Registries,Databases and Repositories for Developing Artificial Intelligence in Cancer Care

Modern artificial intelligence techniques have solved some previously intractable problems and produced impressive results in selected medical domains. One of their drawbacks is that they often need very large amounts of data. Pre-existing datasets in the form of national cancer registries, image/genetic depositories and clinical datasets already exist and have been used for research. In theory, the combination of healthcare Big Data with modern, data-hungry artificial intelligence techniques should offer significant opportunities for artificial intelligence development, but this has not yet happened. Here we discuss some of the structural reasons for this, barriers preventing artificial intelligence from making full use of existing datasets, and make suggestions as to enable progress. To do this, we use the framework of the 6Vs of Big Data and the FAIR criteria for data sharing and availability (Findability, Accessibility, Interoperability, and Reuse). We share our experience in navigating these barriers through The Brain Tumour Data Accelerator, a Brain Tumour Charity-supported initiative to integrate fragmented patient data into an enriched dataset. We conclude with some comments as to the limits of such approaches.     

“人工智能+X”背景下医学信息管理专业研究生培养模式

阐述当前“人工智能+X”背景下市场对医学信息管理专业人才能力的需求，分析医学信息管理专业人才培养现状，提出从重塑学科人才培养目标、优化课程内容与课程设置、建设“双师型”导师队伍、搭建多方协同共建共享在线平台及设立“政用产学研”联合培养基地等方面探索医学信息管理专业研究生培养模式，以期培养适应人工智能时代发展，具备学科优势特色的高层次、高水平、高质量的复合型、应用型、创新型人才。     

The influence of processed total non-forward and non-motile sperm count on the outcome of artificial insemination with the husband’s semen

BackgroundArtificial insemination with the husband’s semen (AIH) is an economical and noninvasive method of infertility treatment. However, AIH’s pregnancy rate is much lower than in vitro fertilization (IVF) as its multiple and complex uncertainty factors. Semen quality has been one of the main factors which affect the pregnancy outcome of AIH.MethodsThe relevant parameters of 1,142 AIH cycles were retrospectively studied, including the general parameters and the semen quality parameters among clinical pregnancy, biochemical pregnancy, non-pregnancy group, age, infertility duration, infertility type, body mass index (BMI), cycle count, morphology in previously semen examination, and semen quality parameters on the day of AIH.ResultsThe statistically significant difference was only found on processed total non-forward and non-motile sperm count (N-TFMSC). The mean processed N-TFMSC in the biochemical pregnancy group was 6.37±4.27 million, significantly higher than the other two groups (vs. 4.40±3.15 million or vs. 4.48±3.60 million, P<0.05). The study was then divided into two groups according to processed N-TFMSC, Group 1 ≤5.0 million, and Group 2 >5.0 million. A statistical increase in biochemical pregnancy rate was observed when the processed N-TFMSC was >5.0 million (2.72% vs. 0.90%).ConclusionsProcessed N-TFMSC may be one of the independent factors on AIH’s outcome; it should be given equal attention the same as processed total forward motile sperm count (TFMSC).     

Intelligent dialogue based on statistical models of clinical decision-making

The independence Bayesian model has been used widely in computer programs designed to support clinical decision-making. A reasoning strategy has been developed to enable these programs to conduct clinically pertinent dialogue and explain their reasoning. It has been implemented in a program for the diagnosis of acute abdominal pain based on the Bayesian model of de Dombal et al. Several features of the dialogue design have been adopted from artificial intelligence research, including shared initiative and critiquing. The program adopts a flexible goal-driven strategy, attempting to confirm the clinician's diagnosis or rule out the likeliest alternative. Symptoms and signs are selected in order of their expected weights of evidence in favour of the hypothesized disease.