Perceptions of the use of artificial intelligence in the diagnosis of skin cancer: an outpatient survey.

BACKGROUND: Convolutional neural networks (artificial intelligence, AI) are rapidly appearing within the field of dermatology, with diagnostic accuracy matching that of dermatologists. As technologies become available for use by both the health professionals and the general public, their uptake in healthcare will become more acceptable. National Health Service England recognizes the potential of AI for healthcare but emphasizes that patient-centred care should be at the forefront of these technological advancements. AIM: To obtain opinions of patients on the use of AI in a dermatology setting, when aiding the diagnosis of skin cancers. METHODS: A cross-sectional 14-point questionnaire was handed out to patients attending dermatology outpatient skin cancer clinics in two UK hospitals, between March and August 2018. RESULTS: In total, 603 patient questionnaires were completed. Nearly half (47%; n = 282) of respondents were not concerned if AI technology was used by a skin specialist to aid skin cancer diagnosis. However, the majority (81%; n = 491) of respondents, considered it important for a dermatologist to examine and confirm a diagnosis and to be present for discussion of a cancer diagnosis. CONCLUSION: Although the majority of respondents were not reluctant about the use of AI for skin cancer diagnosis, respondents still considered it important that dermatologists are involved in the diagnosis and/or confirmation of skin cancer. Furthermore, the study results demonstrate that personal interaction with a clinician is important. This is in keeping with proposals that AI be used as an adjunctive technology to increase accuracy of skin cancer diagnoses, but not as a substitute for a dermatologist.

Peri-operative administration of tranexamic acid in lower limb arthroplasty: a multicentre, prospective cohort study.

In the UK, tranexamic acid is recommended for all surgical procedures where expected blood loss exceeds 500 ml. However, the optimal dose, route and timing of administration are not known. This study aimed to evaluate current practice of peri-operative tranexamic acid administration. Patients undergoing primary total hip arthroplasty, total knee arthroplasty or unicompartmental knee arthroplasty during a 2-week period were eligible for inclusion in this prospective study. The primary outcome was the proportion of patients receiving tranexamic acid in the peri-operative period. Secondary outcomes included: dose, route and timing of tranexamic acid administration; prevalence of pre- and postoperative anaemia; estimated blood loss; and red blood cell transfusion rates. In total, we recruited 1701 patients from 56 NHS hospitals. Out of these, 1523 (89.5%) patients received tranexamic acid and of those, 1052 (69.1%) received a single dose of 1000 mg intravenously either pre- or intra-operatively. Out of the 1701 patients, 571 (33.6%) and 1386 (81.5%) patients were anaemic (haemoglobin < 130 g.l-1 ) in the pre- and postoperative period, respectively. Mean (SD) estimated blood loss for all included patients was 792 (453) ml and 54 patients (3.1%) received a red blood cell transfusion postoperatively. The transfusion rate for patients with pre-operative anaemia was 6.5%, compared with 1.5% in patients without anaemia. Current standard of care in the UK is to administer 1000 mg of tranexamic intravenously either pre- or intra-operatively. Approximately one-third of patients present for surgery with anaemia, although the overall red blood cell transfusion rate is low. These data provide useful comparators when assessing the efficacy of tranexamic acid and other patient blood management interventions in future studies.