Development of an artificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy during IVF.

STUDY QUESTION: Can an artificial intelligence (AI)-based model predict human embryo viability using images captured by optical light microscopy? SUMMARY ANSWER: We have combined computer vision image processing methods and deep learning techniques to create the non-invasive Life Whisperer AI model for robust prediction of embryo viability, as measured by clinical pregnancy outcome, using single static images of Day 5 blastocysts obtained from standard optical light microscope systems. WHAT IS KNOWN ALREADY: Embryo selection following IVF is a critical factor in determining the success of ensuing pregnancy. Traditional morphokinetic grading by trained embryologists can be subjective and variable, and other complementary techniques, such as time-lapse imaging, require costly equipment and have not reliably demonstrated predictive ability for the endpoint of clinical pregnancy. AI methods are being investigated as a promising means for improving embryo selection and predicting implantation and pregnancy outcomes. STUDY DESIGN, SIZE, DURATION: These studies involved analysis of retrospectively collected data including standard optical light microscope images and clinical outcomes of 8886 embryos from 11 different IVF clinics, across three different countries, between 2011 and 2018. PARTICIPANTS/MATERIALS, SETTING, METHODS: The AI-based model was trained using static two-dimensional optical light microscope images with known clinical pregnancy outcome as measured by fetal heartbeat to provide a confidence score for prediction of pregnancy. Predictive accuracy was determined by evaluating sensitivity, specificity and overall weighted accuracy, and was visualized using histograms of the distributions of predictions. Comparison to embryologists' predictive accuracy was performed using a binary classification approach and a 5-band ranking comparison. MAIN RESULTS AND THE ROLE OF CHANCE: The Life Whisperer AI model showed a sensitivity of 70.1% for viable embryos while maintaining a specificity of 60.5% for non-viable embryos across three independent blind test sets from different clinics. The weighted overall accuracy in each blind test set was >63%, with a combined accuracy of 64.3% across both viable and non-viable embryos, demonstrating model robustness and generalizability beyond the result expected from chance. Distributions of predictions showed clear separation of correctly and incorrectly classified embryos. Binary comparison of viable/non-viable embryo classification demonstrated an improvement of 24.7% over embryologists' accuracy (P = 0.047, n = 2, Student's t test), and 5-band ranking comparison demonstrated an improvement of 42.0% over embryologists (P = 0.028, n = 2, Student's t test). LIMITATIONS, REASONS FOR CAUTION: The AI model developed here is limited to analysis of Day 5 embryos; therefore, further evaluation or modification of the model is needed to incorporate information from different time points. The endpoint described is clinical pregnancy as measured by fetal heartbeat, and this does not indicate the probability of live birth. The current investigation was performed with retrospectively collected data, and hence it will be of importance to collect data prospectively to assess real-world use of the AI model. WIDER IMPLICATIONS OF THE FINDINGS: These studies demonstrated an improved predictive ability for evaluation of embryo viability when compared with embryologists' traditional morphokinetic grading methods. The superior accuracy of the Life Whisperer AI model could lead to improved pregnancy success rates in IVF when used in a clinical setting. It could also potentially assist in standardization of embryo selection methods across multiple clinical environments, while eliminating the need for complex time-lapse imaging equipment. Finally, the cloud-based software application used to apply the Life Whisperer AI model in clinical practice makes it broadly applicable and globally scalable to IVF clinics worldwide. STUDY FUNDING/COMPETING INTEREST(S): Life Whisperer Diagnostics, Pty Ltd is a wholly owned subsidiary of the parent company, Presagen Pty Ltd. Funding for the study was provided by Presagen with grant funding received from the South Australian Government: Research, Commercialisation and Startup Fund (RCSF). 'In kind' support and embryology expertise to guide algorithm development were provided by Ovation Fertility. J.M.M.H., D.P. and M.P. are co-owners of Life Whisperer and Presagen. Presagen has filed a provisional patent for the technology described in this manuscript (52985P pending). A.P.M. owns stock in Life Whisperer, and S.M.D., A.J., T.N. and A.P.M. are employees of Life Whisperer.

Outpatient anti-epileptic drug prescribing errors in a Children's Hospital: an audit and literature review.

PURPOSE: Prescription errors are a common and potentially hazardous problem and may cause patient harm. This review evaluates all new anti-epileptic drug (AED) outpatient prescriptions over one year and reviews the subject literature. METHODS: A 12-month retrospective review of all outpatient prescriptions of AEDs within a large Children's Hospital. Copies of all prescriptions were obtained from the Trust's Pharmacy. The evaluation included the completeness of the required information, prescribing errors and the need for pharmacist intervention before the drug could be dispensed. It did not address the severity of prescribing errors or the potential harm to the patient. RESULTS: Two hundred and sixty two new prescriptions were evaluated. Incomplete prescriptions (that omitted at least one piece of required information) were found in 72.1%. The most common omission was the dose strength (mg/ml) or actual dose (mg) of the AED. No clinical diagnosis was documented in 62.6% and in 22%, only the word 'epilepsy', was stated with no reference to the epilepsy syndrome or seizure type. Pharmacist intervention was required in approximately 17% (approximately 1 in 6) of all prescriptions before the AED could be dispensed. CONCLUSION: This review highlights the importance of clinical information on prescriptions and that incomplete or poor documentation may contribute to prescribing errors. It also emphasises the importance of pharmacists in the identification and correction or resolution of potential prescribing errors. There is a need to develop a well-validated measure to assess the severity of prescribing errors that will better address their clinical significance and risk.

The McKesson prop--an essential tool for the emergency physician?

Facial trauma is a commonly encountered presentation to emergency departments. When associated airway compromise occurs, co-existing head and neck injuries serve to produce a challenging clinical situation. We describe two patients who suffered multi-system trauma, with severe maxillofacial injuries that necessitated prompt definitive airway management and mid-face stabilisation in the pre-hospital and emergency department phases of resuscitation. The McKesson prop is a simple yet highly effective tool for use in these injuries.

A structured review and theme analysis of papers published on 'quality of life' in head and neck cancer: 2000-2005.

Over the past 10 years, quality of life (QOL) has been increasingly recognised as an important outcome parameter in head and neck cancer. Validated questionnaires have emerged and there has been an increase in the number of papers published each year. The aim of this article is to review the literature over the past five years (2000-2005 inclusive), to identify papers reporting outcomes using patient self-competed questionnaires and group these into themes. The tabulated summary allows for the areas of health related quality of life research to be identified and to explore issues that are perhaps deficit in the literature. The three authors independently searched the literature published in the English language using the ISI search engine with cross-reference using Pub Med and Ovid. The search terms were; quality of life, questionnaire, and head and neck cancer. Studies were placed in to one of five themes. There were 165 studies identified. The numbers in each theme were predictors of QOL [Hassanein KA, Musgrove BT, Bradbury E. Functional status of patients with oral cancer and its relation to style of coping, social support and psychological status. Br J Oral Maxillofac Surg 2001;39:340-5.], functional outcome [Klug C, Neuburg J, Glaser C, Schwarz B, Kermer C, Millesi W. Quality of life 2-10 years after combined treatment for advanced oral and oropharyngeal cancer. Int J Oral Maxillofac Surg 2002;31:664-9.], questionnaire development [Hanna E, Sherman A, Cash D, Adams D, Vural E, Fan CY, et al. Quality of life for patients following total laryngectomy vs chemoradiation for laryngeal preservation. Arch Otolaryngol Head Neck Surg 2004;130:875-9.], randomised clinical trials [Kanatas AN, Rogers SN. A national survey of health-related quality of life questionnaires in head and neck oncology. Ann R Coll Surg Engl 2004;86:6-10.], and reviews [Kanatas AN, Rogers SN. A national survey of health-related quality of life questionnaires in head and neck oncology. Ann R Coll Surg Engl 2004;86:6-10.]. Although many facets of HRQOL following head and neck cancer have been explored over the last five years the paper identifies issues where research is still lacking.

Plants as biomarkers for monitoring heavy metal contaminants on landfill sites using sequential extraction and inductively coupled plasma atomic emission spectrophotometry (ICP-AES).

There have been a number of studies investigating metal uptake in plants on contaminated landfill sites, but little on their role as biomarkers to identify metal mobility for continuous monitoring purposes. Vegetation can be used as a biomonitor of site pollution, by identifying the mobilisation of heavy metals and by providing an understanding of their bioavailability. Plants selected were the common nettle (Uritica Dioica), bramble (Rubus Fruticosa) and sycamore (Acer Pseudoplatanus). A study of the soil fractionation was made to investigate the soil properties that are likely to influence metal mobility and a correlation exercise was undertaken to investigate if variations in concentration of metals in vegetation can reflect variations in concentration of the metals in soil. The soil was digested using aqua regia in a microwave closed vessel. The vegetation was digested using both microwave and a hydrogen peroxide-nitric acid mixture, refluxed on a heating block and a comparison made. The certified reference materials (CRMs) used were Standard Reference Material (SRM) 1547, peach leaves for vegetation (NIST) and for soil CRM 143R, sewage sludge-amended soil (BCR). The relative standard deviations (RSDs) were 2-6% for the analyses. Our findings show evidence of phytoextraction by some plants, (especially bramble and nettle), with certain plants, (sycamore) exhibiting signs of phytostabilisation. The evidence suggests that there is a degree of selectivity in metal uptake and partitioning within the plant compartments. It was also possible to correlate mobility phases of certain metals (Pb, Cu and Zn) using the soil and plant record. Zn and Cu exhibited the greatest potential to migrate from the roots to the leaves, with Pb found principally in the roots of ground vegetation. Our results suggest that analysis of bramble leaves, nettle leaves and roots can be used to monitor the mobility of Pb in the soil with nettle, bramble and sycamore leaves to monitor Cu and Zn.

Assessment of a commercial pH electrode used with blood.

With the recent development of ion selective electrodes, potentiometry has entered a new era of usefulness ranging from pollution control to the investigation of single cells. Routine use of these sensors in the clinical environment is severely restricted due to errors associated with the reference electrode. Due to the Nernstian response of the potentiometric sensors the entire reference and ion selective electrodes are housed within a thermostatically controlled heater assembly. A clinically based thermostatically controlled combined ion selective/reference electrode system is discussed and a simple algorithm is presented to correct for the additional liquid junction potential encountered when monitoring biological solutions.