A Survey of Vectorization Methods in Topological Data Analysis.

Attempts to incorporate topological information in supervised learning tasks have resulted in the creation of several techniques for vectorizing persistent homology barcodes. In this paper, we study thirteen such methods. Besides describing an organizational framework for these methods, we comprehensively benchmark them against three well-known classification tasks. Surprisingly, we discover that the best-performing method is a simple vectorization, which consists only of a few elementary summary statistics. Finally, we provide a convenient web application which has been designed to facilitate exploration and experimentation with various vectorization methods.

Assessment of the efficacy of hearing screening program in infants in Zahedan.

Introduction: Hearing loss is one of the major congenital problems. The frequency of this problem in different countries has been found to be 3.5-9%, which may induce negative effects on communications, education, and language learning in children. In addition, diagnosing this problem in infants is not possible without implementing the hearing screening methods. Therefore, the objective of this research was to assess the efficacy of newborn hearing screening programs in Zahedan, Iran. Method: In the present cross-sectional observational study, all infants born in the maternity hospitals of Zahedan city (hospitals of Nabi Akram, Imam Ali, and Social Security hospitals) in 2020, were assessed. For conducting the research, TEOAE was primarily performed for all newborns. Following that, according to the findings obtained in the ODA test and in case of inappropriate response, evaluation was performed again for the cases. Cases that were rejected again in the second assessment were subjected to the AABR test and in case of failure in this test, the cases underwent a diagnostic ABR test. Results: According to our findings, 7700 babies were initially assessed with the OAE test. Among them, 580 (8%) showed no OAE response. Out of 580 newborns that were rejected in the first phase, 76 babies were also rejected in the second phase and amongst them, 8 cases were re-diagnosed with hearing loss. Finally, out of 3 infants who were diagnosed with hearing impairments, 1 (33%) had conductive hearing loss and 2 (67%) had sensorineural hearing loss. Conclusion: According to the results of this research, the use of comprehensive neonatal hearing screening programs is necessary for on-time diagnosis and therapy of hearing loss. In addition, screening programs could help improving the health of newborns and their personal, social, and educational development in the future.

Studying the relationship between the Lund Mackay score and response to medical treatment in patients with chronic sinusitis.

INTRODUCTION: One of the most common reasons for patients to visit a doctor is Sinusitis. Treatment of this disease involves a wide range of topical and systemic drugs, if it left untreated, surgery and sinus drainage will be the only choice. Due to symptoms and problems caused by chronic sinusitis and its treatment, as well as the need for an appropriate solution to reduce this, the present study was conducted to investigate the relationship between The Lund Mackay score and response to medical treatment in patients with chronic sinusitis. MATERIALS AND METHODS: The present study was performed cross-sectionally on 150 patients referred to Khatamul- Anbia Hospital in Zahedan for whom the diagnosis of chronic sinusitis was confirmed and met the study criteria. Demographic data and clinical signs of patients were recorded and for based on CT scan, The Lund Mackay score was evaluated. Patients were treated for 4 to 6 weeks and finally re-evaluated for symptoms and response to treatment. Data were analyzed using SPSS software version 24, McNemar test, Mann-Whitney and other necessary tests for descriptive statistics. A significance level of 0.05 was considered. RESULTS: 3.55% of patients were male (83 patients) and 7.44% were female (67 patients). The mean score of the Lund Mackay in the present study was 92.11 with a standard deviation of 2.3. Symptoms of olfactory dysfunction, sinus pain, nasal obstruction and nasal discharge showed significant improvement after treatment (p <05.0). Based on the results obtained at the end of the study, the presence of nasal polyps (p = 001.0) and nasal obstruction (p = 003.0), after the end of the treatment period, showed a significant relationship with the response to treatment. CONCLUSION: In general, this study suggested that the mean score of The Lund Mackay had a significant positive relationship with the severity of patients' clinical symptoms and the severity of sinusitis. Therefore, it can be considered as a suitable criterion in diagnostic and therapeutic evaluations of patients.

Issues associated with deploying CNN transfer learning to detect COVID-19 from chest X-rays.

Covid-19 first occurred in Wuhan, China in December 2019. Subsequently, the virus spread throughout the world and as of June 2020 the total number of confirmed cases are above 4.7 million with over 315,000 deaths. Machine learning algorithms built on radiography images can be used as a decision support mechanism to aid radiologists to speed up the diagnostic process. The aim of this work is to conduct a critical analysis to investigate the applicability of convolutional neural networks (CNNs) for the purpose of COVID-19 detection in chest X-ray images and highlight the issues of using CNN directly on the whole image. To accomplish this task, we use 12-off-the-shelf CNN architectures in transfer learning mode on 3 publicly available chest X-ray databases together with proposing a shallow CNN architecture in which we train it from scratch. Chest X-ray images are fed into CNN models without any preprocessing to replicate researches used chest X-rays in this manner. Then a qualitative investigation performed to inspect the decisions made by CNNs using a technique known as class activation maps (CAM). Using CAMs, one can map the activations contributed to the decision of CNNs back to the original image to visualize the most discriminating region(s) on the input image. We conclude that CNN decisions should not be taken into consideration, despite their high classification accuracy, until clinicians can visually inspect and approve the region(s) of the input image used by CNNs that lead to its prediction.

Phonatory vocal tract stability in stuttering children before and after fluency--enhancing therapy.

BACKGROUND: Stuttering is a complex disorder. Essentially, it is a neuromuscular disorder whose core consists of tiny lags and disruptions in the timing of the complicated movements required for speech. OBJECTIVE: The purpose of the current study was to collec and comparg jitters and shimmer values in children who stutter before and after fluency--enhancing therapy. METHODS: Subjects consisted of 15 Iranian preschool girls with stutterg, and 15 Iranial preschool girls without afflictions, matched according to age. Vocal jittering and shimmer measurements of thesphonation of the children were compared before and after therapy. Each subject phonated vowels nine times in a random order. Each phonation was sustained for at least five seconds and was recorded. The middle three-second portion of each recorded vowel phonation was subjected to jitter and shimmer analysis. RESULTS: On shimmer measures between pre-treatment and post treatment, significant differences were found in all sustained vowels of persons who stutter group and means of shimmer in post therapy were significantly lower than pre-treatment. Differences in jitter measurements were not significant between pre-treatment and post-treatment statuses and this parameter did not change after therapy. CONCLUSION: The findings showed that therapy resulted in decreaseg irregularity in the amplitude of vibrations (shimmer). In other words, the therapy increases the steady-state of the laryngeal system. Moreover, this parameter may be used as an index for the effectiveness of therapy.