Over the past several decades rates of spine surgeries in the U.S. have increased dramatically. Spinal fusion surgery rates, in particular, have grown exponentially despite being one of the most costly, invasive, and controversial methods for treating patients suffering from back conditions. Furthermore, lumbar fusion surgeries continue to be performed at increasing rates despite a lack of scientific evidence and consensus that they are cost-effective and produce better clinical outcomes than less radical treatment of lower back pain. As a result, large amounts of healthcare dollars continue to be invested in these costly procedures which are potentially dangerous and have questionable efficacy in terms of improving patient outcomes. Importantly, there is a lack of population studies in the literature on spinal fusion surgeries from a health services research perspective. Therefore, the present research is a population based study using an administrative database and includes patients of all ages and payer types. The data used in the present study come from the Florida Agency for Health Care Administration (AHCA) and include all hospitalizations in Florida in 2010. The objective of the study is to analyze the incidence of spinal fusion surgeries in Florida hospitals for patients of all ages and payer types by demographic variables to understand who gets these surgeries and for which conditions. The first null hypothesis is that there are no statistically significant predictors of the incidence of lumbar/lumbosacral, dorsal/dorsolumbar spinal fusion surgeries in Florida hospitals. Logistic regression was used to analyze the incidence of fusion surgeries. The binary dependent variable was coded as a "1" for all patients who were a case (i.e. they received one of the five procedure codes being studied in the present research) and a "0" for all patients who were controls (meaning they did not receive any of the five fusion procedure codes). Logistic regression was used to predict the probability of an observation being a "1" given the independent variables included in the model. Additionally, hospital charges were analyzed to understand the associated hospital charges with these surgeries. The second null hypothesis is that there are no statistically significant predictors of the charges of Lumbar/Lumbosacral, Dorsal/Dorsolumbar spinal fusion surgeries in Florida Hospitals. A mixed effects model was used to test this hypothesis and the fixed effects which were included in the model were gender, age, race, principal payer, and principal procedure. A mixed effects model was chosen due to the fact that cases who had surgeries performed at the same hospital are not independent and therefore the data were clustered on hospitals. A random intercept term was used to address this fact. SAS software was used to complete all of the analyses. In 2010, there were 16,236 Lumbar/Lumbosacral, Dorsal/Dorsolumbar fusion surgery cases in Florida hospitals that were included in the case population and 21,856 individuals included in the control population for a total of 38,092 included in the study population. An understanding of who is most likely to receive a fusion surgery, at what age, and for which diagnoses, as has been done here, is extremely important. This knowledge can help researchers, policy makers, and physicians alike. Comprehensive physician practice guidelines for performing fusion surgeries still do not exist in the year 2013; therefore, in order to have the greatest impact, the efforts for creating the guidelines should be focused on those individuals who are most likely to receive fusions as shown for the first time by the data analyzed here. Given the high incidence of these surgeries in Florida alone, the need for practice guidelines cannot be overstated. The total hospital charges in Florida hospitals for the 16,236 cases were $2,095,413,584. Despite having the same principal diagnoses and a similar number of additional diagnoses, patients who received a fusion surgery resulted in approximately three times the charges as those incurred by the controls. Overall, the high incidence and charges for fusion surgeries shown in this study emphasize the importance of having a better understanding of when these surgeries are justified and for which patients. Without comprehensive practice guidelines established through evidence-based research this is difficult, if not impossible, to accomplish. The diagnoses which are most prevalent and show the most inconsistencies between cases may be a good starting point for such guidelines.

The large amounts of clinical data generated by electronic health record systems are an underutilized resource, which, if tapped, has enormous potential to improve health care. Since the majority of this data is in the form of unstructured text, which is challenging to analyze computationally, there is a need for sophisticated clinical language processing methods. Unsupervised methods that exploit statistical properties of the data are particularly valuable due to the limited availability of annotated corpora in the clinical domain. Information extraction and natural language processing systems need to incorporate some knowledge of semantics. One approach exploits the distributional properties of language – more specifically, term co-occurrence information – to model the relative meaning of terms in high-dimensional vector space. Such methods have been used with success in a number of general language processing tasks; however, their application in the clinical domain has previously only been explored to a limited extent. By applying models of distributional semantics to clinical text, semantic spaces can be constructed in a completely unsupervised fashion. Semantic spaces of clinical text can then be utilized in a number of medically relevant applications. The application of distributional semantics in the clinical domain is here demonstrated in three use cases: (1) synonym extraction of medical terms, (2) assignment of diagnosis codes and (3) identification of adverse drug reactions. To apply distributional semantics effectively to a wide range of both general and, in particular, clinical language processing tasks, certain limitations or challenges need to be addressed, such as how to model the meaning of multiword terms and account for the function of negation: a simple means of incorporating paraphrasing and negation in a distributional semantic framework is here proposed and evaluated. The notion of ensembles of semantic spaces is also introduced; these are shown to outperform the use of a single semantic space on the synonym extraction task. This idea allows different models of distributional semantics, with different parameter configurations and induced from different corpora, to be combined. This is not least important in the clinical domain, as it allows potentially limited amounts of clinical data to be supplemented with data from other, more readily available sources. The importance of configuring the dimensionality of semantic spaces, particularly when – as is typically the case in the clinical domain – the vocabulary grows large, is also demonstrated. / De stora mängder kliniska data som genereras i patientjournalsystem är en underutnyttjad resurs med en enorm potential att förbättra hälso- och sjukvården. Då merparten av kliniska data är i form av ostrukturerad text, vilken är utmanande för datorer att analysera, finns det ett behov av sofistikerade metoder som kan behandla kliniskt språk. Metoder som inte kräver märkta exempel utan istället utnyttjar statistiska egenskaper i datamängden är särskilt värdefulla, med tanke på den begränsade tillgången till annoterade korpusar i den kliniska domänen. System för informationsextraktion och språkbehandling behöver innehålla viss kunskap om semantik. En metod går ut på att utnyttja de distributionella egenskaperna hos språk – mer specifikt, statistisk över hur termer samförekommer – för att modellera den relativa betydelsen av termer i ett högdimensionellt vektorrum. Metoden har använts med framgång i en rad uppgifter för behandling av allmänna språk; dess tillämpning i den kliniska domänen har dock endast utforskats i mindre utsträckning. Genom att tillämpa modeller för distributionell semantik på klinisk text kan semantiska rum konstrueras utan någon tillgång till märkta exempel. Semantiska rum av klinisk text kan sedan användas i en rad medicinskt relevanta tillämpningar. Tillämpningen av distributionell semantik i den kliniska domänen illustreras här i tre användningsområden: (1) synonymextraktion av medicinska termer, (2) tilldelning av diagnoskoder och (3) identifiering av läkemedelsbiverkningar. Det krävs dock att vissa begränsningar eller utmaningar adresseras för att möjliggöra en effektiv tillämpning av distributionell semantik på ett brett spektrum av uppgifter som behandlar språk – både allmänt och, i synnerhet, kliniskt – såsom hur man kan modellera betydelsen av flerordstermer och redogöra för funktionen av negation: ett enkelt sätt att modellera parafrasering och negation i ett distributionellt semantiskt ramverk presenteras och utvärderas. Idén om ensembler av semantisk rum introduceras också; dessa överträffer användningen av ett enda semantiskt rum för synonymextraktion. Den här metoden möjliggör en kombination av olika modeller för distributionell semantik, med olika parameterkonfigurationer samt inducerade från olika korpusar. Detta är inte minst viktigt i den kliniska domänen, då det gör det möjligt att komplettera potentiellt begränsade mängder kliniska data med data från andra, mer lättillgängliga källor. Arbetet påvisar också vikten av att konfigurera dimensionaliteten av semantiska rum, i synnerhet när vokabulären är omfattande, vilket är vanligt i den kliniska domänen. / High-Performance Data Mining for Drug Effect Detection (DADEL)

The use of Electronic Health Records (EHR) for reporting patient data has been widely adopted by healthcare providers. This data can encompass many forms of medical information such as disease symptoms, results from laboratory tests, ICD-10 classes and other information from patients. Structured EHR data is often high-dimensional and contain many missing values, which impose a complication to many computing problems. Detecting meaningful structures in EHR data could provide meaningful insights in diagnose detection and in development of medical decision support systems. In this work, a subset of EHR data from patient questionnaires is explored through two well-known clustering algorithms: K-Means and Agglomerative Hierarchical. The algorithms were tested on different types of data, primarily raw data and data where missing values have been imputed using different imputation techniques. The primary evaluation index for the clustering algorithms was the silhouette value using euclidean and cosine distance measures. The result showed that natural groupings most likely exist in the data set. Hierarchical clustering created higher quality clusters than k-means, and the cosine measure yielded a good interpretation of distance. The data imputation imposed large effects to the data and likewise to the clustering results, and other or more sophisticated techniques are needed for handling missing values in the data set. / Användandet av digitala journaler för att rapportera patientdata har ökat i takt med digitaliseringen av vården. Dessa data kan innehålla många typer av medicinsk information så som sjukdomssymptom, labbresultat, ICD-10 diagnoskoder och annan patientinformation. EHR data är vanligtvis högdimensionell och innehåller saknade värden, vilket kan leda till beräkningssvårigheter i ett digitalt format. Att upptäcka grupperingar i sådana patientdata kan ge värdefulla insikter inom diagnosprediktion och i utveckling av medicinska beslutsstöd. I detta arbete så undersöker vi en delmängd av digital patientdata som innehåller patientsvar på sjukdomsfrågor. Detta dataset undersöks genom att applicera två populära klustringsalgoritmer: k-means och agglomerativ hierarkisk klustring. Algoritmerna är ställda mot varandra och på olika typer av dataset, primärt rådata och två dataset där saknade värden har ersatts genom imputationstekniker. Det primära utvärderingsmåttet för klustringsalgoritmerna var silhuettvärdet tillsammans med beräknandet av ett euklidiskt distansmått och ett cosinusmått. Resultatet visar att naturliga grupperingar med stor sannolikhet finns att hitta i datasetet. Hierarkisk klustring visade på en högre klusterkvalitet än k-means, och cosinusmåttet var att föredra för detta dataset. Imputation av saknade data ledde till stora förändringar på datastrukturen och således på resultatet av klustringsexperimenten, vilket tyder på att andra och mer avancerade dataspecifika imputationstekniker är att föredra.