PhD position in health sciences specialising in health informatics

Job description We are seeking an ambitious and motivated doctoral student with a strong interest in applying artificial intelligence and advanced data analytics to health data, mainly from electronic health records. The project focuses on developing and evaluating machine learning models for predicting adverse drug events using both structured healthcare data and unstructured clinical notes. The doctoral student will work in an interdisciplinary environment at the intersection of health informatics, artificial intelligence, clinical decision support and healthcare research. The doctoral studentship forms part of [Samverkan e-hälsa](https://lnu.se/mot-linneuniversitetet/samarbeta-med-oss/Projekt-och-natverk/samverkan-e-halsa/), a long-term collaboration between Linnaeus University and Region Kalmar County, aimed at promoting the development of e-health at regional, national and international levels. The purpose of this collaboration is to establish a strong environment for research and education in e-health that can support the continued, much-needed development of e-health in healthcare. The doctoral student will contribute to the development of the research environment for this collaborative project and will be part of [the Graduate School in Health Informatics and e-Health](https://lnu.se/forskning/forskarutbildning/forskarskolan-i-halsoinformatik-och-ehalsa/). The doctoral student will be expected to: - follow their individual study plan, participate in mandatory courses and seminars, and report their progress regularly to their supervisors and the department - plan, conduct and publish scientific studies as part of the project, in close collaboration with their supervisors and research group - play an active role in the interdisciplinary research environment at the eHealth Institute and within Samverkan e-hälsa - apply and further develop expertise in machine learning, deep learning, natural language processing and predictive modelling using health data, mainly from electronic health records - develop and evaluate AI-based prediction models and contribute to the development of clinical decision support tools by integrating healthcare data and clinical knowledge resources - present research at national and international conferences - actively participate in the graduate school, which is a key academic and social community for doctoral students in the field - contribute to teaching, supervision and administration for up to 20 per cent of their working hours, in accordance with the Higher Education Ordinance. The Higher Education Ordinance states that anyone who is employed as a doctoral student shall primarily devote themselves to their own studies, although they may, to a limited extent, also work with education, research and administration. Before a doctorate has been awarded, such work must not exceed 20% of full-time work. The doctoral studentship may be combined with other professional duties, either in a clinical setting or in industry. ## Eligibility The Higher Education Ordinance (Chapter 7, Section 35) states that in order to be admitted to third-cycle education, the applicant must: - meet the general entry requirements as well as any specific entry requirements set by the relevant higher education institution - be considered to have the abilities required to be able to benefit from the education that they are given. The general entry requirements are met by applicants who - have been awarded a degree at the second-cycle level - have at least 240 credits of passed courses, of which at least 60 credits are at the second-cycle level; or - have acquired essentially equivalent knowledge in some other way, in or outside Sweden. The specific entry requirements are met by applicants who - have a degree at second-cycle level in computer science, data science, artificial intelligence, applied mathematics, or another discipline deemed relevant to the project - have documented knowledge of machine learning, artificial intelligence, data mining or advanced statistical modelling - have a good command of spoken and written English Desirable qualifications include: - experience working with electronic health record data or other large-scale healthcare datasets - experience in machine learning, deep learning, predictive modelling or natural language processing - experience analysing structured and unstructured health data - experience integrating data from clinical knowledge databases - programming experience in Python or other relevant languages for machine learning and data science - experience in web application development or research software development - experience in data visualisation - experience in medication safety research, pharmacoepidemiology, adverse event prediction or related areas - experience with interdisciplinary collaboration ## Assessment criteria The assessment criteria are used to assess the applicant's prospects of successfully completing the doctoral programme. Particular emphasis will be placed on the candidate’s motivation, potential to complete doctoral studies, and personal suitability for the position. The candidate must be well organised and able to work effectively both independently and as part of a team. ## Your application must include: - your curriculum vitae - degree certificate(s), academic transcripts and any other relevant certificates - your master's thesis - your complete list of publications - a personal statement (maximum two pages) describing: (1) any previous research experience; (2) your interest in pursuing doctoral studies; and (3) a brief outline (max 2 pages) of a research idea relevant to answer the research question “How can health data be used to improve predictions of adverse drug events compared with current clinical decision support systems”. - contact details for at least two referees. Interviews and work samples will form part of the selection process. Further information is available on the webpage for doctoral studies in health