Search

Objectives: This study aims to demonstrate the usability of discourse analyses as a means of evaluating medical informatics systems by examining one particular computer-based data-to-text system for delivering neonatal health care information.Methods: Six textual summaries of clinical information, three produced by human clinicians and three by the data-to-text system, were subjected to fine-grain discourse analysis. Analysis was performed 'blind' on all six textual summaries. Analysis focused on the identification of lexical items and on the potential effects of these items on users of these clinical information summaries.Results: Results showed that there were clear differences between human- and system-generated clinical summaries, with human clinicians providing better narrative flow and textual detail. The data-to-text system successfully produced textual summaries although it fell short of human abilities.Conclusions: These results indicate potential future improvements to the system. Discourse analysis as used here may offer significant advantages in evaluating and developing similar medical informatics systems. [ABSTRACT FROM AUTHOR]

The BT-Nurse system uses data-to-text technology to automatically generate a natural language nursing shift summary in a neonatal intensive care unit (NICU). The summary is solely based on data held in an electronic patient record system, no additional data-entry is required. BT-Nurse was tested for two months in the Royal Infirmary of Edinburgh NICU. Nurses were asked to rate the understandability, accuracy, and helpfulness of the computer-generated summaries; they were also asked for free-text comments about the summaries. The nurses found the majority of the summaries to be understandable, accurate, and helpful (p<0.001 for all measures). However, nurses also pointed out many deficiencies, especially with regard to extra content they wanted to see in the computer-generated summaries. In conclusion, natural language NICU shift summaries can be automatically generated from an electronic patient record, but our proof-of-concept software needs considerable additional development work before it can be deployed. [ABSTRACT FROM AUTHOR]

Background: National reporting of adverse incidents has resulted in a number of clinical alerts being issued. Despite a lack of evidence, these alerts are often accompanied by a mandatory requirement to alter practice. There is likely to be clinician resistance to such a method of change management, particularly where evidence of safety is missing. Aim: To determine the level of implementation within neonatal units of an alert requiring the change from litmus to pH paper to test nasogastric tube position. Method: A questionnaire sent to all neonatal units in the United Kingdom with more than 12 cots. Results: From the 207 questionnaires sent, there were 165 (80%) responses. Fifty five percent of units were still using litmus. All continued to use supplementary tests not recommended in best practice statements issued at the time of the alert. There was considerable variation in the pH value at which it was considered safe to feed. Conclusions: Nine months after the alert, more than half the units had not changed to pH paper, and supplementary methods of testing were still being used. The wide range of pH values highlights the uncertainty about the ‘normal’ gastric pH in the newborn. The evidence that, in neonatal units, changing to pH paper is safer than the long established use of litmus is lacking. Recommendations for change in practice must be based on good information and not seen just as a ‘knee jerk’ response to adverse incidents. [ABSTRACT FROM AUTHOR]

Prospective motor control moves the body into the future, from where one is to where one wants to be. It is a hallmark of intentionality. But its origin in development is uncertain. In this study, we tested whether or not the arm movements of newborn infants were prospectively controlled. We measured the spatiotemporal organization of 480 full-term neonatal arm movements and 384 arm movements of prematurely born infants at-risk for neurodevelopmental disorder. We found 75% of healthy term-birth neonatal movements and 68% of prematurely born infant movements conformed to the τ G -coupling model of prospective sensorimotor control. Prospective coupling values were significantly reduced in the latter (p = .010, r = .087). In both cases prospectively controlled movements were tightly organized by fixed-duration units with a base duration of 218 ms and additional temporal units of 145 ms. Yet distances remained constant. Thus, we demonstrate for the first time a precise prospective spatiotemporal organization of neonatal arm movements and demonstrate that at-risk infants exhibit reduced sensorimotor control. Prospective motor control is a hallmark of primary sensorimotor intentionality and gives a strong embodied foundation to conscious motor agency., (© 2018 The Authors. Developmental Science Published by John Wiley & Sons Ltd.)

Late onset neonatal sepsis is one of the major clinical concerns when premature babies receive intensive care. Current practice relies on slow laboratory testing of blood cultures for diagnosis. A valuable research question is whether sepsis can be reliably detected before the blood sample is taken. This paper investigates the extent to which physiological events observed in the patient's monitoring traces could be used for the early detection of neonatal sepsis. We model the distribution of these events with an autoregressive hidden Markov model (AR-HMM). Both learning and inference carefully use domain knowledge to extract the baby's true physiology from the monitoring data. Our model can produce real-time predictions about the onset of the infection and also handles missing data. We evaluate the effectiveness of the AR-HMM for sepsis detection on a dataset collected from the Neonatal Intensive Care Unit at the Royal Infirmary of Edinburgh.

Introduction: Our objective was to determine whether and how a computer system could automatically generate helpful natural language nursing shift summaries solely from an electronic patient record system, in a neonatal intensive care unit (NICU)., Methods: A system was developed which automatically generates partial NICU shift summaries (for the respiratory and cardiovascular systems), using data-to-text technology. It was evaluated for 2 months in the NICU at the Royal Infirmary of Edinburgh, under supervision., Results: In an on-ward evaluation, a substantial majority of the summaries was found by outgoing and incoming nurses to be understandable (90%), and a majority was found to be accurate (70%), and helpful (59%). The evaluation also served to identify some outstanding issues, especially with regard to extra content the nurses wanted to see in the computer-generated summaries., Conclusions: It is technically possible automatically to generate limited natural language NICU shift summaries from an electronic patient record. However, it proved difficult to handle electronic data that was intended primarily for display to the medical staff, and considerable engineering effort would be required to create a deployable system from our proof-of-concept software., (Copyright © 2012 Elsevier B.V. All rights reserved.)

Background: Valid consent for research requires comprehensive and understandable information to be disclosed to participants. The way that information is shared varies, but regulatory bodies usually determine style. Some reports have suggested that although information may be all-inclusive, it does little to support understanding., Objective: To explore the impact of various information-sharing approaches on parents' understanding of a research study and the validity of their consent., Methods: This was a randomized, controlled trial. Parents of immature but well infants admitted to a large tertiary NICU in Edinburgh, Scotland, were randomly assigned within 72 hours of their infant's admission to receive 1 of 2 information leaflets, with or without a standardized verbal explanation, for a hypothetical intensive care research study. The leaflets differed in length and in the amount of detail in which the study process, risks, benefits, and patient rights were described. A questionnaire was used to elicit understanding about the purpose of the research, design of the study, procedures involved, and the consent process., Results: Forty-one parents participated in the study. Those who received the longer leaflet without verbal explanation gained only limited understanding of the purpose of the research. The procedures involved in the study were understood better by those who received the shorter leaflet. Issues relating to consent and study design were readily understood in all groups. Irrespective of documentation style, verbal explanation significantly improved understanding. Differences in understanding had little effect on whether a parent would enroll his or her infant into the study., Conclusions: Verbal explanation significantly enhances understanding of the research process for participants regardless of the style of written documentation. However, shorter written information may lead to better understanding than lengthy, more complex documentation.

As ICUs generate increasing amounts of information, writing medical reports involves complex time-consuming reasoning to build a coherent text which will be meaningful to those who will use it for decision making (e.g.: for nurse handover). Moreover, it has been shown that summarizing complex multi-channel physiological and discrete data in natural language (text) can lead to better decision-making in the intensive care unit (ICU). To facilitate this summarisation, as part of the BabyTalk project, we have developed a system called BT-45 that automatically generates textual summaries from periods of continuous and discrete data in a neonatal ICU. The demonstration will show the system running on real data and will detail the steps in the construction of the final text. Although these summaries are not yet as good as those generated by human experts, we have demonstrated experimentally that they lead to as good decision-making as can be achieved through presenting the same data graphically.

It has been shown that summarizing complex multi-channel physiological and discrete data in natural language (text) can lead to better decision-making in the intensive care unit (ICU). As part of the BabyTalk project, we describe a prototype system (BT-45) which can generate such textual summaries automatically. Although these summaries are not yet as good as those generated by human experts, we have demonstrated experimentally that they lead to as good decision-making as can be achieved through presenting the same data graphically.

Where possible, both parents should be present whenever bad news is broken. Professional calm and carefully chosen words are essential. Staff must be aware of cultural and religious beliefs of the family, and should be cognizant of linguistic and educational capabilities. The unexpected collapse and death of an infant is rare but is exceptionally demanding on communication skills. Time must be given for the family to ask questions, and staff should acknowledge the tragedy and the uncertainty, but should convey a determination to discover the truth for the family. A predictable deterioration allows staff and family to work together towards a "guided consensus" over future management. Compassionate care involves time, comfort and dignity for the child and parents. It is crucial for the family to receive empathetic support from senior nursing and medical staff. Mementoes may help the grieving process. Necropsy may also play an important role in allowing the families to rebuild their lives.

Background: There is concern that exposure of preterm infants to noxious insults over a prolonged period may have long term effects on their developing nervous system., Aims: To investigate medium and long term effects of heel pricks in infants over the first year of life., Study Design: Study 1-a longitudinal study, 2 days and 4 weeks after heel prick. Study 2-a cross sectional study over the first year of life., Subjects: Study 1-13 healthy preterm (PT) infants. Study 2-63 full term (FT) and 62 PT infants, divided into 3 timed groups (0-20, 21-37 and 38-52 weeks postterm and corrected for prematurity)., Outcome Measures: Threshold responses (flexion withdrawal (FWR) , gross body movements (GBM) and grimace (G)) to increasing mechanical force applied with Von Frey filaments., Results: Study 1-Thresholds were all significantly lower (more sensitive) from the pricked heel compared to the contralateral side at 2 days and 4 weeks. Study 2-There were significant differences in threshold between PT and FT infants at all time points for both FWR (P=0.001, <0.001, <0.001) and GBM (P=<0.001, <0.001, 0.009 respectively), the preterm infants always being lower. The threshold for the FWR in FT infants steadily increased, but the threshold for the PT infants remained the same. GBM thresholds increased during the year in both FT and PT infants, but were always significantly lower in the ex-preterm group (P<0.012)., Conclusions: Either PT birth or repetitive procedures associated with such birth alters the sensitivity threshold of PT infants compared with FT infants for at least the first year of life.

Background: The newborn infant's response to stimulation with von Frey filaments has previously been examined only at the spinal level as the flexion withdrawal response or abdominal reflex. The threshold for the spinal responses has been shown to be lower following skin damage and visceral pathology. Higher forces of mechanical stimulation elicit other body responses, which are likely to arise from higher levels in the nervous system: these have not been investigated before., Objective: To investigate the newborn infants' responses to increasing forces of mechanical (von Frey filament) stimulation and whether their progression is affected by repeated heel prick., Subjects and Methods: The study was performed in 31 full term and 77 preterm infants. Graded mechanical forces (using von Frey filaments) were applied to the heels and the abdominal skin. The thresholds for the flexion withdrawal reflex or abdominal reflex and other body responses were recorded., Results: The thresholds for the flexion withdrawal reflex and other body movements to graded mechanical force on the heel were significantly lower in preterm infants compared to full term infants. The threshold for the abdominal reflex and other body responses from graded mechanical stimulation of the abdomen was also significantly lower in preterm infants. In all infants thresholds were further reduced following sensitisation from previous heel pricks. The progression of the responses is independent of gestation or prior sensitisation., Conclusion: Both preterm and full term newborn infants respond to graded mechanical stimuli by a series of body responses, which progress in response to increasing force from a simple spinal withdrawal reflex to more complex responses involving higher levels of the central nervous system., ((c) 2008 S. Karger AG, Basel.)

Indicators of persistent pain in preterm neonates are poorly defined. In the setting of a double blind, placebo-controlled trial investigating morphine use in ventilated preterm infants (NEOPAIN Trial) we aimed to identify factors that may be useful in assessing persistent pain. Twenty-two babies (morphine 12; placebo 10) were assessed for comfort, pain or distress and clinical staff described the factors they had considered. This assessment was performed during the first period of duty with the baby. Based on this, they stated which study drug they believed the infant was receiving. Eighty-nine assessments were made in total (1-14 per baby). The drug was correctly identified on 71% of occasions. Staff considered one or more of the following factors: infant activity; response to routine care; known pain-related behaviours; posture/quality of movements; respiratory effort; synchrony with ventilator; blood pressure and heart rate. Four factors most frequently identified babies receiving placebo: facial expressions of pain, high activity levels, poor response to handling and poor synchrony with ventilation. Absence of pain-related behaviour was less discriminating. Observation of a good response to handling, good synchrony with ventilation, a "settled" baby, normal blood pressure and heart rate were poor discriminators. Hypotension and poor respiratory drive were noted exclusively in babies receiving morphine infusions. Facial expressions of pain, high activity levels, poor response to routine care, and poor ventilator synchrony were associated with placebo versus morphine therapy, and may be considered useful markers for persistent pain in preterm infants.

Objective: To compare expert-generated textual summaries of physiological data with trend graphs, in terms of their ability to support neonatal Intensive Care Unit (ICU) staff in making decisions when presented with medical scenarios., Methods: Forty neonatal ICU staff were recruited for the experiment, eight from each of five groups--junior, intermediate and senior nurses, junior and senior doctors. The participants were presented with medical scenarios on a computer screen, and asked to choose from a list of 18 possible actions those they thought were appropriate. Half of the scenarios were presented as trend graphs, while the other half were presented as passages of text. The textual summaries had been generated by two human experts and were intended to describe the physiological state of the patient over a short period of time (around 40 minutes) but not to interpret it., Results: In terms of the content of responses there was a clear advantage for the Text condition, with participants tending to choose more of the appropriate actions when the information was presented as text rather than as graphs. In terms of the speed of response there was no difference between the Graphs and Text conditions. There was no significant difference between the staff groups in terms of speed or content of responses. In contrast to the objective measures of performance, the majority of participants reported a subjective preference for the Graphs condition., Conclusions: In this experimental task, participants performed better when presented with a textual summary of the medical scenario than when it was presented as a set of trend graphs. If the necessary algorithms could be developed that would allow computers automatically to generate descriptive summaries of physiological data, this could potentially be a useful feature of decision support tools in the intensive care unit.

The aim of this paper is to describe a novel approach to the analysis of data obtained from card-sorting experiments. These experiments were performed as a part of the initial phase of a project, called NEONATE. One of the aims of the project is to develop decision support tools for the neonatal intensive care environment. Physical card-sorts were performed using clinical "action" and patient "descriptor" words. Thirty-two staff (eight junior nurses, eight senior nurses, eight junior doctors, and eight senior doctors) participated in the actions card-sorts and the same number of staff participated in separate descriptors card-sorting experiments. To check for consistency, the card-sorts were replicated for nurses during the action card-sorts. The card-sort data were analysed using hierarchical cluster analysis to produce tree-diagrams or dendrograms. Differences were shown in the way various classes of staff with different levels of experience mentally map clinical concepts. Clinical actions were grouped more loosely by nurses and by those with less experience, with a polarisation between senior doctors and junior nurses. Descriptors were classed more definitively and similarly by nurses and senior doctors but in a less structured way and quite differently by junior doctors. This paper presents a summary of the differences in the card-sort data for the various staff categories. It is shown that concepts are used differently by various staff groups in a neonatal unit and that this may diminish the effectiveness of computerised decision aids unless it is explored during their development.

Background: Common concepts and definitions are important for the effective practice of medicine. In an intensive care unit clear understanding of terminology and communication between different staff groups may be critical for optimal care. If computerised decision support tools are to be successfully deployed in these high intensity environments, all staff must understand the concepts and information that is to be portrayed., Objective: To examine the similarity of language and concepts related to newborn infants and their care in staff groups with different experience., Methods: An experimental study in a tertiary regional neonatal intensive care unit involved 32 staff in 4 groups with varying experience (junior and senior / nurses and doctors). A psychologist developed a lexicon of clinical actions and a second lexicon of possible patient descriptors applicable to newborn infants receiving all degrees of neonatal care by conducting interviews with staff on the unit. Card sorting experiments were performed on the terms in the action and descriptor lexicons, the staff being asked to group words that were related to the same or similar concepts. The card sort data were analysed using conventional cluster analysis to produce tree-diagrams or dendrograms and then by distance matrix analysis to give cumulative probability plots., Results: Differences were shown in the way various classes of staff and staff with different experience mentally map clinical concepts. Clinical actions were grouped more randomly by nurses and by those with less experience with a polarisation between senior doctors and junior nurses. Descriptors were classed more definitively and similarly by junior and senior nurses and senior doctors but more randomly and quite differently by junior doctors. Thus there were differences seen between nurses and doctors with different roles within the unit and differences related to experience., Conclusions: Concepts are used differently by various staff groups in a neonatal unit: this may have an impact on the effectiveness of computerised decision aids unless it is taken into account during their development.