BackgroundMobile phone apps have been shown to enhance guideline adherence by prescribers, but have not been widely evaluated for their impact on guideline adherence by prescribers caring for inpatients with infections.ObjectivesTo determine whether providing the Auckland City Hospital (ACH) antibiotic guidelines in a mobile phone app increased guideline adherence by prescribers caring for inpatients with community acquired pneumonia (CAP) or urinary tract infections (UTIs).MethodsWe audited antibiotic prescribing during the first 24 hours after hospital admission in adults admitted during a baseline and an intervention period to determine whether provision of the app increased the level of guideline adherence. To control for changes in prescriber adherence arising from other factors, we performed similar audits of adherence to antibiotic guidelines in two adjacent hospitals.ResultsThe app was downloaded by 145 healthcare workers and accessed a total of 3985 times during the three month intervention period. There was an increase in adherence to the ACH antibiotic guidelines by prescribers caring for patients with CAP from 19% (37/199) to 27% (64/237) in the intervention period (p = 0.04); but no change in guideline adherence at an adjacent hospital. There was no change in adherence to the antibiotic guidelines by prescribers caring for patients with UTI at ACH or at the two adjacent hospitals.ConclusionsProvision of antibiotic guidelines in a mobile phone app can significantly increase guideline adherence by prescribers. However, providing an app which allows easy access to antibiotic guidelines is not sufficient to achieve high levels of prescriber adherence.

We argue why interpretability should have primacy alongside empiricism for several reasons: first, if machine learning (ML) models are beginning to render some of the high-risk healthcare decisions instead of clinicians, these models pose a novel medicolegal and ethical frontier that is incompletely addressed by current methods of appraising medical interventions like pharmacological therapies; second, a number of judicial precedents underpinning medical liability and negligence are compromised when ‘autonomous’ ML recommendations are considered to be en par with human instruction in specific contexts; third, explainable algorithms may be more amenable to the ascertainment and minimisation of biases, with repercussions for racial equity as well as scientific reproducibility and generalisability. We conclude with some reasons for the ineludible importance of interpretability, such as the establishment of trust, in overcoming perhaps the most difficult challenge ML will face in a high-stakes environment like healthcare: professional and public acceptance.

Long diagnostic wait times hinder international efforts to address antibiotic resistance in M. tuberculosis. Pathogen whole genome sequencing, coupled with statistical and machine learning models, offers a promising solution. However, generalizability and clinical adoption have been limited by a lack of interpretability, especially in deep learning methods. Here, we present two deep convolutional neural networks that predict antibiotic resistance phenotypes of M. tuberculosis isolates: a multi-drug CNN (MD-CNN), that predicts resistance to 13 antibiotics based on 18 genomic loci, with AUCs 82.6-99.5% and higher sensitivity than state-of-the-art methods; and a set of 13 single-drug CNNs (SD-CNN) with AUCs 80.1-97.1% and higher specificity than the previous state-of-the-art. Using saliency methods to evaluate the contribution of input sequence features to the SD-CNN predictions, we identify 18 sites in the genome not previously associated with resistance. The CNN models permit functional variant discovery, biologically meaningful interpretation, and clinical applicability.