Analysis, optimization and development of an answer scoring system

The main contribution of this work is to analyze and describe the state of the art performance as regards answer scoring systems from the SemEval- 2013 task, as well as to continue with the development of an answer scoring system (EHU-ALM) developed in the University of the Basque Country. On the overall this master thesis focuses on finding any possible configuration that lets improve the results in the SemEval dataset by using attribute engineering techniques in order to find optimal feature subsets, along with trying different hierarchical configurations in order to analyze its performance against the traditional one versus all approach. Altogether, throughout the work we propose two alternative strategies: on the one hand, to improve the EHU-ALM system without changing the architecture, and, on the other hand, to improve the system adapting it to an hierarchical con- figuration. To build such new models we describe and use distinct attribute engineering, data preprocessing, and machine learning techniques.

Predicting the likelihood of carrying a BRCA1 or BRCA2 mutation: validation of BOADICEA, BRCAPRO, IBIS, Myriad and the Manchester scoring system using data from UK genetics clinics

Objectives: Genetic testing for the breast and ovarian cancer susceptibility genes BRCA1 and BRCA2 has important implications for the clinical management of people found to carry a mutation. However, genetic testing is expensive and may be associated with adverse psychosocial effects. To provide a cost-efficient and clinically appropriate genetic counselling service, genetic testing should be targeted at those individuals most likely to carry pathogenic mutations. Several algorithms that predict the likelihood of carrying a BRCA1 or a BRCA2 mutation are currently used in clinical practice to identify such individuals.

Non-nutritive sucking scoring system for preterm newborns

Aim: To validate a non-nutritive sucking (NNS) scoring system for oral feeding in preterm newborns (PTNB). Methods: A cohort study was carried out in two phases. In phase one of the study, 22 mastered speech-language pathologists received the protocol and procedure for a NNS scoring system to evaluate the content and presentation of the form and to define the grading scale. In phase two, six speech-language pathologists evaluated 51 PTNBs weekly, using the defined scoring system. Setting: This study was carried out in the Nursery Annex to the Maternity at the Intensive and Neonatal Pediatrics Service, Instituto da Crianca, Hospital das Clinicas, School of Medicine, University of Sao Paulo (FMUSP) during the period from May 2004 to May 2006. Participants: A total of 28 speech-language pathologist experts and 51 PTNBs. Results: In the first phase of the study, 22 speech-language pathologists selected the criteria, utilized in the NNS evaluation with 80% agreement. In the second phase of the study, the NNS evaluation was carried out on 51 PTNB, and a scoring system of 50 points was proposed, which corresponds to the smallest number of false positive and negative results regarding oral feeding ability. Conclusion: An NNS evaluation system was validated that was able to indicate when oral feeding could safely begin in PTNBs with a high level of agreement among the speech-language pathologists who have participated.

Development of an evidence-based scoring system (HF-IS) to assess the quality of heart failure programmes for patients postdischarge from hospital

Aim.  The aim of this study was to develop a potential scoring algorithm for interventions in a chronic heart failure management programme – the Heart Failure Intervention Score – to facilitate quality improvement and programme auditing.

Background.  The overall efficacy of chronic heart failure management programmes has been demonstrated in several meta-analyses. However, meta-analyses did not determine individual interventions in a programme that resulted in beneficial patient outcomes.

Design.  A prospective cross-sectional survey design.

Method.  All chronic heart failure management programmes in Australia (n = 62), identified by a national register, were surveyed to determine programme characteristics and interventions.

Results.  Of the 62 national chronic heart failure management programmes, 48 (77%) completed the survey and 27 individual interventions were identified. Variability in the use of the key interventions was common among the programmes. Each intervention was given an arbitrary weighted score according to the level of supportive evidence available and a total score calculated. Programmes were then categorised into low or high complexity based on several interventions implemented and their weighted score. A total score of ≥190 (median = 178, interquartile range 176–195) was used to divide programmes into two groups. Nine programmes were categorised into high Heart Failure Intervention Score group and majority of these were based in the acute hospital setting (78%). In the low Heart Failure Intervention Score group, there were 39 programmes of which there were a higher proportion of community-based programmes (38%) and programmes in small community hospitals (10%).

Conclusion.  The Heart Failure Intervention Score provides a potential evidence-based quality improvement tool through which a set of minimum standards can be developed. Implementation of the Heart Failure Intervention Score provides guidance to programme coordinators to enable monitoring of standards of heart failure programmes, which may potentially result in better patient outcomes.

Melanoma maligno cutâneo: sistema de pontos (scoring system) para auxílio no diagnóstico histopatológico

INTRODUÇÃO: O diagnóstico histopatológico de algumas lesões melanocíticas pode ser muito difícil, mesmo para especialistas, mas há casos em que a dificuldade surge pela inadequada e subjetiva aplicação dos critérios diagnósticos. OBJETIVO: O objetivo deste estudo é desenvolver um método de aplicação sistemática desses critérios, atribuindo valores para os mais importantes. MATERIAL E MÉTODOS: Selecionaram-se os critérios mais relevantes para o diagnóstico de melanoma, atribuindo valores de 1 a 5 de acordo com sua importância. Foram escolhidos 101 casos de melanomas de tipo extensivo-superficial com menos de 2mm de espessura para análise comparativa com 33 lesões melanocíticas benignas (13 nevos de Spitz, seis de Reed, seis displásicos, três congênitos, três adquiridos, um combinado e um recorrente). RESULTADOS: A soma dos valores dados aos critérios (score) apresentou diferença significativa entre lesões malignas e benignas, mostrando que esse método pode ser útil ao patologista cirúrgico generalista em sua rotina diária. CONCLUSÃO: A aplicação objetiva e sistemática dos critérios histopatológicos pelo sistema de pontos (scoring system) pode ajudar o diagnóstico diferencial entre maligno e benigno em muitas lesões, porém não tendo o efeito desejado nas lesões melanocíticas de comportamento biológico indeterminado.

An epidemiological scoring system for tooth wear and dental erosive wear

Background: The prevalence and severity of tooth wear and dental erosion is rising in children and there is no consensus about an index to be employed. Aim: To assess the reliability of an epidemiological scoring system dental wear index (DWI) to measure tooth wear and dental erosive wear. Design: An epidemiological cross-sectional survey was conducted to evaluate and compare tooth wear and dental erosion using the dental wear index and erosion wear index (EWI). The study was conducted with randomised samples of 2,371 children aged between 4 years and 12 years selected from the State of São Paulo, Brazil. Records were used for calculating tooth wear and dental erosion; the incisal edge and canine cusp were excluded. Results: As the schoolchildren's ages increased the severity of primary tooth wear increased in canines (P = 0.0001, OR = 0.34) and molars (P = 0.0001, OR = 2.47) and erosion wear increased in incisal/occlusal (P = 0.0001, OR = 5.18) and molars (P = 0.0001, OR = 2.47). There was an increased prevalence of wear in the permanent teeth of older schoolchildren, particularly on the incisal/occlusal surfaces (P = 0.0001, OR = 7.03). Conclusion: The prevalence of tooth wear and dental erosion increased as age increased in children. The epidemiological scoring system Dental Wear Index is able to measure both tooth wear and dental erosive wear. This index should be used to monitor the progression of non-carious lesions and to evaluate the levels of disease in the population.

A new histology scoring system for the assessment of the quality of human cartilage repair: ICRS II

A reliable and reproducible method is needed to assess cartilage repair.

Risk assessment in the first fifteen minutes: a prospective cohort study of a simple physiological scoring system in the emergency department

Introduction The survival of patients admitted to an emergency department is determined by the severity of acute illness and the quality of care provided. The high number and the wide spectrum of severity of illness of admitted patients make an immediate assessment of all patients unrealistic. The aim of this study is to evaluate a scoring system based on readily available physiological parameters immediately after admission to an emergency department (ED) for the purpose of identification of at-risk patients. Methods This prospective observational cohort study includes 4,388 consecutive adult patients admitted via the ED of a 960-bed tertiary referral hospital over a period of six months. Occurrence of each of seven potential vital sign abnormalities (threat to airway, abnormal respiratory rate, oxygen saturation, systolic blood pressure, heart rate, low Glasgow Coma Scale and seizures) was collected and added up to generate the vital sign score (VSS). VSSinitial was defined as the VSS in the first 15 minutes after admission, VSSmax as the maximum VSS throughout the stay in ED. Occurrence of single vital sign abnormalities in the first 15 minutes and VSSinitial and VSSmax were evaluated as potential predictors of hospital mortality. Results Logistic regression analysis identified all evaluated single vital sign abnormalities except seizures and abnormal respiratory rate to be independent predictors of hospital mortality. Increasing VSSinitial and VSSmax were significantly correlated to hospital mortality (odds ratio (OR) 2.80, 95% confidence interval (CI) 2.50 to 3.14, P < 0.0001 for VSSinitial; OR 2.36, 95% CI 2.15 to 2.60, P < 0.0001 for VSSmax). The predictive power of VSS was highest if collected in the first 15 minutes after ED admission (log rank Chi-square 468.1, P < 0.0001 for VSSinitial;,log rank Chi square 361.5, P < 0.0001 for VSSmax). Conclusions Vital sign abnormalities and VSS collected in the first minutes after ED admission can identify patients at risk of an unfavourable outcome.

Hip Osteoarthritis MRI Scoring System (HOAMS): reliability and associations with radiographic and clinical findings

To develop a semiquantitative MRI-based scoring system (HOAMS) of hip osteoarthritis (OA) and test its reliability and validity.

Tumor budding score based on 10 high-power fields is a promising basis for a standardized prognostic scoring system in stage II colorectal cancer

Tumor budding is recognized by the World Health Organization as an additional prognostic factor in colorectal cancer but remains unreported in diagnostic work due to the absence of a standardized scoring method. This study aims to assess the most prognostic and reproducible scoring systems for tumor budding in colorectal cancer. Tumor budding on pancytokeratin-stained whole tissue sections from 105 well-characterized stage II patients was scored by 3 observers using 7 methods: Hase, Nakamura, Ueno, Wang (conventional and rapid method), densest high-power field, and 10 densest high-power fields. The predictive value for clinicopathologic features, the prognostic significance, and interobserver variability of each scoring method was analyzed. Pancytokeratin staining allowed accurate evaluation of tumor buds. Interobserver agreement for 3 observers was excellent for densest high-power field (intraclass correlation coefficient, 0.83) and 10 densest high-power fields (intraclass correlation coefficient, 0.91). Agreement was moderate to substantial for the conventional Wang method (κ = 0.46-0.62) and moderate for the rapid method (κ = 0.46-0.58). For Nakamura, moderate agreement (κ = 0.41-0.52) was reached, whereas concordance was fair to moderate for Ueno (κ = 0.39-0.56) and Hase (κ = 0.29-0.51). The Hase, Ueno, densest high-power field, and 10 densest high-power field methods identified a significant association of tumor budding with tumor border configuration. In multivariate analysis, only tumor budding as evaluated in densest high-power field and 10 densest high-power fields had significant prognostic effects on patient survival (P < .01), with high prognostic accuracy over the full 10-year follow-up. Scoring tumor buds in 10 densest high-power fields is a promising method to identify stage II patients at high risk for recurrence in daily diagnostics; it is highly reproducible, accounts for heterogeneity, and has a strong predictive value for adverse outcome.