Submitted by JÚLIO HEBER SILVA (julioheber@yahoo.com.br) on 2016-12-02T15:54:04Z No. of bitstreams: 2 Dissertação - Porthos Ribeiro de Albuquerque Motta - 2016.pdf: 10397634 bytes, checksum: 0610600c9a91143c40d1c6d22a401524 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Jaqueline Silva (jtas29@gmail.com) on 2016-12-13T15:28:18Z (GMT) No. of bitstreams: 2 Dissertação - Porthos Ribeiro de Albuquerque Motta - 2016.pdf: 10397634 bytes, checksum: 0610600c9a91143c40d1c6d22a401524 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2016-12-13T15:28:18Z (GMT). No. of bitstreams: 2 Dissertação - Porthos Ribeiro de Albuquerque Motta - 2016.pdf: 10397634 bytes, checksum: 0610600c9a91143c40d1c6d22a401524 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2016-10-20 / Educational Data Mining, by the triad of quality improvement, cost reduction and educational effectiveness, acts and seeks to better understand the teaching and learning process. In this context, the aim of this work is an exploratory study of classification methods to predict student performance and dropout from data in university academic databases. In this study we used demographic, socio-economic and academic results, obtained from the Vestibular and the university database to analyze several classification techniques, as well as balancing and attribute selection techniques, identified through a systematic review of the literature. Following a trend found in the selected articles, we chose to use decision trees as the primary classification algorithm, although comparative studies showed better results with logistic regression techniques and Bayesian networks. This is because decision trees allow an analysis of the attributes used in the generated models while maintaining acceptable levels of accuracy, while other techniques work as a black box. Through the tests we found that you get better results using balanced sets. In this sense, the Resample technique that selects a balanced subset of the data showed better results than SMOTE technique that generates synthetic data for balancing the dataset. Regarding the use of attribute selection techniques, these did not bring significant advantages. Among the attributes used, grades and economic factors often appear as nodes in the generated models. An attempt to predict performance for each subject based on data from previous courses was less successful, maybe because of the use of ternary predictive classes. Nevertheless, the analysis carried out showed that the use of classifiers is a promising way to predict performance and dropout, but further studies are still needed. / A Mineração de Dados Educacionais, por meio da tríade melhoria da qualidade, redução do custo e eficácia do ensino, age e procura compreender melhor o processo de ensinoaprendizagem dos alunos. Neste contexto, o objetivo desta dissertação é o estudo exploratório de métodos de classificação para predizer o desempenho e o abandono de alunos a partir de dados existentes nas bases de dados acadêmicas das universidades. Neste trabalho foram usados dados demográficos, sócio-econômicos e resultados acadêmicos, oriundos do Vestibular e do banco de dados acadêmico da universidade para analisar diversas técnicas de classificação, assim como técnicas de balanceamento e seleção de atributos identificadas através de uma revisão sistemática da literatura. Seguindo uma tendência verificada nos artigos levantados, optou-se por utilizar como principal algoritmo de classificação o J48, apesar de estudos comparativos terem mostrado melhores resultados com técnicas de regressão logística e redes Bayesianas. Isto se deve ao fato das árvores de decisão permitirem uma análise dos atributos usados nos modelos gerados, mantendo ní- veis de acurácia aceitáveis, enquanto as outras técnicas funcionam como uma caixa preta. Neste sentido, a técnica de Resample, que escolhe um subconjunto balanceado dos dados, apresentou melhores resultados que a técnica de SMOTE, que gera dados sintéticos para balancear os dados. Quanto ao uso de técnicas de seleção de atributos, estas não trouxeram vantagens significativas. Dentre os atributos usados, notas e aspectos econômicos aparecem com frequência nos modelos gerados. Uma tentativa de prever desempenho por disciplina, com base em dados de disciplinas já cursadas em semestres anteriores foi menos bem sucedida, talvez pelo fato de usar classes preditoras ternárias. Apesar disto, as análises realizadas mostraram que o uso de classificadores é um caminho promissor para a predição de desempenho e abandono, mas estudos mais aprofundados ainda são necessários

Being able to predict the outcome of a game is useful in many aspects. Such as,to aid designers in the process of understanding how the game is played by theplayers, as well as how to be able to balance the elements within the game aretwo of those aspects. If one could predict the outcome of games with certaintythe design process could possibly be evolved into more of an experiment basedapproach where one can observe cause and effect to some degree. It has previouslybeen shown that it is possible to predict outcomes of games to varying degrees ofsuccess. However, there is a lack of research which compares and evaluates severaldifferent models on the same domain with common aims. To narrow this identifiedgap an experiment is conducted to compare and analyze seven different classifierswithin the same domain. The classifiers are then ranked on accuracy against eachother with help of appropriate statistical methods. The classifiers compete onthe task of predicting which team will win or lose in a match of the game BloodBowl 2. For nuance three different datasets are made for the models to be trainedon. While the results vary between the models of the various datasets the general consensus has an identifiable pattern of rejections. The results also indicatea strong accuracy for Support Vector Machine and Logistic Regression across allthe datasets.

Motivation: Disease progression in cancer can vary substantially between patients. Yet, patients often receive the same treatment. Recently, there has been much work on predicting disease progression and patient outcome variables from gene expression in order to personalize treatment options. A widely used approach is high-throughput experiments that aim to explore predictive signature genes which would provide identification of clinical outcome of diseases. Microarray data analysis helps to reveal underlying biological mechanisms of tumor progression, metastasis, and drug-resistance in cancer studies. Despite first diagnostic kits in the market, there are open problems such as the choice of random gene signatures or noisy expression data. The experimental or computational noise in data and limited tissue samples collected from patients might furthermore reduce the predictive power and biological interpretability of such signature genes. Nevertheless, signature genes predicted by different studies generally represent poor similarity; even for the same type of cancer. Integration of network information with gene expression data could provide more efficient signatures for outcome prediction in cancer studies. One approach to deal with these problems employs gene-gene relationships and ranks genes using the random surfer model of Google's PageRank algorithm. Unfortunately, the majority of published network-based approaches solely tested their methods on a small amount of datasets, questioning the general applicability of network-based methods for outcome prediction. Methods: In this thesis, I provide a comprehensive and systematically evaluation of a network-based outcome prediction approach -- NetRank - a PageRank derivative -- applied on several types of gene expression cancer data and four different types of networks. The algorithm identifies a signature gene set for a specific cancer type by incorporating gene network information with given expression data. To assess the performance of NetRank, I created a benchmark dataset collection comprising 25 cancer outcome prediction datasets from literature and one in-house dataset. Results: NetRank performs significantly better than classical methods such as foldchange or t-test as it improves the prediction performance in average for 7%. Besides, we are approaching the accuracy level of the authors' signatures by applying a relatively unbiased but fully automated process for biomarker discovery. Despite an order of magnitude difference in network size, a regulatory, a protein-protein interaction and two predicted networks perform equally well. Signatures as published by the authors and the signatures generated with classical methods do not overlap -- not even for the same cancer type -- whereas the network-based signatures strongly overlap. I analyze and discuss these overlapping genes in terms of the Hallmarks of cancer and in particular single out six transcription factors and seven proteins and discuss their specific role in cancer progression. Furthermore several tests are conducted for the identification of a Universal Cancer Signature. No Universal Cancer Signature could be identified so far, but a cancer-specific combination of general master regulators with specific cancer genes could be discovered that achieves the best results for all cancer types. As NetRank offers a great value for cancer outcome prediction, first steps for a secure usage of NetRank in a public cloud are described. Conclusion: Experimental evaluation of network-based methods on a gene expression benchmark dataset suggests that these methods are especially suited for outcome prediction as they overcome the problems of random gene signatures and noisy expression data. Through the combination of network information with gene expression data, network-based methods identify highly similar signatures over all cancer types, in contrast to classical methods that fail to identify highly common gene sets across the same cancer types. In general allows the integration of additional information in gene expression analysis the identification of more reliable, accurate and reproducible biomarkers and provides a deeper understanding of processes occurring in cancer development and progression.:1 Definition of Open Problems 2 Introduction 2.1 Problems in cancer outcome prediction 2.2 Network-based cancer outcome prediction 2.3 Universal Cancer Signature 3 Methods 3.1 NetRank algorithm 3.2 Preprocessing and filtering of the microarray data 3.3 Accuracy 3.4 Signature similarity 3.5 Classical approaches 3.6 Random signatures 3.7 Networks 3.8 Direct neighbor method 3.9 Dataset extraction 4 Performance of NetRank 4.1 Benchmark dataset for evaluation 4.2 The influence of NetRank parameters 4.3 Evaluation of NetRank 4.4 General findings 4.5 Computational complexity of NetRank 4.6 Discussion 5 Universal Cancer Signature 5.1 Signature overlap – a sign for Universal Cancer Signature 5.2 NetRank genes are highly connected and confirmed in literature 5.3 Hallmarks of Cancer 5.4 Testing possible Universal Cancer Signatures 5.5 Conclusion 6 Cloud-based Biomarker Discovery 6.1 Introduction to secure Cloud computing 6.2 Cancer outcome prediction 6.3 Security analysis 6.4 Conclusion 7 Contributions and Conclusions

Autism Spectrum Disorder (ASD) is a condition that carries high costs for families and the healthcare system, requiring extensive management both in terms of diagnosis and treatment. The implementation of AI-based systems in clinical practice represents a possible supportive solution that can help clinicians by providing more systematic meth- ods to monitor child behavior. The main advantage over more traditional observational approaches is to offer quantitative and refined analysis solutions that can be ecological at the same time. The relevance of AI in clinical applications can have a role both in the challenge of early detection and in designing intervention programs better tai- lored to the specific functioning of children with ASD. The research project presented in this dissertation focused on developing AI-based systems for fine-grained analysis of autism-related social behaviors and their validation in concrete clinical environments. Specifically, in Chapter 2, our first study is presented, which targets on implementing a computational phenotyping system to address the need for new early markers of the condition. Through fine-grained analytics of facial dynamics in videos, we identified a set of features that distinguished young (6-12 months) infants with ASD (18 ASD, 15 non-ASD) during unconstrained at-home interactions. In Chapters 3 and 4, we introduce EYE-C, a Behavior Imaging model for robust analysis of eye contact episodes in eco- logical therapist-child interactions. The system was validated in the clinical setting for personalized early intervention. First, we investigated the influence of extracted features in categorizing spectrum heterogeneity across a sample of 62 preschool (<6 years) chil- dren with ASD. Further, we tested our metrics as predictors of early intensive treatment outcomes in a sub-sample of 18 subjects with ASD. The project aims to demonstrate the feasibility of effective computational systems that are robust to the high variability of unstructured interactions, with emphasis on the applicative value in real-world scenar- ios. Even though based on limited sample sizes, the work presented may offer interesting insights into the perspective of integrating AI into clinical practice. The research project was funded by an FBK scholarship and developed in a double in- ternship at ODFLab (University of Trento) and the FBK Data Science for Health (DSH) research unit.

Radiomics analyses commonly apply imaging features of different complexity for the prediction of the endpoint of interest. However, the prognostic value of each feature class is generally unclear. Furthermore, many radiomics models lack independent external validation that is decisive for their clinical application. Therefore, in this manuscript we present two complementary studies. In our modelling study, we developed and validated different radiomics signatures for outcome prediction after neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC) based on computed tomography (CT) and T2-weighted (T2w) magnetic resonance (MR) imaging datasets of 4 independent institutions (training: 122, validation 68 patients). We compared different feature classes extracted from the gross tumour volume for the prognosis of tumour response and freedom from distant metastases (FFDM): morphological and first order (MFO) features, second order texture (SOT) features, and Laplacian of Gaussian (LoG) transformed intensity features. Analyses were performed for CT and MRI separately and combined. Model performance was assessed by the area under the curve (AUC) and the concordance index (CI) for tumour response and FFDM, respectively. Overall, intensity features of LoG transformed CT and MR imaging combined with clinical T stage (cT) showed the best performance for tumour response prediction, while SOT features showed good performance for FFDM in independent validation (AUC = 0.70, CI = 0.69). In our external validation study, we aimed to validate previously published radiomics signatures on our multicentre cohort. We identified relevant publications on comparable patient datasets through a literature search and applied the reported radiomics models to our dataset. Only one of the identified studies could be validated, indicating an overall lack of reproducibility and the need of further standardization of radiomics before clinical application.

La radiothérapie est une des méthodes principales utilisée dans le traitement thérapeutique des tumeurs malignes. Pour améliorer son efficacité, deux problèmes essentiels doivent être soigneusement traités : la prédication fiable des résultats thérapeutiques et la segmentation précise des volumes tumoraux. La tomographie d’émission de positrons au traceur Fluoro- 18-déoxy-glucose (FDG-TEP) peut fournir de manière non invasive des informations significatives sur les activités fonctionnelles des cellules tumorales. Les objectifs de cette thèse sont de proposer: 1) des systèmes fiables pour prédire les résultats du traitement contre le cancer en utilisant principalement des caractéristiques extraites des images FDG-TEP; 2) des algorithmes automatiques pour la segmentation de tumeurs de manière précise en TEP et TEP-TDM. La théorie des fonctions de croyance est choisie dans notre étude pour modéliser et raisonner des connaissances incertaines et imprécises pour des images TEP qui sont bruitées et floues. Dans le cadre des fonctions de croyance, nous proposons une méthode de sélection de caractéristiques de manière parcimonieuse et une méthode d’apprentissage de métriques permettant de rendre les classes bien séparées dans l’espace caractéristique afin d’améliorer la précision de classification du classificateur EK-NN. Basées sur ces deux études théoriques, un système robuste de prédiction est proposé, dans lequel le problème d’apprentissage pour des données de petite taille et déséquilibrées est traité de manière efficace. Pour segmenter automatiquement les tumeurs en TEP, une méthode 3-D non supervisée basée sur le regroupement évidentiel (evidential clustering) et l’information spatiale est proposée. Cette méthode de segmentation mono-modalité est ensuite étendue à la co-segmentation dans des images TEP-TDM, en considérant que ces deux modalités distinctes contiennent des informations complémentaires pour améliorer la précision. Toutes les méthodes proposées ont été testées sur des données cliniques, montrant leurs meilleures performances par rapport aux méthodes de l’état de l’art. / Radiation therapy is one of the most principal options used in the treatment of malignant tumors. To enhance its effectiveness, two critical issues should be carefully dealt with, i.e., reliably predicting therapy outcomes to adapt undergoing treatment planning for individual patients, and accurately segmenting tumor volumes to maximize radiation delivery in tumor tissues while minimize side effects in adjacent organs at risk. Positron emission tomography with radioactive tracer fluorine-18 fluorodeoxyglucose (FDG-PET) can noninvasively provide significant information of the functional activities of tumor cells. In this thesis, the goal of our study consists of two parts: 1) to propose reliable therapy outcome prediction system using primarily features extracted from FDG-PET images; 2) to propose automatic and accurate algorithms for tumor segmentation in PET and PET-CT images. The theory of belief functions is adopted in our study to model and reason with uncertain and imprecise knowledge quantified from noisy and blurring PET images. In the framework of belief functions, a sparse feature selection method and a low-rank metric learning method are proposed to improve the classification accuracy of the evidential K-nearest neighbor classifier learnt by high-dimensional data that contain unreliable features. Based on the above two theoretical studies, a robust prediction system is then proposed, in which the small-sized and imbalanced nature of clinical data is effectively tackled. To automatically delineate tumors in PET images, an unsupervised 3-D segmentation based on evidential clustering using the theory of belief functions and spatial information is proposed. This mono-modality segmentation method is then extended to co-segment tumor in PET-CT images, considering that these two distinct modalities contain complementary information to further improve the accuracy. All proposed methods have been performed on clinical data, giving better results comparing to the state of the art ones.

近幾年來遊戲軟硬體的進步以及遊玩人數的增加，虛擬世界中的使用者行為已經開始受到注目，也有研究指出人們在虛擬世界的行為會反應他們在現實世界的行為並且交互影響。現今最熱門的線上遊戲更是提供多樣化的機制讓玩家們進行合作、競爭、交流等活動，遊戲開發者也會根據不同的目的開始分析玩家的行為，希望能藉此發現遊戲中更多的可能性。 遊戲的種類繁多，遊玩機制也相當多元，目前是以MOBA這類的線上遊戲最為熱門、擁有最多的玩家基數，MOBA是基於團隊合作的對戰型遊戲，玩家可以自由選擇多種職業（或稱作角色）的其中一種並和其他4位玩家組成隊伍，而對手也是同樣由5位玩家組成的隊伍。這類遊戲最大特色是職業的組合關係以及玩家之間的合作關係。在各個遊戲論壇或電競場合中，玩家們對於找出最佳的團隊組成或遊戲技巧提高勝率的分析相當熱衷，但在學術研究領域上目前針對線上遊戲團隊還沒有太多深入的研究。 本研究的目標旨在提出一個結合資料探勘與社群網路分析的方法來分析玩家與團隊績效之間的關係，並用於團隊績效預測與團隊組成上，藉此進行隊友的推薦。首先從抓取來的資料中取出三種玩家與英雄之間的關係，考量玩家的合作關係與英雄的組合關係，藉此篩選出具有高相關度的玩家作為推薦候選人。而在團隊績效預測的部分，取出對玩家個人表現或團隊表現具有影響的特徵值，並分析勝利的玩家或團隊通常會具備什麼樣的特質，再進行團隊表現的預測模型的建置。最後再結合兩者推薦出適合此隊伍的隊友供團隊選擇。 / Multiplayer online battle arenas (MOBA) is a subgenre of strategy games and has become the most popular online game genres recently. Teams of players could fight against each other in arena environments. To find good team members when playing MOBA is a challenge. In this thesis, we proposed a team member recommender mechanism to recommend team members for MOBA. The proposed mechanism first takes the team chemistry into consideration and generates the candidates based on the cooperation history among players and associated heroes. Then the proposed win/lose prediction model is employed to predict the win rate of each candidate by considering characteristics and proficiency of players and associated heroes. The recommended team members are ranked according to the predicted win rates. The experiments show that the proposed win/lose prediction model achieves approximately 91.6% accuracy and our mechanism could recommend players who have close cooperation with query players instead of considering the win rate only. Our proposed method could help the team formation and may enhance team performance of the on-line game.

Les lésions traumatiques de la moelle épinière entraînent de graves conséquences d’un point de vue personnel, physique et social chez les individus qui en sont victimes. La prise en charge médicale et chirurgicale de ces patients évolue au fil de l’amélioration des connaissances sur ce qui favorise la récupération neurologique et la qualité de vie à long terme. Pour le chirurgien du rachis, les facteurs modifiables qui influencent de façon significative l’issue neurologique à long terme chez les blessés médullaires thoraco-lombaires sont peu explorés dans la littérature. Le délai entre le trauma et l’exécution du geste chirurgical est un de ces facteurs, mais la définition de chirurgie précoce chez cette population spécifique demeure à être objectivée. De plus, il n’y a pas de paramètres sur le scan préopératoire ayant été décrit pour aider la prise en charge en fonction de l’issue neurologique à long-terme. L’objectif général de ces travaux est de préciser ce qui influence la récupération neurologique chez les patients paraplégiques ayant subi une fracture dans la région thoraco-lombaire et évaluer l’impact de la morphologie de la fracture sur l’effet du délai entre le traumatisme et la chirurgie de décompression et de stabilisation de la colonne vertébrale. Le premier volet de ce mémoire concerne l’étude du seuil de délai chirurgical associé à une récupération neurologique optimale. Pour ce faire, une étude clinique rétrospective a été menée en évaluant plusieurs issues neurologiques à long terme chez une cohorte prospective de 35 patients blessés médullaires secondairement à un traumatisme vertébral de la région thoraco-lombaire. Déterminer de façon objective le seuil de délai optimal pour la récupération neurologique a été possible en utilisant une méthode statistique faisant intervenir des modèles de prédiction sous la forme d’arbres décisionnels élaborés par partition objective récursive. Cette méthode a démontré que la chirurgie de décompression et de stabilisation entreprise dans les 21 heures suivant le moment du traumatisme augmente la probabilité d’améliorer l’état neurologique 12 mois après le traumatisme, en termes de sévérité (grade) de la lésion et du niveau neurologique. Le deuxième volet du mémoire concerne l’étude de la morphologie de la fracture la plus commune de la région thoraco-lombaire, la fracture de type « burst ». De nombreux paramètres radiologiques sont connus et définissent ce type de fracture mais aucun n’a été bien évalué en fonction de la récupération neurologique à long terme. Une deuxième étude clinique rétrospective implique l’étude du scan préopératoire à la recherche de paramètres reliés à l’issue neurologique chez les blessés médullaires avec atteinte motrice sévère. Trois caractéristiques morphologiques fortement associées à la récupération ont été identifiées : la présence d’une fracture complète de la lame, le recul de plus de 4 mm de la portion inférieure du mur postérieur du corps vertébral et la présence de comminution du fragment de corps vertébral rétropulsé dans le canal spinal. Ces paramètres sont des facteurs de pronostic défavorable de récupération neurologique plus importants que l’atteinte neurologique initiale ou l’estimation du degré d’énergie impliquée durant le traumatisme. Puisque ces paramètres décrivent la géométrie du canal spinal endommagé lors d’une fracture de type « burst », ils offrent un reflet de l’énergie locale dissipée dans le canal spinal et transmise aux éléments neuraux. Le troisième volet du mémoire implique l’intégration des nouvelles connaissances issues des deux articles présentés, à la recherche de l’influence de certains paramètres morphologiques sur l’effet de la chirurgie précoce sur la récupération neurologique. Les analyses complémentaires effectuées sur la cohorte de patients atteints de fracture de type « burst » n’ont pas démontré que l’avantage procuré par une chirurgie de décompression et stabilisation précoce était modifié ou altéré par la présence d’un des paramètres démontrés comme importants d’un point de vue neurologique. Ces travaux permettent de mieux guider le chirurgien du rachis dans la planification du geste chirurgical de par une meilleure compréhension des facteurs prédictifs de l’issue neurologique à long terme. En déterminant un seuil de délai objectif optimal de 21 heures, ils permettent d’établir une recommandation pour la définition même de la chirurgie précoce chez le blessé médullaire thoraco-lombaire. Ils proposent également une base pour l’étude subséquente de nouveaux paramètres clés quantifiables sur le scan préopératoire, un examen essentiel et disponible chez tous les patients, et de leur relation potentielle avec le choix de l’approche chirurgicale idéale ainsi qu’avec de multiples issues neurologiques et non-neurologiques. / Traumatic spinal cord injury (TSCI) is a debilitating condition that leads to many adverse consequences on a personal, physical and social standpoint for the injured victim. Medical and surgical care evolved along with the progression of understanding regarding what factors lead to better neurological recovery and overall quality of life in paralyzed patients. With respect to surgical care, modifiable factors significantly related to neurological recovery in thoracolumbar TSCI are not well known. In this regard, the optimal timing threshold for surgical spinal decompression and stabilization has not been demonstrated objectively. Moreover, there are no radiological parameter on the pre-operative computed tomography scan (CT scan) that have been shown to predict long term neurological outcome. The main goal of the presented work is to provide precise identification of such factors, and therefore evaluate the impact of the spine fracture specific morphological features on the effect of early surgical care. The first part involves the assessment of the optimal surgical timing threshold for neurological recovery. A retrospective clinical study was conducted to evaluate several neurological outcome measures in a prospective cohort of 35 thoracolumbar TSCI patients. Thresholds were obtained from the elaboration of prediction models with the use of Classification And Regression Tree (CART) statistical analysis. The first article demonstrated that for optimal recovery of the neurological level of injury, a timing threshold of a maximum of 21 hours should ideally be respected between the traumatic event and the beginning of the surgical intervention. The second part encompasses the study of the morphology of the fractured vertebrae in thoracolumbar burst fractures. Many radiological descriptors are used to describe these severe spine compression injuries but few have been evaluated with regards to neurological recovery. A second retrospective clinical study was conducted and associated a thorough examination of the preoperative CT scan reconstructions to the assessment of long term neurological outcome. Three morphologic parameters were found to be linked to poor prognostic of neurological recovery: complete lamina fracture, comminution of the posteriorly retropulsed fragment and vertebral body postero-inferior corner translation of 4 mm or more. Such features, all three describing the disrupted anatomy of the spinal canal, could be potential indicators of the amount of energy locally dissipated to the neural elements. These parameters were found to be more important to predict neurological outcome than the initial neurologic examination and global trauma energy indicators. The third part integrates the notions derived from the two presented studies and aims to assess for the influence of the presence of specific fracture parameters on the effect of early surgery regarding neurological outcome. Additional analyses did not show that the advantage of early surgery, defined in the first article, was influenced by the presence of any of the relevant fracture features demonstrated in the second article. Therefore, this work emphasizes on the importance of early surgery for better neurological recovery and serves to guide the surgeon in planning the timing of the intervention. Defining the concept of early surgery is key in implementing future retrospective or prospective research protocols. It also highlights the importance of new morphological features of the most common type of thoracolumbar fracture. It sets standards for further research involving preoperative CT scan parameters and their potential relationship with surgical approach, neurological and non-neurological outcomes.