Multi-label Diagnosis Classification of Swedish Discharge Summaries -- ICD-10 Code Assignment Using KB-BERT

The International Classification of Diseases (ICD) is a system for systematically recording patients' diagnoses. Clinicians or professional coders assign ICD codes to patients' medical records to facilitate funding, research, and administration. In most health facilities, clinical coding is a manual, time-demanding task that is prone to errors. A tool that automatically assigns ICD codes to free-text clinical notes could save time and reduce erroneous coding. While many previous studies have focused on ICD coding, research on Swedish patient records is scarce. This study explored different approaches to pairing Swedish clinical notes with ICD codes. KB-BERT, a BERT model pre-trained on Swedish text, was compared to the traditional supervised learning models Support Vector Machines, Decision Trees, and K-nearest Neighbours used as the baseline. When considering ICD codes grouped into ten blocks, the KB-BERT was superior to the baseline models, obtaining an F1-micro of 0.80 and an F1-macro of 0.58. When considering the 263 full ICD codes, the KB-BERT was outperformed by all baseline models at an F1-micro and F1-macro of zero. Wilcoxon signed-rank tests showed that the performance differences between the KB-BERT and the baseline models were statistically significant.

Rare-Class Dialogue Act Tagging for Alzheimer's Disease Diagnosis

Alzheimer's Disease (AD) is associated with many characteristic changes, not only in an individual's language but also in the interactive patterns observed in dialogue. The most indicative changes of this latter kind tend to be associated with relatively rare dialogue acts (DAs), such as those involved in clarification exchanges and responses to particular kinds of questions. However, most existing work in DA tagging focuses on improving average performance, effectively prioritizing more frequent classes; it thus gives a poor performance on these rarer classes and is not suited for application to AD analysis. In this paper, we investigate tagging specifically for rare class DAs, using a hierarchical BiLSTM model with various ways of incorporating information from previous utterances and DA tags in context. We show that this can give good performance for rare DA classes on both the general Switchboard corpus (SwDA) and an AD-specific conversational dataset, the Carolinas Conversation Collection (CCC); and that the tagger outputs then contribute useful information for distinguishing patients with and without AD

A Comparative Study between Artificial Neural Network Performance and Adaptive Neuro-fuzzy Inference Systems in Breast Cancer Diagnosis Depending On Structural Features

This research aims to produce a diagnosis system for breast cancer by using Neural Network depending on Back Propagation algorithm(BPNN) and Adaptive Neuro Fuzzy Inference System ‘ANFIS’, the both of studies was done using structural features of biopsies in “Wisconson Breast Cancer “data base. In the end a comparison was made between the two studies of malignant- benign classification of breast masses of breast cancer which has accuracy 95,95% with BPNN and 91.9% with ANFIS system, this results can be consider very important if they compared with researches depending on image features that obtained of various devises like mammography, magnetic resonance.

Determinants of up taking the papsmear among women visiting outpatient clinic in hospital tishreen university

Cancer is generally causing a second death after heart and blood vessels in the developed countries diseases is cervical cancer, the second most common cancer among women in developed and developing countries and is considered the early detection of cervical cancer is a very important factor in the increase cure rate and the rate of survival, and the most important ways screening Pap smear to detect abnormal changes in cervical tissue and recommended to initiate it every three years for women in the age of sexual activity and is an easy and inexpensive and painless, and high sensitivity and contributes to reducing the burden treatment and reduce the deaths and morbidity rate., according to several studies there are many obstacles that prevent it, including the lack of information,, difficulty of access to hospitals, pain, cost, side effects, feeling of shame and embarrassment of procedure, lack of encouragement by the health team, or the husband, not feeling any symptoms paid to conduct the examination, and the fear of discovery of the cancer . the importance of this study was to find out the obstacles that limit the conduct smear screening in the Syrian society and propose appropriate solutions in addition to that not conducted any study in this area in Syria this research was conducted on a sample of 100 married woman of tishreen University Hospital in Latakia in manner convenient sampling. The results showed that the majority of respondents (80%) did not undergo the smear examination, and that the majority of the respondents (93.75%) who did not undergo the smear examination was due to the lack of women's problem to have, and it was the reason (75%) of cases they fear the cancer is detected and 85% of them feel ashamed and embarrassed of the vote and (12.5%) do not have the time to conduct and (62.5 %) they believe that the procedure is painless and (90%) was the lack of encouragement from the doctors and nurses and the proportion (87.5%) was the lack of information about the procedure, Therefore proposed design and implementation of educational programs about the importance , benefits and methode of screening.

Study of tinea capitis among children in Damascus city between 2011- 2015

Tinea capitis is a common fungal infection of the scalp. The purpose of this study was to determine the percentage of the spread of tinea capitisin Damascus and determine the type of this tinea capitis and lasted between 2011 and 2015.

Automated Diagnosis Of Cutaneous Malignant Melanoma in Histological Slides Using Spectral Imaging Technology

Inasmuch as for incrimination of occurrence dermal malignant melanoma and difficulties of the clinical and histological diagnosis, so it is needed to search about method, giving fast diagnosis and self of high credibility, so the automatic spectral imaging was for the histological slides of dermal melanoma, where use of the morphological information is complete with the local information in establishing of the tissue print, through education of the machine (machine learning). 31 Cutaneous biopsies have been studied, of their 11 malignant melanomas, 16 benign lesions, and 4 normal skin. It has done spectral imaging for Histological sections stained routinely during the evaluation in digital camera pick up (CCD Camera) on luminous spectroscope, his luminous wavelengths ranges from 390-700 nanometer. the automated classifying results showed in the acquaintance on the malignant cells in tumor tissues in a ratio of ranged between 65-82%, these are very promising results. method of the non-supported classification revealed better results. in the future, we must complete classification of all types of other tissues, and build data base characterized each type of disease in various tissues. in order to use it as supportive factor in the accurate diagnosis and correct.

The Poetic Image of the Almouatamed ben Abbad

The research discusses the importance of poetic image, and its methods of study, and the types of images the poet uses, as reflection, a diagnosis of abstractions, concrete objects, and human emotions in a suggestive expressive way: The study also observes the poet's use of images that observe the dynamics of mobile and static objects that move only in the imagination; of single and compound colors; of correspondences of times; of figurative passions with their musical rhythms, and of significations of lexical meaning of words so that the poetic expression will reach the highest levels of artistic aesthetics. It also discusses and a single, composite color, and correspond between the times, and the varying situations , also words of emotion either catalog music, or cast the various implications of the lexical semantic; then the poetic expression, will reatch to the highest levels of influence and artistic beauty.

The New Methods for the Prenatal Diagnosis of Down syndrome

The aim of the present research is to determine the appropriate diagnostic methods to find out the affected fetuses with Down Syndrome in order to decrease as possible subjecting the pregnant women to invasive prenatal diagnosis . This is a Prospective – practical study, where /1137/ pregnant women at 13- 16 gestation weeks, ( age range: 20-42 years) were included. Biochemical screening of the pregnant women, ultrasound screening of the fetuses: nuchal translucency, nasal bone, which helped us to isolate the highrisk pregnancies for Down syndrome (the potential rate of incidence ≥ 0.4%). The screen positive group included 57 pregnant ( 5.01% ) . Amniocentesis and subsequently karyotyping was done to each woman in this group . We found out 4 affected fetuses from 5 ( 80%) , because the following up of the remaining pregnancies revealed a fifth affected newborn with Down syndrome. The early prenatal diagnosis of Down syndrome was possible in ( 80% ) by subjecting only ( 5.01% ) of pregnants to the invasive prenatal diagnosis .

Epidemiological Study of The Cutaneous Leishmaniasis Disease at Dermatological Hospital and General Clinic in Damascus

In this study the total of ٤١٥ cases of cutaneous leishmaniasis was evaluated from Dermatology hospital and General clinic in Damascus from February ٢٠٠١ to February ٢٠٠٢. Most of these cases was reported in Damascus and its suburb, and when we made the direct microscopic test, amastigotes were detectable in ٢٧١ cases, and the positive cases was increased to ٣٦٤ cases by realizing the parasite culture into diphasic N. N. N. media, which confirm the diagnosis.