Background: Laboratory results are of central importance for clinical decision making. The time span between availability and review of results by clinicians is crucial to patient care. Clinical decision support systems (CDSS) are computational tools that can identify critical values automatically and help decrease treatment delay. Objective: With this work, we aimed to implement and evaluate a CDSS that supports health care professionals and improves patient safety. In addition to our experiences, we also describe its main components in a general manner to make it applicable to a wide range of medical institutions and to empower colleagues to implement a similar system in their facilities. Methods: Technical requirements must be taken into account before implementing a CDSS that performs laboratory diagnostics (labCDSS). These can be planned within the functional components of a reactive software agent, a computational framework for such a CDSS. Results: We present AMPEL (Analysis and Reporting System for the Improvement of Patient Safety through Real-Time Integration of Laboratory Findings), a labCDSS that notifies health care professionals if a life-threatening medical condition is detected. We developed and implemented AMPEL at a university hospital and regional hospitals in Germany (University of Leipzig Medical Center and the Muldental Clinics in Grimma and Wurzen). It currently runs 5 different algorithms in parallel: hypokalemia, hypercalcemia, hyponatremia, hyperlactatemia, and acute kidney injury. Conclusions: AMPEL enables continuous surveillance of patients. The system is constantly being evaluated and extended and has the capacity for many more algorithms. We hope to encourage colleagues from other institutions to design and implement similar CDSS using the theory, specifications, and experiences described in this work.

Primary health care is facing extensive changes due to digitalization, while the field of application for machine learning is expanding. The merging of these two fields could result in a range of outcomes, one of them being an improved and more rigorous adoption of clinical decision support systems. Clinical decision support systems have been around for a long time but are still not fully adopted in primary health care due to insufficient performance and interpretation. Clinical decision support systems have a range of supportive functions to assist the clinician during decision making, where one of the most researched topics is diagnostic support. This thesis investigates how the use of self-described anamnesis in the form of free text and multiple-choice questions performs in prediction of diagnostic outcome. The chosen approach is to compare text to different subsets of multiple-choice questions for diagnostic prediction on a range of classification methods. The results indicate that text data holds a substantial amount of information, and that the multiple-choice questions used in this study are of varying quality, yet suboptimal compared to text data. The over-all tendency is that Support Vector Machines perform well on text classification and that Random Forests and Naive Bayes have equal performance to Support Vector Machines on multiple-choice questions. / Primärvården förväntas genomgå en utbredd digitalisering under de kommande åren, samtidigt som maskininlärning får utökade tillämpningsområden. Sammanslagningen av dessa två fält möjliggör en mängd förbättrade tekniker, varav en vore ett förbättrat och mer rigoröst anammande av kliniska beslutsstödsystem. Det har länge funnits varianter av kliniska beslutsstödsystem, men de har ännu inte lyckats blivit fullständigt inkorporerade i primärvården, framför allt på̊ grund av bristfällig prestanda och förmåga till tolkning. Kliniskt beslutstöd erbjuder en mängd funktioner för läkare vid beslutsfattning, där ett av de mest uppmärksammade fälten inom forskningen är support vid diagnosticering. Denna uppsats ämnar att undersöka hur självbeskriven anamnes i form av fritext och flervalsfrågor presterar för förutsägning av diagnos. Det valda tillvägagångssättet har varit att jämföra text med olika delmängder av flervalsfrågor med hjälp av en mängd metoder för klassificering. Resultaten indikerar att textdatan innehåller en avsevärt större mängd information än flervalsfrågorna, samt att flervalsfrågorna som har använts i denna studie är av varierande kvalité, men generellt sett suboptimala vad gäller prestanda i jämförelse med textdatan. Den generella tendensen är att Support Vector Machines presterar bra för klassificering med text data medan Random Forests och Naive Bayes är likvärdiga alternativ till Support Vector Machines för predicering vid användning av flervalsfrågor.

New diagnostic methods and novel therapeutic agents spawn additional and heterogeneous in-formation, leading to an increasingly complex decision-making process for optimal treatment of cancer. A great amount of information is collected in organ-specific multidisciplinary tumor boards (MDTBs). By considering the patient’s tumor properties, molecular pathological test re-sults, and comorbidities, the MDTB has to consent an evidence-based treatment decision. Im-munotherapies are increasingly important in today’s cancer treatment, resulting in detailed in-formation that influences the decision-making process. Clinical decision support systems can fa-cilitate a better understanding via processing of multiple datasets of oncological cases and mo-lecular genetic information, potentially fostering transparency and comprehensibility of available information, eventually leading to an optimum treatment decision for the individual patient. We constructed a digital patient model based on Bayesian networks to combine the relevant pa-tient-specific and molecular data with depended probabilities derived from pertinent studies and clinical guidelines to calculate treatment decisions in head and neck squamous cell carcinoma (HNSCC). In a validation analysis, the model can provide guidance within the growing subject of immunotherapy in HNSCC and, based on its ability to calculate reliable probabilities, facilitates estimation of suitable therapy options. We compared actual treatment decisions of 25 patients with the calculated recommendations of our model and found significant concordance (Cohen’s κ=0.505, p=0.009) and 84% accuracy.