A novel machine-learning framework based on early embryo morphokinetics identifies a feature signature associated with blastocyst development.

BACKGROUND: Artificial Intelligence entails the application of computer algorithms to the huge and heterogeneous amount of morphodynamic data produced by Time-Lapse Technology. In this context, Machine Learning (ML) methods were developed in order to assist embryologists with automatized and objective predictive models able to standardize human embryo assessment. In this study, we aimed at developing a novel ML-based strategy to identify relevant patterns associated with the prediction of blastocyst development stage on day 5. METHODS: We retrospectively analysed the morphokinetics of 575 embryos obtained from 80 women who underwent IVF at our Unit. Embryo morphokinetics was registered using the Geri plus® time-lapse system. Overall, 30 clinical, morphological and morphokinetic variables related to women and embryos were recorded and combined. Some embryos reached the expanded blastocyst stage on day 5 (BL Group, n = 210), some others did not (nBL Group, n = 365). RESULTS: The novel EmbryoMLSelection framework was developed following four-steps: Feature Selection, Rules Extraction, Rules Selection and Rules Evaluation. Six rules composed by a combination of 8 variables were finally selected, and provided a predictive power described by an AUC of 0.84 and an accuracy of 81%. CONCLUSIONS: We provided herein a new feature-signature able to identify with an high performance embryos with the best developmental competence to reach the expanded blastocyst stage on day 5. Clear and clinically relevant cut-offs were identified for each considered variable, providing an objective tool for early embryo developmental assessment.

[Perceived quality assessment in the University Hospital Authority in Sassary, Italy]. / Valutazione della qualità percepita nell'azienda Ospedaliero Universitaria di Sassari.

In line with the health legislation that introduced a system to monitor and review the quality, the Hospital Authority of University of Sassari has placed among its main objectives the satisfaction of patients/clients and has made an initial assessment of customer satisfaction for users hospitalized in their facilities with the methodology of the questionnaire. It was drawn up a questionnaire to closed questions, with default value scales, divided into 4 areas: 1) Hospitality, 2) Hotel treatment, 3) Professionalism of staff-information related pathology, informed consent, 4) personal opinion of the patient upon discharge. The questionnaire was administered the day of discharge, to users hospitalized of six UO of Hospital Authority in the months of September and October 2009, and patients discharged within 2 months were given a total of 514, of them have completed the testing 290 (54% of discharged patients). The questionnaires were analyzed in the results of both the individual UO involved in both the overall result, persons responsible for each facility was sent a report with the results of its own. The survey results are satisfactory with regard to both positive aspects, that is the overall grade average of 86.23% which to criticism, to which they are planning initiatives for their solution.

[Observational study of adverse events in admissions in general hospital of Sassari about corporate planning of clinical risk management]. / Studio osservazionale degli eventi avversi relativi ai ricoveri del 2005, nell'ambito di un programma di gestione del rischio clinico della ASL di Sassari.

In the corporate planning of clinical risk management, we performed an observational retrospective study based on random sampling of admission in General Hospital of Sassari, in 2005. We examined 400 patient clinical documentations in order to find the most frequent adverse events (AE), according to the international literature. We looked for 9 different adverse events; for each of these we elaborated a form personal data and detailed information for each event. During the analysis of the clinical documentations we have found also adverse events not previously classified: they were recorded and classified. We classified the events as explicit, if declared in clinical documentation, and implicit if not declared but clearly present in the records. 47 EA included in the initial 9 categories were found; while other 26 were not included the defined categories, global frequency of AE in our sample resulted: 18.3%. The study is an initial approach to the survey of AE and needs to be refined by determination of liability, severity, predictability, preventability.

[Quality of the clinical reports: observational study in Sassari]. / La qualità delle cartelle cliniche: studio osservazionale nella ASL di Sassari.

Within the program of clinical risk management, and in particular in the phase of the "knowledge" of company reality, the work deals with the topic of the case history in Sassari' local health authority. A study is treated where, on a sample of about 400 cases history, four definite aspects are considered, in particular those that are regarded as the most important in the risk management and about medical responsability: 1) formal consent; 2) daily clinical allowance; 3) therapeutic card; 4) operating card. The results we got show the presence of a formal consent filled in correctly in 36 cases (9%), completed a daily allowance in 36 cases (9%), therapeutic card in 14 (3.5%) cases, operation card in 21 cases (19% su 116 surgical cases). These data, that have permitted to estimate the specific company reality as from pointed out critical states, show the necessity of working, with involvement of professional doctors, to build a history case model with clear and shared rules where you can clearly find the clinical path of a patient, where everything made is quoted and easily readable when necessary.