industry development along the Yangtze River Economic Belt has decreased in recent years, the degree of spatial disequilibrium remains significant.
Subject(s)
Artificial Intelligence , Rivers , Industry , Cities , Economic DevelopmentABSTRACT
The overuse of agrochemicals in greenhouse production system has aroused high concerns in China. Existing studies have investigated the status and determinants of agrochemicals overuse for greenhouse vegetables whereas little is known about whether the agrochemicals are allocated efficiently from economic perspective. We use a translog production function and the inputs and outputs data of vegetable production in 34 Chinese cities during 2004-2017 to calculate agrochemicals allocation efficiency for both open-field and greenhouse vegetables. We find that the agrochemicals are allocated inefficiently due to overuse for both open-field and greenhouse vegetables, whereas the overuse degree of chemical fertilizer used in greenhouse vegetables is lower than that of open-field vegetables during a growing duration. In addition, we also find that the application levels of agrochemicals for greenhouse vegetables per mu (15 mu = 1 hectare) are higher than those of open-field vegetables, but the application levels of agrochemicals for per kilogram greenhouse vegetables are significantly lower. We conclude that the overuse of agrochemicals in greenhouse production system may attribute to the year-round production of greenhouse vegetables induced by economic incentives. Therefore, reducing the number of production rotations may be an effective method to alleviate the overuse of agrochemicals in greenhouse vegetables.
ABSTRACT
Speech diagnosis of Parkinson's disease (PD) as a non-invasive and simple diagnosis method is particularly worth exploring. However, the number of samples of speech-based PD is relatively small, and there exist discrepancies in the distribution between subjects. In order to solve the two problems, a novel unsupervised two-step sparse transfer learning is proposed in this paper to tackle with PD speech diagnosis. In the first step, convolution sparse coding with the coordinate selection of samples and features is designed to learn speech structure from the source domain to replenish sample information of the target domain. In the second step, joint local structure distribution alignment is designed to maintain the neighbor relationship between the respective samples of the training set and test set, and reduce the distribution difference between the two domains at the same time. Two representative public PD speech datasets and one real-world PD speech dataset were exploited to verify the proposed method on PD speech diagnosis. Experimental results demonstrate that each step of the proposed method has a positive effect on the PD speech classification results, and it also delivers superior performance over the existing relative methods.
ABSTRACT
BACKGROUND: As tympanotomy using the transcanal approach was a routine surgical technique for traumatic ossicular disruption, the efficacy of the posterior tympanum approach was rarely explored. AIM: This study aimed to investigate whether the hearing outcomes improved after simultaneous ossiculoplasty and facial nerve decompression using the posterior tympanum approach compared with the transcanal approach. MATERIAL AND METHODS: The data of 11 patients who underwent ossiculoplasty and facial nerve decompression using the posterior tympanum approach and 21 patients who underwent ossiculoplasty via transcannal approach were analyzed. RESULTS: The average air-bone gap (ABG) of patients undergoing posterior tympanotomy showed a statistically significant improvement. Postoperative ABG within 20 dB was observed in 81.8% of patients in the posterior tympanum group and 76.2% of patients in the transcanal group. However, the ABG closure in the two groups was not statistically different. CONCLUSIONS AND SIGNIFICANCE: Simultaneous ossiculoplasty using the posterior tympanum approach was practical, and the hearing outcomes were promising for the patients with traumatic facial nerve paralysis and ossicular disruption.
Subject(s)
Ear Ossicles/injuries , Facial Nerve Injuries/surgery , Facial Paralysis/surgery , Hearing , Otologic Surgical Procedures/methods , Tympanic Membrane/surgery , Adult , Audiometry, Pure-Tone , Auditory Threshold , Bone Conduction , Craniocerebral Trauma/complications , Ear Ossicles/surgery , Facial Nerve Injuries/complications , Facial Paralysis/etiology , Female , Humans , Male , Middle Aged , Ossicular Prosthesis , Ossicular Replacement , Young AdultABSTRACT
Abstract Introduction: Previous research has suggested that individuals with different blood groups show varied incidences of noise-induced hearing loss. The reduced otoacoustic emissions amplitudes indicate the higher possibilities of outer hair cell damage for noise exposure. Objective: The objective is to analyze the characteristics of otoacoustic emissions, including the occurrence of spontaneous otoacoustic emission and the amplitudes of distortion product otoacoustic emission at certain frequencies in full term neonates with different ABO blood groups. Methods: A total of 80 selected full-term female neonates who passed the initial newborn hearing screen were enrolled into the study, with equal number of participants in four ABO blood groups (Blood Group A, Blood Group B, Blood Group AB, Blood Group O). Measurements of spontaneous otoacoustic emission and distortion product otoacoustic emission were performed in both ears for all participants. Results: (1) The blood group O participants showed significantly fewer spontaneous otoacoustic emission occurrences than the other three blood groups (A = 70%, B = 80%, AB = 67%, O = 25%, p < 0.05). (2) The blood group O participants showed lower DPOAE amplitudes at 1257 Hz (M = 4.55 dB, SD = 8.36), 1587 Hz (M = 11.60 dB, SD = 6.57), 3174 Hz (M = 7.25 dB, SD = 5.99), 5042 Hz (M = 13.60, SD = 6.70) than participants with the other three blood groups in left ears (p < 0.05). In right ears, the blood group O participants showed reduced amplitudes at 1257 Hz (M = 6.55 dB, SD = 8.36), 1587 Hz (M = 13.60 dB, SD = 6.57), 3174 Hz (M = 7.65 dB, SD = 6.43), 5042 Hz (M = 13.65 dB, SD = 6.50) than participants from non-O blood groups (p < 0.05). Conclusion: Female individuals with blood group O have lower otoacoustic emissions values than individuals with the other three blood groups. We need to further investigate the possible relationships between ABO blood group and cochlear function, including the potential influences of noise damage on cochlear outer hair cells.
Resumo Introdução: Pesquisas anteriores sugeriram que indivíduos de diferentes grupos sanguíneos apresentam incidências distintas de perda auditiva induzida por ruído. As amplitudes reduzidas das emissões otoacústicas indicaram maiores ou menores possibilidades de danos às células ciliadas por exposição a ruídos. Objetivo: Analisar as características das emissões otoacústicas, inclusive a ocorrência de emissões otoacústicas espontâneas e as amplitudes de emissões otoacústicas por produto de distorção em determinadas frequências em neonatos a termo de diferentes grupos sanguíneos do sistema ABO. Método: Foram incluídos 80 neonatos a termo selecionados na triagem auditiva neonatal inicial para participar do estudo, com número igual de participantes de grupos sanguíneos do sistema ABO (grupo sanguíneo A, grupo sanguíneo B, grupo sanguíneo AB e grupo sanguíneo O). As emissões otoacústicas espontâneas e emissões otoacústicas por produto de distorção foram medidas em ambas as orelhas de todos os participantes. Resultados: (1) Os participantes do grupo sanguíneo O apresentaram ocorrências de emissões otoacústicas espontâneas significantemente menores do que os dos outros três grupos sanguíneos (A = 70%, B = 80%, AB = 67%, O = 25%, p < 0,05). (2) Os participantes do grupo sanguíneo O apresentaram amplitudes de emissões otoacústicas por produto de distorção mais baixas a 1257 Hz (M = 4,55 dB, DP = 8,36), 1587 Hz (M = 11,60 dB, DP = 6,57), 3174 Hz (M = 7,25 dB, DP = 5,99), 5042 Hz (M = 13,0, DP = 6,70) do que os participantes dos outros três grupos sanguíneos nas orelhas esquerdas (p < 0,05). Nas orelhas direitas, os participantes do grupo sanguíneo O apresentaram amplitudes reduzidas em 1257 Hz (M = 6,55 dB, DP = 8,36), 1587 Hz (M = 13,60 dB, DP = 6,57), 3174 Hz (M = 7,65 dB, DP = 6,43), 5042 Hz (M = 13,65 dB, DP = 6,50) em comparação aos participantes de grupos sanguíneos não O (p < 0,05). Conclusão: Os indivíduos do sexo feminino do grupo sanguíneo O apresentaram valores menores de emissões otoacústicas do que os indivíduos dos outros três grupos sanguíneos. É necessário continuar a investigar as possíveis relações entre o grupo sanguíneo ABO e a função coclear, inclusive as possíveis influências do dano por ruídos às células ciliadas externas da cóclea.
Subject(s)
Humans , Female , Infant, Newborn , Otoacoustic Emissions, Spontaneous , Blood Group Antigens , Hair Cells, Auditory, Outer , Term Birth , Hearing Loss, Noise-Induced , NoiseABSTRACT
OBJECTIVES: The study aimed to analyze the developmental mode of auditory at the level of brainstem in preschool autistic children using click-evoked auditory brainstem response (click-ABR). METHODS: Twenty children with autism spectrum disorder (ASD) and 20 age matched typical development children (TD) were recruited. The detail data recorded from click-ABR were collected at two time periods (T1 and T2). RESULTS: There was no significant change in TD group at two time periods. In ASD group, wave V latency was significantly shortened at T2 compared to that recorded at T1. The interpeak latency of I-V was short at T2 versus at T1 in the autistic children. Compared to the TD group, ASD was associated with longer latencies for waves V and longer interpeak latencies of I-III, I-V at T1. In addition, ASD group also indicated longer latencies of wave III and wave V, longer interpeak latencies of I-III and I-V at T2 compared to the TD group. CONCLUSIONS: ASD group had immature and dysfunction developmental mode in auditory stimuli perception at the level of brainstem. The performance of auditory ability in children with ASD improved gradually with ages. However, there are still differences compared with TD children.
Subject(s)
Autism Spectrum Disorder , Evoked Potentials, Auditory, Brain Stem , Auditory Perception , Autism Spectrum Disorder/diagnosis , Brain Stem , Child , Child, Preschool , HumansABSTRACT
This study assesses the impacts of the COVID-19 pandemic on Chinese residents' food safety knowledge and behavior, and explores the possible influence mechanism, namely, focus on media information. The study is based on internet survey data of 1 373 residents in China. A series of econometric models are developed to estimate food safety knowledge and behavior of residents. Both the descriptive and econometric results indicate that the existence of COVID-19 cases in a community has a significantly positive effect on residents' food safety knowledge and behavior. Residents focusing on food safety-related information tend to have higher food safety knowledge and practice food safety behavior. When controlling the variable focused on food safety-related information, the marginal effects of the existence of COVID-19 cases in a community on residents' food safety knowledge and behavior significantly decrease. However, the decrease in consumers' food safety knowledge is quite minor. Hence, the COVID-19 pandemic indeed improves Chinese residents' food safety knowledge and behavior, while focus on food safety-related information is an important mechanism for improving food safety behavior. Moreover, the estimation results of the simultaneous equations model reveal that consumers' food safety knowledge has a significant and positive effect on their food safety behavior. Heterogeneous impacts of the COVID-19 pandemic on residents' food safety knowledge and behavior among different regions and income groups are observed. The findings of this study provide evidence that public health events could enhance residents' safety awareness and behavior, while residents' focus on relevant information plays an important role in improving knowledge and impacting behavior.
ABSTRACT
INTRODUCTION: Previous research has suggested that individuals with different blood groups show varied incidences of noise-induced hearing loss. The reduced otoacoustic emissions amplitudes indicate the higher possibilities of outer hair cell damage for noise exposure. OBJECTIVE: The objective is to analyze the characteristics of otoacoustic emissions, including the occurrence of spontaneous otoacoustic emission and the amplitudes of distortion product otoacoustic emission at certain frequencies in full term neonates with different ABO blood groups. METHODS: A total of 80 selected full-term female neonates who passed the initial newborn hearing screen were enrolled into the study, with equal number of participants in four ABO blood groups (Blood Group A, Blood Group B, Blood Group AB, Blood Group O). Measurements of spontaneous otoacoustic emission and distortion product otoacoustic emission were performed in both ears for all participants. RESULTS: (1) The blood group O participants showed significantly fewer spontaneous otoacoustic emission occurrences than the other three blood groups (A=70%, B=80%, AB=67%, O=25%, p< 0.05). (2) The blood group O participants showed lower DPOAE amplitudes at 1257 Hz (M = 4.55 dB, SD = 8.36), 1587 Hz (M = 11.60 dB, SD = 6.57), 3174 Hz (M = 7.25 dB, SD = 5.99), 5042 Hz (M = 13.60, SD = 6.70) than participants with the other three blood groups in left ears (p < 0.05). In right ears, the blood group O participants showed reduced amplitudes at 1257Hz (M=6.55dB, SD=8.36), 1587Hz (M=13.60dB, SD=6.57), 3174Hz (M=7.65dB, SD=6.43), 5042Hz (M=13.65dB, SD=6.50) than participants from non-O blood groups (p<0.05). CONCLUSION: Female individuals with blood group O have lower otoacoustic emissions values than individuals with the other three blood groups. We need to further investigate the possible relationships between ABO blood group and cochlear function, including the potential influences of noise damage on cochlear outer hair cells.
Subject(s)
Otoacoustic Emissions, Spontaneous , Blood Group Antigens , Female , Hair Cells, Auditory, Outer , Hearing Loss, Noise-Induced , Humans , Infant, Newborn , Noise , Term BirthABSTRACT
Highlight1. Patients with patulous Eustachian tube (PET) were older, had a shorter duration of disease, and were more likely to develop bilateral otitis media with effusion.2. Patients with PET were more likely to develop comorbidities of gastroesophageal reflux and allergies.
Subject(s)
Eustachian Tube , Hypersensitivity , Otitis Media with Effusion , Otitis Media , Adult , Humans , Otitis Media with Effusion/complicationsABSTRACT
INTRODUCTION: Foreign body impaction is a common emergency in the field of otolaryngology. The prevalence of a jujube pit as an esophageal foreign body has increased in the Jiaodong Peninsula. However, reports on this are scarce. AIM: To investigate the methods for diagnosing and treating esophageal foreign body impaction of a jujube pit and to determine the risk factors for complications. MATERIAL AND METHODS: We conducted a retrospective review of the medical records of patients who were diagnosed with esophageal impaction of a jujube pit. Demographic, clinical, radiological, and endoscopic data were collected and analyzed. RESULTS: Neither plain radiography nor esophagogram provided enough information on the surrounding issues and complications. The rate of secondary radiological examination was 51.61% for the patients who did not undergo prior computed tomography. The success rate of rigid esophagoscopy was 95.45%; 18 of these patients (27.27%) had previously undergone flexible esophagoscopy without foreign body removal. Logistic regression showed that the time from ingestion to presentation and the jujube pit size were independent risk factors for complications. CONCLUSIONS: Computed tomography without contrast material is the preferred diagnostic method for adults with esophageal jujube pit impaction, and rigid esophagoscopy can be used for therapy even though the first flexible esophagoscopy failed. Large diameter of the jujube pit constituting the esophageal foreign body (≥ 25 mm) and long duration between pit ingestion and presentation (> 12 h) were associated with increased complications in the patients in this study.
ABSTRACT
Diagnosis of Parkinson's disease (PD) based on speech data has been proved to be an effective way in recent years. However, current researches just care about the feature extraction and classifier design, and do not consider the instance selection. Former research by authors showed that the instance selection can lead to improvement on classification accuracy. However, no attention is paid on the relationship between speech sample and feature until now. Therefore, a new diagnosis algorithm of PD is proposed in this paper by simultaneously selecting speech sample and feature based on relevant feature weighting algorithm and multiple kernel method, so as to find their synergy effects, thereby improving classification accuracy. Experimental results showed that this proposed algorithm obtained apparent improvement on classification accuracy. It can obtain mean classification accuracy of 82.5%, which was 30.5% higher than the relevant algorithm. Besides, the proposed algorithm detected the synergy effects of speech sample and feature, which is valuable for speech marker extraction.
ABSTRACT
Objective This study was performed to identify the differences in clinical characteristics, operative methods, complications, and postoperative hospitalization stays for adults with esophageal foreign bodies with different durations of time from ingestion to effective treatment. Methods We retrospectively reviewed the medical records of 221 patients with a diagnosis of a foreign body in the esophagus, confirmed by rigid esophagoscopy, flexible esophagoscopy, or surgery. The differences between the two groups (Group A, ≤24 hours from ingestion to effective treatment; Group B, >24 hours from ingestion to effective treatment) were analyzed. Results Sharp foreign bodies comprised the majority of objects in the two groups, including jujube pits, bones (excluding fish bones), fish bones, dentures, and seafood shells. Foreign bodies located in the upper esophagus were more commonly observed in Group A than B. Significant differences were observed in the complication rate and length of postoperative hospitalization stays. Adults with esophageal foreign bodies had a high complication rate. Conclusions Rigid esophagoscopy can be used to remove sharp and bulky foreign bodies if more effective methods are unavailable. Effective treatment within 24 hours resulted in fewer complications and shorter postoperative hospitalization stays.
Subject(s)
Esophageal Perforation/surgery , Esophagus/pathology , Foreign Bodies/surgery , Adolescent , Adult , Esophageal Perforation/diagnostic imaging , Esophagus/diagnostic imaging , Female , Foreign Bodies/diagnostic imaging , Humans , Male , Middle Aged , Retrospective Studies , Time-to-Treatment , Treatment Outcome , Young AdultABSTRACT
Parkinson's disease(PD)diagnosis based on speech data has been proved to be an effective way in recent years.There are still some problems on preprocessing samples,ensemble learning,and so on.The problems can further cause misleading of classifiers,unsatisfactory classification accuracy and stability.This paper proposed a new diagnosis algorithm of PD by combining multi-edit sample selection method and random forest.At the end of it,this paper presents a group of experiments carried out with the newest public datasets.Experimental results showed that this proposed algorithm realized the classification of the samples and the subjects of PD.Furthermore,it achieved average classification accuracy of 100% and obtained improvement of up to 29.44% compared to those provided by the subjects.This paper proposes a new speech diagnosis algorithm for PD based on instance selection;and the method algorithm has a higher and more stable classification accuracy,compared with the other algorithms.
Subject(s)
Parkinson Disease/diagnosis , Speech , Algorithms , HumansABSTRACT
OBJECTIVE: To explore the surgical treatment of rhinogenous optic function damage (ROFD) through transnasal endoscopic approach. METHODS: Twenty-three patients (25 eyes) with ROFD were retrospectively reviewed. All patients were operated on through transnasal endoscopic approach, and 9 patients underwent endoscopic optic nerve decompression. RESULTS: Four patients had bilateral pansinusitis, 6 patients had unilateral posterior ethmoidal sinusitis and sphenoiditis. One patient had frontal and ethmoidal sinusitis. Five patients had fungal sinusitis occurred in the sphenoid sinus and unilateral posterior ethmoid sinus. Two patients had unilateral pyocyst and cyst of the sphenoid and ethmoid sinus. The preoperative visual acuity preoperative were as follows: 2 patients (2 eyes) no light perception (NLP), 6 patients (7 eyes) hand movement (HM), 7 patients (7 eyes) fingers counting (FC) less than 20 cm and 8 patients (9 eyes) were vision impaired in different degree. One patient (1 eye) was ophthalmoptosis, direct and indirect light reflex vanished. Three patients (3 eyes) diplopia, 2 patients (2 eyes) abduction paralysis, 3 patients (3 eyes) defect of visual field. One patient ptosis of upper lid. The visual acuity postoperative: 2 eyes failed, 10 eyes cured;13 eyes improved from HM or FC to FC (30-60 cm). CONCLUSIONS: The endoscopic sinus surgery combined with appropriate medical therapy are effective to ROFD. Patients who suffered from severe visual damage and either unresponsive or intolerant to medical treatment should be administrated endoscopic sinus surgery including endoscopic optic nerve decompression.