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.     

The Resorbable Magnesium Scaffold Magmaris in Acute Coronary Syndrome: An Appraisal of Evidence and User Group Guidance

Bioresorbable scaffolds provide transient vessel support without the long-term limitations of permanent metallic drug-eluting stents. The sirolimus-eluting resorbable magnesium scaffold Magmaris is the only CE-marked metallic bioresorbable scaffold and provides short-term lumen support before being completely bioresorbed. To date, clinical trial results have demonstrated low adverse event rates in patients with simple coronary lesions. Seven European centers with large experience in Magmaris implantation, combined efforts in an informal collaboration to evaluate and appraise clinical data currently available regarding the performance of Magmaris in patients presenting with acute coronary syndromes, and to supply user-advice on patient selection and optimal implantation practice.     

The impact of foot shock-induced stress on pain-related behavior associated with burn injury

Acute pain is prevalent following burn injury and can often transition to chronic pain. Prolonged acute pain is an important risk factor for chronic pain and there is little preclinical research to address this problem. Using a mouse model of second-degree burn, we investigated whether pre-existing stress influences pain(sensitivity) after a burn injury. We introduced a contribution of stress in two different ways: (1) the use of foot-shock as a pre-injury stressor or (2) the use of A/J mice to represent higher pre-existing stress compared to C57Bl/6 mice. C57Bl/6 and A/J mice were exposed to repeated mild foot shock to induce stress for 10 continuous days and mice underwent either burn injury or sham burn injury of the plantar surface of the right hind paw. Assessments of mechanical and thermal sensitivities of the injured and uninjured paw were conducted during the shock protocol and at intervals up to 82-day post-burn injury. In both strains of mice that underwent burn injury, thermal hypersensitivity and mechanical allodynia appeared rapidly in the ipsilateral paw. Mice that were stressed took much longer to recover their hind paw mechanical thresholds to baseline compared to non-stressed mice in both burn and non-burn groups. Analysis of the two mouse strains revealed that the recovery of mechanical thresholds in A/J mice which display higher levels of baseline anxiety was shorter than C57Bl/6 mice. No differences were observed regarding thermal sensitivities between strains. Our results support the view that stress exposure prior to burn injury affects mechanical and thermal thresholds and may be relevant to as a risk factor for the transition from acute to chronic pain. Finally, genetic differences may play a key role in modality-specific recovery following burn injury.     

Midazolam exposure in the paediatric intensive care unit predicts acute post-traumatic stress symptoms in children

BackgroundClinically significant post-traumatic stress symptoms (PTSS) have been reported in up to a quarter of paediatric intensive care unit (PICU) survivors. Ongoing PTSS negatively impacts children's psychological development and physical recovery. However, few data regarding associations between potentially modifiable PICU treatment factors, such as analgosedatives and invasive procedures, and children's PTSS have been reported.ObjectivesWe sought to investigate the medical treatment factors associated with children's PTSS after PICU discharge.MethodsA prospective longitudinal cohort study was conducted in two Australian tertiary referral PICUs. Children aged 2-16 y admitted to the PICU between June 2008 and January 2011 for >8 h and <28 d were eligible for participation. Biometric and clinical data were obtained from medical records. Parents reported their child's PTSS using the Trauma Symptom Checklist for Young Children at 1, 3, 6, and 12 months after discharge. Logistic regression was used to assess potential associations between medical treatment and PTSS.ResultsA total of 265 children and their parents participated in the study. In the 12-month period following PICU discharge, 24% of children exhibited clinically elevated PTSS. Median risk of death (Paediatric Index of Mortality 2 [PIM2]) score was significantly higher in the PTSS group (0.31 [IQR 0.14–1.09] v 0.67 [IQR 0.20–1.18]; p = 0.014). Intubation and PICU and hospital length of stay were also significantly associated with PTSS at 1 month, as were midazolam, propofol, and morphine. After controlling for gender, reason for admission, and PIM2 score, only midazolam was significantly and independently associated with PTSS and only at 1 month (adjusted odds ration (aOR) 3.63, 95% CI 1.18, 11.12, p = 0.024). No significant relationship was observed between the use of medications and PTSS after 1 month.ConclusionsElevated PTSS were evident in one quarter (24%) of children during the 12 months after PICU discharge. One month after discharge, elevated PTSS were most likely to occur in children who had received midazolam therapy.