Capone A, Cicchetti A, Mennini F S, Marcellusi A, Baio G, Favato G
Institute for Leadership and Management in Health - Kingston University London, London, UK - Economic Evaluation and HTA (CEIS- EEHTA) - IGF Department, Faculty of Economics, University of Rome Tor Vergata, Rome, Italy.
Department of Business Administration, Catholic University of Sacred Heart, Rome, Italy.
Clin Ter. 2016 Sep-Oct;167(5):e102-e111. doi: 10.7417/CT.2016.1952.
Healthcare expenses will be the most relevant policy issue for most governments in the EU and in the USA. This expenditure can be associated with two major key categories: demographic and economic drivers. Factors driving healthcare expenditure were rarely recognised, measured and comprehended. An improvement of health data generation and analysis is mandatory, and in order to tackle healthcare spending growth, it may be useful to design and implement an effective, advanced system to generate and analyse these data. A methodological approach relied upon the Health Data Entanglement (HDE) can be a suitable option. By definition, in the HDE a large amount of data sets having several sources are functionally interconnected and computed through learning machines that generate patterns of highly probable future health conditions of a population. Entanglement concept is borrowed from quantum physics and means that multiple particles (information) are linked together in a way such that the measurement of one particle's quantum state (individual health conditions and related economic requirements) determines the possible quantum states of other particles (population health forecasts to predict their impact). The value created by the HDE is based on the combined evaluation of clinical, economic and social effects generated by health interventions. To predict the future health conditions of a population, analyses of data are performed using self-learning AI, in which sequential decisions are based on Bayesian algorithmic probabilities. HDE and AI-based analysis can be adopted to improve the effectiveness of the health governance system in ways that also lead to better quality of care.
医疗保健费用将成为欧盟和美国大多数政府最相关的政策问题。这项支出可与两个主要关键类别相关联：人口和经济驱动因素。推动医疗保健支出的因素很少得到认可、衡量和理解。必须改进健康数据的生成和分析，为应对医疗保健支出增长，设计并实施一个有效的先进系统来生成和分析这些数据可能会有所帮助。一种依赖于健康数据纠缠（HDE）的方法学途径可能是一个合适的选择。根据定义，在HDE中，大量具有多个来源的数据集在功能上相互连接，并通过学习机器进行计算，这些学习机器生成人群未来健康状况的高度可能模式。纠缠概念借鉴自量子物理学，意味着多个粒子（信息）以一种方式链接在一起，即对一个粒子量子态（个体健康状况和相关经济需求）的测量决定了其他粒子（人群健康预测以预测其影响）的可能量子态。HDE创造的价值基于对健康干预产生的临床、经济和社会效应的综合评估。为预测人群的未来健康状况，使用自学习人工智能进行数据分析，其中顺序决策基于贝叶斯算法概率。HDE和基于人工智能的分析可被采用，以提高卫生治理系统的有效性，同时也能带来更高的医疗质量。
