Browsing by Subject "Classification"

Sort by: Order: Results:

Now showing items 1-14 of 14
  • Bjorck, M.; Kirkpatrick, A. W.; Cheatham, M.; Kaplan, M.; Leppäniemi, Ari; De Waele, J. J. (2016)
    Background: In 2009, a classification system for the open abdomen was introduced. The aim of such a classification is to aid the (1) description of the patient's clinical course; (2) standardization of clinical guidelines for guiding open abdomen management; and (3) facilitation of comparisons between studies and heterogeneous patient populations, thus serving as an aid in clinical research. Methods: As part of the revision of the definitions and clinical guidelines performed by the World Society of the Abdominal Compartment Syndrome, this 2009 classification system was amended following a review of experiences in teaching and research and published as part of updated consensus statements and clinical practice guidelines in 2013. Among 29 articles citing the 2009 classification system, nine were cohort studies. They were reviewed as part of the classification revision process. A total of 542 patients (mean: 60, range: 9-160) had been classified. Two problems with the previous classification system were identified: the definition of enteroatmospheric fistulae, and that an enteroatmospheric fistula was graded less severe than a frozen abdomen. Results: The following amended classification was proposed: Grade 1, without adherence between bowel and abdominal wall or fixity of the abdominal wall (lateralization), subdivided as follows: 1A, clean; 1B, contaminated; and 1C, with enteric leak. An enteric leak controlled by closure, exteriorization into a stoma, or a permanent enterocutaneous fistula is considered clean. Grade 2, developing fixation, subdivided as follows: 2A, clean; 2B, contaminated; and 2C, with enteric leak. Grade 3, frozen abdomen, subdivided as follows: 3A clean and 3B contaminated. Grade 4, an established enteroatmospheric fistula, is defined as a permanent enteric leak into the open abdomen, associated with granulation tissue. Conclusions: The authors believe that, with these changes, the requirements on a functional and dynamic classification system, useful in both research and training, will be fulfilled. We encourage future investigators to apply the system and report on its merits and constraints.
  • Simsek, Burak (Helsingin yliopisto, 2020)
    In this study, a classification scheme is implemented to obtain high resolution snow cover information from Sentinel-2 data using a very simple Bayesian Network (Naive-Bayes) that is trained with ground snow measurement data. Performance comparison of using Bayesian/non-Bayesian Naive-Bayes, different feature sets and different discretization methods is conducted. Results show that Bayesian NB performs the best with up to 0.88 classification accuracy for snow/no-snow classification. Use of most relevant spectral bands rather than all available bands provided improvement in some cases but also performed slighty worse in some, hence not giving a clear answer. However, effect of discretization method was clear, chimerge performed better than equal width binning but it was much slower to a point that it was not practical to discretisize a full Sentinel-2 image’s pixels.
  • Koolen, Ninah; Oberdorfer, Lisa; Rona, Zsofia; Giordano, Vito; Werther, Tobias; Klebermass-Schrehof, Katrin; Stevenson, Nathan; Vanhatalo, Sampsa (2017)
    Objective: To develop a method for automated neonatal sleep state classification based on EEG that can be applied over a wide range of age. Methods: We collected 231 EEG recordings from 67 infants between 24 and 45 weeks of postmenstrual age. Ten minute epochs of 8 channel polysomnography (N = 323) from active and quiet sleep were used as a training dataset. We extracted a set of 57 EEG features from the time, frequency, and spatial domains. A greedy algorithm was used to define a reduced feature set to be used in a support vector machine classifier. Results: Performance tests showed that our algorithm was able to classify quiet and active sleep epochs with 85% accuracy, 83% sensitivity, and 87% specificity. The performance was not substantially lowered by reducing the epoch length or EEG channel number. The classifier output was used to construct a novel trend, the sleep state probability index, that improves the visualisation of brain state fluctuations. Conclusions: A robust EEG-based sleep state classifier was developed. It performs consistently well across a large span of postmenstrual ages. Significance: This method enables the visualisation of sleep state in preterm infants which can assist clinical management in the neonatal intensive care unit. (C) 2017 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.
  • Lammers, Gert Jan; Bassetti, Claudio L.A.; Dolenc-Groselj, Leja; Jennum, Poul J.; Kallweit, Ulf; Khatami, Ramin; Lecendreux, Michel; Manconi, Mauro; Mayer, Geert; Partinen, Markku; Plazzi, Giuseppe; Reading, Paul J.; Santamaria, Joan; Sonka, Karel; Dauvilliers, Yves (2020)
    Summary The aim of this European initiative is to facilitate a structured discussion to improve the next edition of the International Classification of Sleep Disorders (ICSD), particularly the chapter on central disorders of hypersomnolence. The ultimate goal for a sleep disorders classification is to be based on the underlying neurobiological causes of the disorders with clear implication for treatment or, ideally, prevention and or healing. The current ICSD classification, published in 2014, inevitably has important shortcomings, largely reflecting the lack of knowledge about the precise neurobiological mechanisms underlying the majority of sleep disorders we currently delineate. Despite a clear rationale for the present structure, there remain important limitations that make it difficult to apply in routine clinical practice. Moreover, there are indications that the current structure may even prevent us from gaining relevant new knowledge to better understand certain sleep disorders and their neurobiological causes. We suggest the creation of a new consistent, complaint driven, hierarchical classification for central disorders of hypersomnolence; containing levels of certainty, and giving diagnostic tests, particularly the MSLT, a weighting based on its specificity and sensitivity in the diagnostic context. We propose and define three diagnostic categories (with levels of certainty): 1/“Narcolepsy” 2/“Idiopathic hypersomnia”, 3/“Idiopathic excessive sleepiness” (with subtypes)
  • Longato, Enrico; Acciaroli, Giada; Facchinetti, Andrea; Hakaste, Liisa; Tuomi, Tiinamaija; Maran, Alberto; Sparacino, Giovanni (2018)
    Many glycaemic variability (GV) indices extracted from continuous glucose monitoring systems data have been proposed for the characterisation of various aspects of glucose concentration profile dynamics in both healthy and non-healthy individuals. However, the inter-index correlations have made it difficult to reach a consensus regarding the best applications or a subset of indices for clinical scenarios, such as distinguishing subjects according to diabetes progression stage. Recently, a logistic regression-based method was used to address the basic problem of differentiating between healthy subjects and those affected by impaired glucose tolerance (IGT) or type 2 diabetes (T2D) in a pool of 25 GV-based indices. Whereas healthy subjects were classified accurately, the distinction between patients with IGT and T2D remained critical. In the present work, by using a dataset of CGM time-series collected in 62 subjects, we developed a polynomial-kernel support vector machine-based approach and demonstrated the ability to distinguish between subjects affected by IGT and T2D based on a pool of 37 GV indices complemented by four basic parameters—age, sex, BMI, and waist circumference—with an accuracy of 87.1%.
  • WSES-AAST Expert Panel; Coccolini, Federico; Moore, Ernest E.; Kluger, Yoram; Leppäniemi, Ari; Catena, Fausto (2019)
    Renal and urogenital injuries occur in approximately 10-20% of abdominal trauma in adults and children. Optimal management should take into consideration the anatomic injury, the hemodynamic status, and the associated injuries. The management of urogenital trauma aims to restore homeostasis and normal physiology especially in pediatric patients where non-operative management is considered the gold standard. As with all traumatic conditions, the management of urogenital trauma should be multidisciplinary including urologists, interventional radiologists, and trauma surgeons, as well as emergency and ICU physicians. The aim of this paper is to present the World Society of Emergency Surgery (WSES) and the American Association for the Surgery of Trauma (AAST) kidney and urogenital trauma management guidelines.
  • Lindahl, Jan (2019)
  • Jernman, Juha (2015)
    Neuroendocrine tumors of the rectum were regarded as benign, when Oberndorfer originally described the entity in 1907. Later, he acknowledged that some neuroendocrine tumors (or carcinoids, the term at that time) behave in a more aggressive manner, and a few of them even had the potential to metastasize with poor outcome. In the novel World Health Organization (WHO) classification launched in 2010, all neuroendocrine tumors of the gastrointestinal (GI) tract are malignant. In this classification, tumors of every part of the GI tract are graded uniformly according to proliferation index and mitotic frequency, whereas the TNM-classification (tumor, node, metastasis) is specific for each site. Around 10% of gastroenteropancreatic neuroendocrine tumors (GEP-NETs) occur in the rectum. The tumor series comprised 73 rectal NETs, with the main objective being to study the prognostic value of the WHO 2010 classification in rectal NETs: additionally, as the WHO classification has been used for a rather short time, tumor markers were tested to find a good, reliable prognostic tool. The WHO 2010 had excellent prognostic significance; none of the G1- NETs (grade 1) metastasized, whereas G2-NETs were often disseminated, some of them at initial presentation. Metastatic NETs have a poor prognosis. Cell-cycle antigen cyclin A also correlated with prognosis, and G2-NETs with high cyclin A expression were all metastatic. Transcription factor prospero homeobox 1 (PROX1) was immunohistochemically positive in a significant proportion of rectal NETs, and showed a correlation with metastatic potential and survival. It was also possible to conclude that the novel stem cell-associated factor HES77 (human embryonic stem cell factor 77) correlated well with rectal NETs metastatic potential and prognosis. These results support the validity of the WHO 2010 classification in rectal NETs. In view of this study, for patients with a rectal G1-NET, one follow-up endoscopy to exclude local recurrence might suffice. Intensive follow-up does not seem indicated, as metastatic potential is very low. As to G2-NETs, a thorough work-up is recommended, since most of these tumors disseminate eventually, some after several years, and a standard 5-year follow-up may not suffice. PROX1-positivity suggests that colorectal adenocarcinoma and rectal NET may, to some extent, share the same pathway in oncogenesis, which could lead to future therapeutic applications.
  • Näsi, Roope; Honkavaara, Eija; Blomqvist, Minna; Lyytikäinen-Saarenmaa, Päivi Marja Emilia; Hakala, Teemu; Viljanen, Niko; Kantola, Tuula Anneli; Holopainen, Markus Edvard (2018)
    Climate-related extended outbreaks and range shifts of destructive bark beetle species pose a serious threat to urban boreal forests in North America and Fennoscandia. Recent developments in low-cost remote sensing technologies offer an attractive means for early detection and management of environmental change. They are of great interest to the actors responsible for monitoring and managing forest health. The objective of this investigation was to develop, assess, and compare automated remote sensing procedures based on novel, low-cost hyperspectral imaging technology for the identification of bark beetle infestations at the individual tree level in urban forests. A hyperspectral camera based on a tunable Fabry-Perot interferometer was operated from a small, unmanned airborne vehicle (UAV) platform and a small Cessna-type aircraft platform. This study compared aspects of using UAV datasets with a spatial extent of a few hectares (ha) and a ground sample distance (GSD) of 10-12 cm to the aircraft data covering areas of several km(2) and having a GSD of 50 cm. An empirical assessment of the automated identification of mature Norway spruce (Picea abies L. Karst.) trees suffering from infestation (representing different colonization phases) by the European spruce bark beetle (Ips typographus L.) was carried out in the urban forests of Lahti, a city in southern Finland. Individual spruces were classified as healthy, infested, or dead. For the entire test area, the best aircraft data results for overall accuracy were 79% (Cohen's kappa: 0.54) when using three crown color classes (green as healthy, yellow as infested, and gray as dead). For two color classes (healthy, dead) in the same area, the best overall accuracy was 93% (kappa: 0.77). The finer resolution UAV dataset provided better results, with an overall accuracy of 81% (kappa: 0.70), compared to the aircraft results of 73% (kappa: 0.56) in a smaller sub-area. The results showed that novel, low-cost remote sensing technologies based on individual tree analysis and calibrated remote sensing imagery offer great potential for affordable and timely assessments of the health condition of vulnerable urban forests.
  • Sternby, Hanna; Verdonk, Robert C.; Aguilar, Guadalupe; Dimova, Alexandra; Ignatavicius, Povilas; Ilzarbe, Lucas; Koiva, Peeter; Lantto, Eila; Loigom, Tonis; Penttilä, Anne; Regner, Sara; Rosendahl, Jonas; Strahinova, Vanya; Zackrisson, Sophia; Zviniene, Kristina; Bollen, Thomas L. (2016)
    Background: For consistent reporting and better comparison of data in research the revised Atlanta classification (RAC) proposes new computed tomography (CT) criteria to describe the morphology of acute pancreatitis (AP). The aim of this study was to analyse the interobserver agreement among radiologists in evaluating CT morphology by using the new RAC criteria in patients with AP. Methods: Patients with a first episode of AP who obtained a CT were identified and consecutively enrolled at six European centres backwards from January 2013 to January 2012. A local radiologist at each center and a central expert radiologist scored the Cfs separately using the RAC criteria. Center dependent and independent interobserver agreement was determined using Kappa statistics. Results: In total, 285 patients with 388 CTs were included. For most CT criteria, interobserver agreement was moderate to substantial. In four categories, the center independent kappa values were fair: extrapancreatic necrosis (EXPN) (0.326), type of pancreatitis (0.370), characteristics of collections (0.408), and appropriate term of collections (0.356). The fair kappa values relate to discrepancies in the identification of extrapancreatic necrotic material. The local radiologists diagnosed EXPN (33% versus 59%, P <0.0001) and non-homogeneous collections (35% versus 66%, P <0.0001) significantly less frequent than the central expert. Cases read by the central expert showed superior correlation with clinical outcome. Conclusion: Diagnosis of EXPN and recognition of non-homogeneous collections show only fair agreement potentially resulting in inconsistent reporting of morphologic findings. (C) 2016 IAP and EPC. Published by Elsevier B.V. All rights reserved.
  • Coccolini, Federico; Montori, Giulia; Catena, Fausto; Kluger, Yoram; Biffl, Walter; Moore, Ernest E.; Reva, Viktor; Bing, Camilla; Bala, Miklosh; Fugazzola, Paola; Bahouth, Hany; Marzi, Ingo; Velmahos, George; Ivatury, Rao; Soreide, Kjetil; Horer, Tal; ten Broek, Richard; Pereira, Bruno M.; Fraga, Gustavo P.; Inaba, Kenji; Kashuk, Joseph; Parry, Neil; Masiakos, Peter T.; Mylonas, Konstantinos S.; Kirkpatrick, Andrew; Abu-Zidan, Fikri; Gomes, Carlos Augusto; Benatti, Simone Vasilij; Naidoo, Noel; Salvetti, Francesco; Maccatrozzo, Stefano; Agnoletti, Vanni; Gamberini, Emiliano; Solaini, Leonardo; Costanzo, Antonio; Celotti, Andrea; Tomasoni, Matteo; Khokha, Vladimir; Arvieux, Catherine; Napolitano, Lena; Handolin, Lauri; Pisano, Michele; Magnone, Stefano; Spain, David A.; de Moya, Marc; Davis, Kimberly A.; De Angelis, Nicola; Leppaniemi, Ari; Ferrada, Paula; Latifi, Rifat; Navarro, David Costa; Otomo, Yashuiro; Coimbra, Raul; Maier, Ronald V.; Moore, Frederick; Rizoli, Sandro; Sakakushev, Boris; Galante, Joseph M.; Chiara, Osvaldo; Cimbanassi, Stefania; Mefire, Alain Chichom; Weber, Dieter; Ceresoli, Marco; Peitzman, Andrew B.; Wehlie, Liban; Sartelli, Massimo; Di Saverio, Salomone; Ansaloni, Luca (2017)
    Spleen injuries are among the most frequent trauma-related injuries. At present, they are classified according to the anatomy of the injury. The optimal treatment strategy, however, should keep into consideration the hemodynamic status, the anatomic derangement, and the associated injuries. The management of splenic trauma patients aims to restore the homeostasis and the normal physiopathology especially considering the modern tools for bleeding management. Thus, the management of splenic trauma should be ultimately multidisciplinary and based on the physiology of the patient, the anatomy of the injury, and the associated lesions. Lastly, as the management of adults and children must be different, children should always be treated in dedicated pediatric trauma centers. In fact, the vast majority of pediatric patients with blunt splenic trauma can be managed non-operatively. This paper presents the World Society of Emergency Surgery (WSES) classification of splenic trauma and the management guidelines.
  • Abdul-Rahim, Azmil H.; VISTA Collaborators; Kaste, M. (2019)
    BackgroundInter-observer variability in stroke aetiological classification may have an effect on trial power and estimation of treatment effect. We modelled the effect of misclassification on required sample size in a hypothetical cardioembolic (CE) stroke trial.MethodsWe performed a systematic review to quantify the reliability (inter-observer variability) of various stroke aetiological classification systems. We then modelled the effect of this misclassification in a hypothetical trial of anticoagulant in CE stroke contaminated by patients with non-cardioembolic (non-CE) stroke aetiology. Rates of misclassification were based on the summary reliability estimates from our systematic review. We randomly sampled data from previous acute trials in CE and non-CE participants, using the Virtual International Stroke Trials Archive. We used bootstrapping to model the effect of varying misclassification rates on sample size required to detect a between-group treatment effect across 5000 permutations. We described outcomes in terms of survival and stroke recurrence censored at 90days.ResultsFrom 4655 titles, we found 14 articles describing three stroke classification systems. The inter-observer reliability of the classification systems varied from fair' to very good' and suggested misclassification rates of 5% and 20% for our modelling. The hypothetical trial, with 80% power and alpha 0.05, was able to show a difference in survival between anticoagulant and antiplatelet in CE with a sample size of 198 in both trial arms. Contamination of both arms with 5% misclassified participants inflated the required sample size to 237 and with 20% misclassification inflated the required sample size to 352, for equivalent trial power. For an outcome of stroke recurrence using the same data, base-case estimated sample size for 80% power and alpha 0.05 was n=502 in each arm, increasing to 605 at 5% contamination and 973 at 20% contamination.ConclusionsStroke aetiological classification systems suffer from inter-observer variability, and the resulting misclassification may limit trial power.Trial registrationProtocol available at reviewregistry540.
  • Hinkka, Markku; Lehto, Teemu; Heljanko, Keijo; Jung, Alexander (Springer-Verlag, 2018)
    Lecture Notes in Business Information Processing
    We consider the problem of classifying business process instances based on structural features derived from event logs. The main motivation is to provide machine learning based techniques with quick response times for interactive computer assisted root cause analysis. In particular, we create structural features from process mining such as activity and transition occurrence counts, and ordering of activities to be evaluated as potential features for classification. We show that adding such structural features increases the amount of information thus potentially increasing classification accuracy. However, there is an inherent trade-off as using too many features leads to too long run-times for machine learning classification models. One way to improve the machine learning algorithms' run-time is to only select a small number of features by a feature selection algorithm. However, the run-time required by the feature selection algorithm must also be taken into account. Also, the classification accuracy should not suffer too much from the feature selection. The main contributions of this paper are as follows: First, we propose and compare six different feature selection algorithms by means of an experimental setup comparing their classification accuracy and achievable response times. Second, we discuss the potential use of feature selection results for computer assisted root cause analysis as well as the properties of different types of structural features in the context of feature selection.
  • Kallela, Jenni; Jääskeläinen, Tiina; Kortelainen, Eija; Heinonen, Seppo; Kajantie, Eero; Kere, Juha; Kivinen, Katja; Pouta, Anneli; Laivuori, Hannele (2016)
    Background: The Finnish Pre-eclampsia Consortium (FINNPEC) case-control cohort consisting of 1447 pre-eclamptic and 1068 non-pre-eclamptic women was recruited during 2008-2011 to study genetic background of pre-eclampsia and foetal growth. Pre-eclampsia was defined by hypertension and proteinuria according to the American College of Obstetricians and Gynecologists (ACOG) 2002 classification. The ACOG Task Force Report on Hypertension in Pregnancy (2013) and The International Society for the Study of Hypertension in Pregnancy (ISSHP) (2014) have published new classifications, in which proteinuria is not necessary for diagnosis when specific symptoms are present. For diagnoses based on proteinuria, the ISSHP 2014 criteria raised its threshold to 2+ on dipstick. We studied how the new classifications would affect pre-eclampsia diagnoses in the FINNPEC cohort. Methods: We re-evaluated pre-eclampsia diagnosis using the ACOG 2013 and the ISSHP 2014 classifications in pre-eclamptic women whose proteinuria did not exceed 1+ on dipstick (n = 68), in women with gestational hypertension (n = 138) and in women with chronic hypertension (n = 66). Results: The number of women with pre-eclampsia increased 0.8 % (1459/1447) according to the ACOG 2013 criteria and 0.6 % (1455/1447) according to the ISSHP 2014 criteria. All 68 women with the amount of proteinuria not exceeding 1+ on dipstick diagnosed originally pre-eclamptic met the ACOG 2013 criteria but only 20 women (29.4 %) met the ISSHP 2014 criteria. Seven (5.1 %) and 35 (25.4 %) women with gestational hypertension were diagnosed with pre-eclampsia according to the ACOG 2013 and the ISSHP 2014 criteria, respectively. Correspondingly five (7.6 %) and 21 (31.8 %) women with chronic hypertension were diagnosed with pre-eclampsia according to the ACOG 2 013 and the ISSHP 2014 criteria. Conclusions: Only minor changes were observed in the total number of pre-eclamptic women in the FINNPEC cohort when comparing the ACOC 2002 classification with the ACOG 2013 and ISSHP 2014 classifications.