The use of machine learning methods for the prediction of reaction yield is an emerging area. We demonstrate the applicability of support vector regression (SVR) for predicting reaction yields, using combinatorial data. Molecular descriptors used in regression tasks related to chemical reac?tivity have often been based on time-consuming, computationally demanding quantum chemical calculations, usually density functional theory. Structure-based descriptors (molecular fingerprints and molecular graphs) are quicker and easier to calculate, and are applicable to any molecule. In this study, SVR models built on structure-based descriptors were compared to models built on quantum chemical descriptors. The models were evaluated along the dimension of each reaction component in a set of Buchwald-Hartwig amination reactions. The structure-based SVR models out-performed the quantum chemical SVR models, along the dimension of each reaction compo?nent. The applicability of the models was assessed with respect to similarity to training. Prospec?tive predictions of unseen Buchwald-Hartwig reactions are presented for synthetic assessment, to validate the generalisability of the models, with particular interest along the aryl halide dimension.

No abstract

Within the German statutory health care system the practice of sociomedicine as an applied health science is mainly related to individual aspects of theinsured persons. Combining factors due to medical and socio-economical developments it plays an important integrative role as so to say a lawyer of the patients. Furthermore, practical sociomedicine must provide consultant services to support the social insurance in the sphere of shaping the health care system. Profound knowledge on the required level must be acquired by graduate studies and can be deepened by well-planned continuing medical education. Professionalism in providing services and fulfillment of legal obligations can be achieved by standardisation of social medical procedures, scientific orientation towards public health aspects, appropriate methods of delivering medical knowledge, use of information systems, refinement of co-operation, quality management, social medical controlling, application of modern planning and control concepts as well as model leadership.

A representative sample of MDK expertises examining the DRG encoding by hospitals showed a very high percentage of correct examination by the MDK experts. Identical MDK expertises cannot be achieved in all cases due to the scope of the assessment. Further improvement and simplification of codes and coding guidelines are required to reduce the scope of assessment with regard to correct DRG encoding and its examination.

The "Medical Services of the German Statutory Sickness Insurance Bodies (MDK)" is a non-profit organisation providing socio-medical specialist advice to the German Statutory Health and Nursing Care Insurances. Facing demographic changes as well as progress in medicine, highly qualified expertises and consultations are of increasing importance to manage the social security system and to continue to develop its structure. Sociomedical assignments of the MDK as applied health science is so far mainly related to individual aspects of insured persons (case management) but more and more to general aspects such as quality, consumer protection, efficiency, guiding concepts and organisation of the health care system. Based on its widespread experience, profound knowledge and confidence in its expertise the MDK is aware of its great sociopolitical responsibility and faces the wide range of assignments with regard to personneldevelopment and organisational innovations. Identification with principles of genuine medical practice, creating a modern job profile, and exercising creative power in accordance with the fundamental social legislation. This characterises the self-image and roleperception of medical experts of the MDK.