Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments.

Short-term reattendances to emergency departments are a key quality of care indicator. Identifying patients at increased risk of early reattendance could help reduce the number of missed critical illnesses and could reduce avoidable utilization of emergency departments by enabling targeted post-discharge intervention. In this manuscript, we present a retrospective, single-centre study where we created and evaluated an extreme gradient boosting decision tree model trained to identify patients at risk of reattendance within 72 h of discharge from an emergency department (University Hospitals Southampton Foundation Trust, UK). Our model was trained using 35,447 attendances by 28,945 patients and evaluated on a hold-out test set featuring 8847 attendances by 7237 patients. The set of attendances from a given patient appeared exclusively in either the training or the test set. Our model was trained using both visit level variables (e.g., vital signs, arrival mode, and chief complaint) and a set of variables available in a patients electronic patient record, such as age and any recorded medical conditions. On the hold-out test set, our highest performing model obtained an AUROC of 0.747 (95% CI 0.722-0.773) and an average precision of 0.233 (95% CI 0.194-0.277). These results demonstrate that machine-learning models can be used to classify patients, with moderate performance, into low and high-risk groups for reattendance. We explained our models predictions using SHAP values, a concept developed from coalitional game theory, capable of explaining predictions at an attendance level. We demonstrated how clustering techniques (the UMAP algorithm) can be used to investigate the different sub-groups of explanations present in our patient cohort.

After egg collection, can we predict the chance of embryos for day 5 transfer or freezing?

Even partway through an IVF cycle, at the point when a woman's eggs have been collected, it is hard to provide reliable answers to the common question of 'Am I likely to have a good embryo to transfer?' Sometimes, it only takes one good egg to be successful. However, doctors and patients are acutely aware that low egg numbers, older age and having conditions such as endometriosis can stack the odds against success. We have developed a model to try and answer this question for those patients who wish for more information to help guide their expectations after egg collection. A new tool is presented to predict whether a woman having IVF treatment will have a good enough embryo either to transfer on day 5 or freeze. It was built using information from all 2015 to 2016 UK cycles and predicts using age, number of eggs collected and cause of subfertility.

Streamlining follicular monitoring during controlled ovarian stimulation: a data-driven approach to efficient IVF care in the new era of social distancing.

STUDY QUESTION: What is the optimal follicular tracking strategy for controlled ovarian stimulation (COS) in order to minimise face-to-face interactions? SUMMARY ANSWER: As data from follicular tracking scans on Days 5, 6 or 7 of stimulation are the most useful to accurately predict trigger timing and risk of over-response, scans on these days should be prioritised if streamlined monitoring is necessary. WHAT IS KNOWN ALREADY: British Fertility Society guidance for centres restarting ART following coronavirus disease 2019 (COVID-19) pandemic-related shutdowns recommends reducing the number of patient visits for monitoring during COS. Current evidence on optimal monitoring during ovarian stimulation is sparse, and protocols vary significantly. Small studies of simplifying IVF therapy by minimising monitoring have reported no adverse effects on outcomes, including live birth rate. There are opportunities to learn from the adaptations necessary during these extraordinary times to improve the efficiency of IVF care in the longer term. STUDY DESIGN, SIZE, DURATION: A retrospective database analysis of 9294 ultrasound scans performed during monitoring of 2322 IVF cycles undertaken by 1875 women in a single centre was performed. The primary objective was to identify when in the IVF cycle the data obtained from ultrasound are most predictive of both oocyte maturation trigger timing and an over-response to stimulation. If a reduced frequency of clinic visits is needed due to COVID-19 precautions, prioritising attendance for monitoring scans on the most predictive cycle days may be prudent. PARTICIPANTS/MATERIALS, SETTING, METHODS: The study comprised anonymised retrospective database analysis of IVF/ICSI cycles at a tertiary referral IVF centre. Machine learning models are used in combining demographic and follicular tracking data to predict cycle oocyte maturation trigger timing and over-response. The primary outcome was the day or days in cycle from which scan data yield optimal model prediction performance statistics. The model for predicting trigger day uses patient age, number of follicles at baseline scan and follicle count by size for the current scan. The model to predict over-response uses age and number of follicles of a given size. MAIN RESULTS AND THE ROLE OF CHANCE: The earliest cycle day for which our model has high accuracy to predict both trigger day and risk of over-response is stimulation Day 5. The Day 5 model to predict trigger date has a mean squared error 2.16 ± 0.12 and to predict over-response an area under the receiver operating characteristic curve 0.91 ± 0.01. LIMITATIONS, REASONS FOR CAUTION: This is a retrospective single-centre study and the results may not be generalisable to centres using different treatment protocols. The results are derived from modelling, and further clinical validation studies will verify the accuracy of the model. WIDER IMPLICATIONS OF THE FINDINGS: Follicular tracking starting at Day 5 of stimulation may help to streamline the amount of monitoring required in COS. Previous small studies have shown that minimal monitoring protocols did not adversely impact outcomes. If IVF can safely be made less onerous on the clinic's resources and patient's time, without compromising success, this could help to reduce burden-related treatment drop-out. STUDY FUNDING/COMPETING INTEREST(S): F.P.C. acknowledges funding from the NIHR Applied Research Collaboration Wessex. The authors declare they have no competing interests in relation to this work. TRIAL REGISTRATION NUMBER: N/A.

Observation of magnetic vortex pairs at room temperature in a planar α-Fe2O3/Co heterostructure.

Vortices, occurring whenever a flow field 'whirls' around a one-dimensional core, are among the simplest topological structures, ubiquitous to many branches of physics. In the crystalline state, vortex formation is rare, since it is generally hampered by long-range interactions: in ferroic materials (ferromagnetic and ferroelectric), vortices are observed only when the effects of the dipole-dipole interaction are modified by confinement at the nanoscale1-3, or when the parameter associated with the vorticity does not couple directly with strain 4 . Here, we observe an unprecedented form of vortices in antiferromagnetic haematite (α-Fe2O3) epitaxial films, in which the primary whirling parameter is the staggered magnetization. Remarkably, ferromagnetic topological objects with the same vorticity and winding number as the α-Fe2O3 vortices are imprinted onto an ultra-thin Co ferromagnetic over-layer by interfacial exchange. Our data suggest that the ferromagnetic vortices may be merons (half-skyrmions, carrying an out-of plane core magnetization), and indicate that the vortex/meron pairs can be manipulated by the application of an in-plane magnetic field, giving rise to large-scale vortex-antivortex annihilation.

Coherent Magnetoelastic Domains in Multiferroic BiFeO_{3} Films.

The physical properties of epitaxial films can fundamentally differ from those of bulk single crystals even above the critical thickness. By a combination of nonresonant x-ray magnetic scattering, neutron diffraction and vector-mapped x-ray magnetic linear dichroism photoemission electron microscopy, we show that epitaxial (111)-BiFeO_{3} films support submicron antiferromagnetic domains, which are magnetoelastically coupled to a coherent crystallographic monoclinic twin structure. This unique texture, which is absent in bulk single crystals, should enable control of magnetism in BiFeO_{3} film devices via epitaxial strain.