Clustering Lab value working with medical data

Data mining is a relatively new field of research that its objective is to acquire knowledge from large amounts of data. In medical and health care areas, due to regulations and due to the availability of computers, a large amount of data is becoming available [27]. On the one hand, practitioners are expected to use all this data in their work but, at the same time, such a large amount of data cannot be processed by humans in a short time to make diagnosis, prognosis and treatment schedules. A major objective of this thesis is to evaluate data mining tools in medical and health care applications to develop a tool that can help make rather accurate decisions. In this thesis, the goal is finding a pattern among patients who got pneumonia by clustering of lab data values which have been recorded every day. By this pattern we can generalize it to the patients who did not have been diagnosed by this disease whose lab values shows the same trend as pneumonia patients does. There are 10 tables which have been extracted from a big data base of a hospital in Jena for my work .In ICU (intensive care unit), COPRA system which is a patient management system has been used. All the tables and data stored in German Language database.

Evaluating balance, stability and gait symmetry of stroke patients using kinematic and dynamic gait lab data

Dissertação de mestrado integrado em Engenharia Biomédica

A multidimensional segmentation evaluation for medical image data.

Evaluation of segmentation methods is a crucial aspect in image processing, especially in the medical imaging field, where small differences between segmented regions in the anatomy can be of paramount importance. Usually, segmentation evaluation is based on a measure that depends on the number of segmented voxels inside and outside of some reference regions that are called gold standards. Although some other measures have been also used, in this work we propose a set of new similarity measures, based on different features, such as the location and intensity values of the misclassified voxels, and the connectivity and the boundaries of the segmented data. Using the multidimensional information provided by these measures, we propose a new evaluation method whose results are visualized applying a Principal Component Analysis of the data, obtaining a simplified graphical method to compare different segmentation results. We have carried out an intensive study using several classic segmentation methods applied to a set of MRI simulated data of the brain with several noise and RF inhomogeneity levels, and also to real data, showing that the new measures proposed here and the results that we have obtained from the multidimensional evaluation, improve the robustness of the evaluation and provides better understanding about the difference between segmentation methods.

Fertility-preservation counselling and treatment for medical reasons: data from a multinational network of over 5000 women.

Fertility-preservation techniques for medical reasons are increasingly offered in national networks. Knowledge of the characteristics of counselled patients and techniques used are essential. The FertiPROTEKT network registry was analysed between 2007 and 2013, and included up to 85 university and non-university centres in Germany, Austria and Switzerland; 5159 women were counselled and 4060 women underwent fertility preservation. In 2013, fertility-preservation counselling for medical reasons increased significantly among nullipara and women aged between 21 and 35 years (n = 1043; P < 0.001). Frequency of GnRH applications slowly decreased, whereas tissue, oocytes and zygote cryopreservation increased. In 2013, women with breast cancer mainly opted for tissue freezing, whereas women with lymphoma opted for GnRH agonist. Women younger than 20 years predominantly opted for GnRH agonists and ovarian tissue cryopreservation; women aged between 20 and 40 years underwent a variety of techniques; and women over 40 years opted for GnRH agonists. The average number of aspirated oocytes per stimulation cycle decreased as age increased (< 30 years: 12.9; 31-35 years: 12.3; 36-46: 9.0; > 41 years: 5.7). For ovarian tissue cryopreservation, removal and cryopreservation of fewer than one ovary was preferred and carried out in 97% of cases in 2013.

Cloud Computing Service for Managing Large Medical Image Data-Sets Using Balanced Collaborative Agents

Managing large medical image collections is an increasingly demanding important issue in many hospitals and other medical settings. A huge amount of this information is daily generated, which requires robust and agile systems. In this paper we present a distributed multi-agent system capable of managing very large medical image datasets. In this approach, agents extract low-level information from images and store them in a data structure implemented in a relational database. The data structure can also store semantic information related to images and particular regions. A distinctive aspect of our work is that a single image can be divided so that the resultant sub-images can be stored and managed separately by different agents to improve performance in data accessing and processing. The system also offers the possibility of applying some region-based operations and filters on images, facilitating image classification. These operations can be performed directly on data structures in the database.

Feasibility of developing a medical condition data collection system for driver licensing. Final report.

National Highway Traffic Safety Administration, Office of Driver and Pedestrian Research, Washington, D.C.

Architecture of a community medical history data base /

"UIUCDCS-R-73-589"

Development of procedures for the design, optimization and manufacturing of customized orthopaedic and trauma implants: Geometrical/anatomical modelling from 3D medical imaging

Tese de Doutoramento (Programa Doutoral em Engenharia Biomédica)

Medical aspects of helicopter rescue missions involving winching of a physician

Introduction: Whereas the use of helicopters as a rapid means toreach victims and to bring them to a secure place is well-recognized,very few data are available about the value of winching physicians toprovide medical care for the victims directly on-site. We sought to studythe medical aspects of alpine helicopter rescue operations involving thewinching of an emergency physician to the victim.Methods: We retrospectively reviewed the medical reports of a singlehelicopter-based emergency medical service. Data from 1 January 2003to 31 December 2008 were analyzed. Cases with emergency callindicating that the victim was deceased were excluded. Data includedthe category (trauma or illnesses), and severity (NACA score) of theinjuries, along with the main medical procedures performed on site.Results: 9879 rescue missions were conducted between 1 January2003 and 31 December 2008. The 921 (9.3%) missions involvingwinching of the emergency physician were analysed. 840 (91%)patients suffered from trauma-related injuries. The cases of the 81 (9%)people presenting with medical emergencies were, when compared tothe trauma victims, significantly more severe according to the NACAindex (p <0.001). Overall, 246 (27%) patients had a severe injury orillness, namely, a potential or overt vital threat (NACA score between4-6, table 1). A total of 478 (52%) patients required administration ofmajor analgesics: fentanyl (443 patients; 48%), ketamine (42 patients;5%) or morphine (7 patients; 1%). The mean dose of fentanyl was 188micrograms (range 25-750, SD 127). Major medical interventions wereperformed 72 times on 39 (4%) patients (table 2).Conclusions: The severity of the patients' injuries or illnesses alongwith the high proportion of medical procedures performed directlyon-site validate emergency physician winching for advanced life supportprocedures and analgesia.

Higher red blood cell distribution width is associated with a worse virologic and clinical situation in HIV-infected patients.

Background A high level of red blood cell distribution width (RDW) is a novel prognostic marker that may reflect an underlying inflammatory state. It has recently shown that when increased, it is related to cardiovascular disease, mortality, and metabolic syndrome (MetS) in the general population. Objectives To analyse the potential relation between high levels of RDW and cardiovascular risk (CVR) and MetS in HIVpatients. Patients and methods Observational, cross-sectional study of a series of HIVoutpatients attended in our Hospital. Demographic, anthropometric, clinical, and fasting lab data were recorded in all cases. CVR at 10 years was evaluated by Framingham equation, and MetS diagnosed according to the National Cholesterol Education Program criteria. Statistic program: SPSS 17.0. Results 666 patients were included, 79.3% were men, and mean age was 44.7 years. Mean CD4 count was 506 cells/ mm3 , 87.5% of the patients were on antiretroviral therapy, and 85.3% had undetectable HIV viral load. Mean RDW was 13.07% (range: 7.7-33.6%; 75th percentile 14,1%), with a prevalence of MetS of 15.7, 9.3, 18.8 and 16.6% first through fourth RDW quartile, and of patients with CVR >20% of 8.4, 4.0, 4.4 and 6.4%, respectively (p>0,05). The highest quartile of RDW (>14.1%) was associated with AIDS (OR 1.6, 95%CI 1.0-2.4; p 0.02), detectable HIV viral load (OR 1.5, 95%CI 1.01-2.4; p 0.04), and hypertension (OR 2.3, 95%CI 1.4-4.0; p 0.001). Conclusions In HIV-infected outpatients, higher RDW is related with detectable HIV viral load and with AIDS. Although it was associated with a traditional CVR factor as hypertension, we found no relation with MetS nor with higher CVR.

A laboratory study of the transfer of U-234 and U-238 during water-rock interactions in the Carnmenellis granite (Cornwall, England) and implications for the interpretation of field data

Laboratory time-scale experiments were conducted on gravels from the Carnmenellis granite, Cornwall, England, with the purpose of evaluating the release of natural uranium isotopes to the water phase. The implications of these results for the production of enhanced U-234/U-238 activity ratios in Cornish groundwaters are discussed. It is suggested that the U-234/U-238 lab data can be used to interpret activity ratios from Cornwall, even when the observed inverse relationship between dissolved U and U-234/U-238 in leachates/etchates is taken into account. (C) 2001 Elsevier B.V. Ltd. All rights reserved.

The application of medical informatics to the veterinary management programs at companion animal practices in Alberta, Canada: a case study.

Companion animals closely share their domestic environment with people and have the potential to, act as sources of zoonotic diseases. They also have the potential to be sentinels of infectious and noninfectious, diseases. With the exception of rabies, there has been minimal ongoing surveillance of, companion animals in Canada. We developed customized data extraction software, the University of, Calgary Data Extraction Program (UCDEP), to automatically extract and warehouse the electronic, medical records (EMR) from participating private veterinary practices to make them available for, disease surveillance and knowledge creation for evidence-based practice. It was not possible to build, generic data extraction software; the UCDEP required customization to meet the specific software, capabilities of the veterinary practices. The UCDEP, tailored to the participating veterinary practices', management software, was capable of extracting data from the EMR with greater than 99%, completeness and accuracy. The experiences of the people developing and using the UCDEP and the, quality of the extracted data were evaluated. The electronic medical record data stored in the data, warehouse may be a valuable resource for surveillance and evidence-based medical research.

Second, do less harm: The state of states' medical error reporting programs

Statement of the problem and public health significance. Hospitals were designed to be a safe haven and respite from disease and illness. However, a large body of evidence points to preventable errors in hospitals as the eighth leading cause of death among Americans. Twelve percent of Americans, or over 33.8 million people, are hospitalized each year. This population represents a significant portion of at risk citizens exposed to hospital medical errors. Since the number of annual deaths due to hospital medical errors is estimated to exceed 44,000, the magnitude of this tragedy makes it a significant public health problem. ^ Specific aims. The specific aims of this study were threefold. First, this study aimed to analyze the state of the states' mandatory hospital medical error reporting six years after the release of the influential IOM report, "To Err is Human." The second aim was to identify barriers to reporting of medical errors by hospital personnel. The third aim was to identify hospital safety measures implemented to reduce medical errors and enhance patient safety. ^ Methods. A descriptive, longitudinal, retrospective design was used to address the first stated objective. The study data came from the twenty-one states with mandatory hospital reporting programs which report aggregate hospital error data that is accessible to the public by way of states' websites. The data analysis included calculations of expected number of medical errors for each state according to IOM rates. Where possible, a comparison was made between state reported data and the calculated IOM expected number of errors. A literature review was performed to achieve the second study aim, identifying barriers to reporting medical errors. The final aim was accomplished by telephone interviews of principal patient safety/quality officers from five Texas hospitals with more than 700 beds. ^ Results. The state medical error data suggests vast underreporting of hospital medical errors to the states. The telephone interviews suggest that hospitals are working at reducing medical errors and creating safer environments for patients. The literature review suggests the underreporting of medical errors at the state level stems from underreporting of errors at the delivery level. ^

Data quality in trauma transfusion studies and the impact of missing data on predicting massive transfusion

Maximizing data quality may be especially difficult in trauma-related clinical research. Strategies are needed to improve data quality and assess the impact of data quality on clinical predictive models. This study had two objectives. The first was to compare missing data between two multi-center trauma transfusion studies: a retrospective study (RS) using medical chart data with minimal data quality review and the PRospective Observational Multi-center Major Trauma Transfusion (PROMMTT) study with standardized quality assurance. The second objective was to assess the impact of missing data on clinical prediction algorithms by evaluating blood transfusion prediction models using PROMMTT data. RS (2005-06) and PROMMTT (2009-10) investigated trauma patients receiving ≥ 1 unit of red blood cells (RBC) from ten Level I trauma centers. Missing data were compared for 33 variables collected in both studies using mixed effects logistic regression (including random intercepts for study site). Massive transfusion (MT) patients received ≥ 10 RBC units within 24h of admission. Correct classification percentages for three MT prediction models were evaluated using complete case analysis and multiple imputation based on the multivariate normal distribution. A sensitivity analysis for missing data was conducted to estimate the upper and lower bounds of correct classification using assumptions about missing data under best and worst case scenarios. Most variables (17/33=52%) had <1% missing data in RS and PROMMTT. Of the remaining variables, 50% demonstrated less missingness in PROMMTT, 25% had less missingness in RS, and 25% were similar between studies. Missing percentages for MT prediction variables in PROMMTT ranged from 2.2% (heart rate) to 45% (respiratory rate). For variables missing >1%, study site was associated with missingness (all p≤0.021). Survival time predicted missingness for 50% of RS and 60% of PROMMTT variables. MT models complete case proportions ranged from 41% to 88%. Complete case analysis and multiple imputation demonstrated similar correct classification results. Sensitivity analysis upper-lower bound ranges for the three MT models were 59-63%, 36-46%, and 46-58%. Prospective collection of ten-fold more variables with data quality assurance reduced overall missing data. Study site and patient survival were associated with missingness, suggesting that data were not missing completely at random, and complete case analysis may lead to biased results. Evaluating clinical prediction model accuracy may be misleading in the presence of missing data, especially with many predictor variables. The proposed sensitivity analysis estimating correct classification under upper (best case scenario)/lower (worst case scenario) bounds may be more informative than multiple imputation, which provided results similar to complete case analysis.^