This thesis contains a review of previous work in the fields of encoding sequential healthcare data and predicting graft- versus- host disease, a medical condition, based on patient history using machine learning. A new encoding of such data is proposed for machine learning purposes. The proposed encoding, called bag of binned weighted events, is a combination of two strategies proposed in previous work, called bag of binned events and bag of weighted events. An empirical experiment is designed to evaluate the predictive performance of the proposed encoding over various binning windows to that of the previous encodings, based on the area under the receiver operating characteristic curve (AUC) metric. The experiment is carried out on real- world healthcare data obtained from Swedish registries, using the random forest and the logistic regression algorithms. After filtering the data, solving quality issues and tuning hyperparameters of the models, final results are obtained. These results indicate that the proposed encoding strategy performs on par, or slightly better than the bag of weighted events, and outperforms the bag of binned events in most cases. However, differences in metrics show small differences. It is also observed that the proposed encoding usually performs better with longer binning windows which may be attributed to data noise. Future work is proposed in the form of repeating the experiment with different datasets and models, as well as changing the binning window length of the baseline algorithms. / Denna avhandling innehåller en recension av tidigare arbete inom områden av kodning av sekventiell sjukvårdsdata och förutsägelse av transplantat- mot- värdsjukdom, ett medicinskt tillstånd, baserat på patienthistoria med maskininlärning. En ny kodning av sådan data föreslås i maskininlärningssyfte. Den föreslagna kodningen, kallad bag of binned weighted events, är en kombination av två strategier som föreslagits i tidigare arbete, kallad bag of binned events och bag of weighted events. Ett empiriskt experiment är utformat för att utvärdera den föreslagna prestandan för den föreslagna kodningen över olika binningfönster jämfört med tidigare kodningar, baserat på AUC- måttet. Experimentet utförs på verkliga sjukvårdsdata som erhållits från svenska register, med random forest och logistic regression. Efter filtrering av data, lösning av kvalitetsproblem och justering av hyperparametrar för modellerna, erhålls slutliga resultat. Dessa resultat indikerar att den föreslagna kodningsstrategin presterar i nivå med, eller något bättre än bag of weighted events, och överträffar i de flesta fall bag of binned events. Skillnader i mått är dock små. Det observeras också att den föreslagna kodningen vanligtvis fungerar bättre med längre binningfönster som kan tillskrivas dataljud. Framtida arbete föreslås i form av att upprepa experimentet med olika datamängder och modeller, samt att ändra binningfönstrets längd för basalgoritmerna.

<p>This research focused on developing adaptable models and protocols for early warning systems for forecasting plant diseases and datasets. It compared the performance of deep learning models in predicting soybean rust disease outbreaks using three years of public epidemiological data and gridded weather data. The models selected were a dense network and a Long Short-Term Memory (LSTM) network. The objectives included evaluating the effectiveness of small citizen science datasets and gridded meteorological weather in sequential forecasting, assessing the ideal window size and important inputs, and exploring the generalizability of the model protocol and models to other diseases. The model protocol was developed using a soybean rust dataset. Both the dense and the LSTM networks produced accuracies of over 90% during optimization. When tested for forecasting, both networks could forecast with an accuracy of 85% or higher over various window sizes. Experiments on window size indicated a minimum input of 8 -11 days. Generalizability was demonstrated by applying the same protocol to a southern corn rust dataset, resulting in 87.8% accuracy. In addition, transfer learning and pre-trained models were tested. Direct transfer learning between disease was not successful, while pre training models resulted both positive and negative results. Preliminary results are reported for building generalizable disease models using epidemiological and weather data that researchers could apply to generate forecasts for new diseases and locations.</p>

千年以來，人類不斷遭遇各種疫病的侵襲，流行速度更勝戰火蔓延，影響整體人類重大，然而隨著醫學知識的進步與衛生環境的改善，許多傳染病已經受到控制乃至根絕，但是生活周遭仍然面臨諸多威脅生命健康的潛藏危機，如果稍有疏失或不慎，傳染病不僅對於人體造成傷害，甚至恐將危害社會、經濟和政治層面，而近年的SARS、H1N1等流行病毒皆造成全球恐慌。 防疫工作重點在於及早掌握疫情趨勢以利制定相關因應政策，目前各國對於傳染病的掌握主要透過層層監測系統與歷史平均，藉以判斷該年特定傳染病流行與散佈程度。這些方法受到各種人為與環境因素影響，導致推估疫情成效有限之外，同時所得資料無法直接反應未來疫情，因此導致各國相關單位逐漸嘗試其他預測方法。 近年應用預測市場機制預測疫情模式引起公衛領域的重視，相關學術期刊與著名雜誌相繼介紹此一新興模式，同時肯定其在預測傳染病方面的成效與貢獻，而美國和台灣政府部門先後透過此項機制改善現有防疫體系的不足。那麼，預測市場用以預測疫情的成效是否確實如同其在眾多領域取得的成效一樣出眾？鑑於前述問題，本研究分別透過質化與量化的方式發掘公衛、醫學或流病學等其他領域對於「傳染病預測市場」是否能夠成為有效的預測機制或是成為常規的參考方法，結果證實使用的疾管局人員與參與的專業醫事人員認為「傳染病預測市場」確實可以應用於我國疫情預測的層面，但是兩者意見具有程度的差異。 / For centuries, the spread of various diseases damage countless human beings, which surpass wars in the world. Those diseases not only endanger people’s life, but also invade the other dimensions, including society, economic and politics. With the advancement of medical knowledge and the improvement of public health, many infectious diseases have been brought under control and even eradicated. But humans still face and experience threats from pandemic viruses such as SARS and H1N1 constantly. Epidemic prevention work focuses on understanding the variation of situation as soon as possible. Then governments can set up suitable decisions and policies based on epidemic situation. Though the monitoring system and the historical average are the mainstream to control the trends of infections for related departments, scientists believe that the two methods are subject to humans and environmental factors. In other words, it is difficult to draw effective information and direct response of the future trends from present methods. And it leads to national units gradually try other epidemic forecasting methods. In recent years, using prediction markets to predict flu causes the attention of public health. Thus academic journals and well-known magazines not only introduce this application but approve its effectiveness and contribution in predicting infectious diseases. The departments of US and Taiwan have tried to improve the deficiencies of the existing prevention system through prediction markets. Is this application really as successful as PM in many issues and fields? To response the question, this research intends to through qualitative and quantitative ways respectively to explore the evaluations on Epidemic Prediction Markets behind public health, medical, epidemiology, etc. The result confirms that CDC staff and health workers identify the feasibility of Epidemic Prediction Markets, but with the degree of variation.

The diploma thesis is aim at analysis of determinants that determine whether is the market of homes for the elderly and homes with special regime attractive for current and potential entrepreneurs. Theoretical part explains the phenomenom of population ageing, analyzes predictions of population development and the development of number of people suffering from Alzheimer disease, senior's financial resources, reasearches rights and duties of social services providers and analyzes effectiveness of financing the social services according to the type of founder. For needed findings is used analysis of specialized literature and studies. Analytical part analyzes preferences for examined kinds of social services. Offers practical example of running the home with special regime and brings the opinions of specialists on economization of social services. In the end of work are collected findings evaluate by means of SWOT analysis.