Intention Recognition With ProbLog.

In many scenarios where robots or autonomous systems may be deployed, the capacity to infer and reason about the intentions of other agents can improve the performance or utility of the system. For example, a smart home or assisted living facility is better able to select assistive services to deploy if it understands the goals of the occupants in advance. In this article, we present a framework for reasoning about intentions using probabilistic logic programming. We employ ProbLog, a probabilistic extension to Prolog, to infer the most probable intention given observations of the actions of the agent and sensor readings of important aspects of the environment. We evaluated our model on a domain modeling a smart home. The model achieved 0.75 accuracy at full observability. The model was robust to reduced observability.

Impact of the COVID-19 pandemic on in-hospital cardiac arrests in the UK.

AIMS: To compare in-hospital cardiac arrest (IHCA) rates and patient outcomes during the first COVID-19 wave in the United Kingdom (UK) in 2020 with the same period in previous years. METHODS: A retrospective, multicentre cohort study of 154 UK hospitals that participate in the National Cardiac Arrest Audit and have intensive care units participating in the Case Mix Programme national audit of intensive care. Hospital burden of COVID-19 was defined by the number of patients with confirmed SARS-CoV2 infection admitted to critical care per 10,000 hospital admissions. RESULTS: 16,474 patients with IHCA where a resuscitation team attended were included. Patients admitted to hospital during 2020 were younger, more often male, and of non-white ethnicity compared with 2016-2019. A decreasing trend in IHCA rates between 2016 and 2019 was reversed in 2020. Hospitals with higher burden of COVID-19 had the greatest difference in IHCA rates (21.8 per 10,000 admissions in April 2020 vs 14.9 per 10,000 in April 2019). The proportions of patients achieving ROSC ≥ 20 min and surviving to hospital discharge were lower in 2020 compared with 2016-19 (46.2% vs 51.2%; and 21.9% vs 22.9%, respectively). Among patients with IHCA, higher hospital burden of COVID-19 was associated with reduced survival to hospital discharge (OR = 0.95; 95% CI 0.93 to 0.98; p < 0.001). CONCLUSIONS: In comparison with 2016-2019, the first COVID-19 wave in 2020 was associated with a higher rate of IHCA and decreased survival among patients attended by resuscitation teams. These changes were greatest in hospitals with the highest COVID-19 burden.

Escalation triggers and expected responses in obstetric early warning systems used in UK consultant-led maternity units.

BACKGROUND: The use of obstetric early warning systems (OEWS) are recommended as an adjunct to reduce maternal morbidity and mortality. The aim of this review was to document the variation in OEWS trigger thresholds and the quality of information included within accompanying escalation protocols. METHODS: A review of OEWS charts and escalation policies across consultant-led maternity units in the UK (n = 147) was conducted. OEWS charts were analysed for variation in the values of physiological parameters triggering different levels of clinical escalation. Relevant data within the escalation protocols were also searched for: urgency of clinical response; seniority of responder; frequency of on-going clinical monitoring; and clinical setting recommended for on-going care. RESULTS: The values of physiological parameters triggering specific clinical responses varied significantly between OEWS. Only 99 OEWS charts (67.3%) had an escalation protocol as part of the chart. For 29 charts (19.7%), the only escalation information included was generic, for example to "contact a doctor if triggers". Only 76 (51.7%) charts detailed the required seniority of responder, 37 (25.2%) the frequency for on-going clinical monitoring, eight (5.4%) the urgency of clinical response and two (1.4%) the recommended clinical setting for on-going care. CONCLUSION: The observed variations in the trigger thresholds used in OEWS charts and the quality of information included within the accompanying escalation protocols is likely to lead to suboptimal detection and response to clinical deterioration during pregnancy and the post-partum period. The development of a national OEWS and escalation protocol would help to standardise care across obstetric units.

Impact of the coronavirus pandemic on the patterns of vital signs recording and staff compliance with expected monitoring schedules on general wards.

INTRODUCTION: Coronavirus disease 2019 (COVID-19) placed increased burdens on National Health Service hospitals and necessitated significant adjustments to their structures and processes. This research investigated if and how these changes affected the patterns of vital sign recording and staff compliance with expected monitoring schedules on general wards. METHODS: We compared the pattern of vital signs and early warning score (EWS) data collected from admissions to a single hospital during the initial phase of the COVID-19 pandemic with those in three control periods from 2018, 2019 and 2020. Main outcome measures were weekly and monthly hospital admissions; daily and hourly patterns of recorded vital signs and EWS values; time to next observation and; proportions of 'on time', 'late' and 'missed' vital signs observations sets. RESULTS: There were large falls in admissions at the beginning of the COVID-19 era. Admissions were older, more unwell on admission and throughout their stay, more often required supplementary oxygen, spent longer in hospital and had a higher in-hospital mortality compared to one or more of the control periods. More daily observation sets were performed during the COVID-19 era than in the control periods. However, there was no clear evidence that COVID-19 affected the pattern of vital signs collection across the 24-h period or the week. CONCLUSIONS: The increased burdens of the COVID-19 pandemic, and the alterations in healthcare structures and processes necessary to respond to it, did not adversely affect the hospitals' ability to monitor patients under its care and to comply with expected monitoring schedules.

The performance of the National Early Warning Score and National Early Warning Score 2 in hospitalised patients infected by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

INTRODUCTION: Since the introduction of the UK's National Early Warning Score (NEWS) and its modification, NEWS2, coronavirus disease 2019 (COVID-19), has caused a worldwide pandemic. NEWS and NEWS2 have good predictive abilities in patients with other infections and sepsis, however there is little evidence of their performance in COVID-19. METHODS: Using receiver-operating characteristics analyses, we used the area under the receiver operating characteristic (AUROC) curve to evaluate the performance of NEWS or NEWS2 to discriminate the combined outcome of either death or intensive care unit (ICU) admission within 24 h of a vital sign set in five cohorts (COVID-19 POSITIVE, n = 405; COVID-19 NOT DETECTED, n = 1716; COVID-19 NOT TESTED, n = 2686; CONTROL 2018, n = 6273; CONTROL 2019, n = 6523). RESULTS: The AUROC values for NEWS or NEWS2 for the combined outcome were: COVID-19 POSITIVE, 0.882 (0.868-0.895); COVID-19 NOT DETECTED, 0.875 (0.861-0.89); COVID-19 NOT TESTED, 0.876 (0.85-0.902); CONTROL 2018, 0.894 (0.884-0.904); CONTROL 2019, 0.842 (0.829-0.855). CONCLUSIONS: The finding that NEWS or NEWS2 performance was good and similar in all five cohorts (range = 0.842-0.894) suggests that amendments to NEWS or NEWS2, such as the addition of new covariates or the need to change the weighting of existing parameters, are unnecessary when evaluating patients with COVID-19. Our results support the national and international recommendations for the use of NEWS or NEWS2 for the assessment of acute-illness severity in patients with COVID-19.

The impact of the Tracey judgment on the rates and outcomes of in-hospital cardiac arrests in UK hospitals participating in the National Cardiac Arrest Audit.

AIMS: The aim was to determine if the 17 June 2014 Tracey judgment regarding 'do not attempt cardiopulmonary resuscitation' decisions led to increases in the rate of in-hospital cardiac arrests resulting in a resuscitation attempt (IHCA) and/or proportion of resuscitation attempts deemed futile. METHOD: Using UK National Cardiac Arrest Audit data, the IHCA rate and proportion of resuscitation attempts deemed futile were compared for two periods (pre-judgment (01 July 2012 - 16 June 2014, inclusive) and post-judgment (01 July 2014 - 30 June 2016, inclusive)) using interrupted time series analyses. RESULTS: A total of 43,109 IHCAs (115 hospitals) were analysed. There were fewer IHCAs post- than pre-judgment (21,324 vs 21,785, respectively). The IHCA rate was declining over time before the judgment but there was an abrupt and statistically significant increase in the period immediately following the judgment (p<0.001). This was not sustained post-judgment. The proportion of resuscitation attempts deemed futile was smaller post-judgment than pre-judgment (8.2% vs 14.9%, respectively). The rate of attempts deemed futile decreased post-judgment (p<0.001). CONCLUSION: The IHCA rate increased immediately after the Tracey judgment while the proportion of resuscitation attempts deemed futile decreased. The precise mechanisms for these changes are unclear.

What is the nursing time and workload involved in taking and recording patients' vital signs? A systematic review.

AIMS AND OBJECTIVES: To synthesise evidence regarding the time nurses take to monitor and record vital signs observations and to calculate early warning scores. BACKGROUND: While the importance of vital signs' monitoring is increasingly highlighted as a fundamental means of maintaining patient safety and avoiding patient deterioration, the time and associated workload involved in vital signs activities for nurses are currently unknown. DESIGN: Systematic review. METHODS: A literature search was performed up to 17 December 2019 in CINAHL, Medline, EMBASE and the Cochrane Library using the following terms: vital signs; monitoring; surveillance; observation; recording; early warning scores; workload; time; and nursing. We included studies performed in secondary or tertiary ward settings, where vital signs activities were performed by nurses, and we excluded qualitative studies and any research conducted exclusively in paediatric or maternity settings. The study methods were compliant with the PRISMA checklist. RESULTS: Of 1,277 articles, we included 16 papers. Studies described taking vital signs observations as the time to measure/collect vital signs and time to record/document vital signs. As well as mean times being variable between studies, there was considerable variation in the time taken within some studies as standard deviations were high. Documenting vital signs observations electronically at the bedside was faster than documenting vital signs away from the bed. CONCLUSIONS: Variation in the method(s) of vital signs measurement, the timing of entry into the patient record, the method of recording and the calculation of early warning scores values across the literature make direct comparisons of their influence on total time taken difficult or impossible. RELEVANCE TO CLINICAL PRACTICE: There is a very limited body of research that might inform workload planning around vital signs observations. This uncertainty means the resource implications of any recommendation to change the frequency of observations associated with early warning scores are unknown.

The association between nurse staffing levels and a failure to respond to patients with deranged physiology: A retrospective observational study in the UK.

BACKGROUND: Responding to abnormalities in patients' vital signs is a fundamental aspect of nursing. However, failure to respond to patient deterioration is common and often leads to adverse patient outcomes. This study aimed to determine the association between Registered Nurse (RN) and Nursing Assistant (NA) staffing levels and the failure to respond promptly to patients' abnormal physiology. METHODS: This retrospective, observational study used routinely collected patients' vital signs and administrative data, including nursing staffing, from 32 general wards of an acute hospital in England between April 2012 and March 2015. Mixed-effects binomial regression was used to model the relationship between nurse staffing, measured as 'Hours per Patient Day' (HPPD), and a composite primary outcome representing failure to respond for patients with National Early Warning Score (NEWS) values ≥ 6 and ≥ 7. RESULTS: There were 189,123 NEWS values ≥ 6 and 114,504 NEWS values ≥ 7, affecting 28,098 patients. For patients with NEWS values ≥ 7, failure to respond was significantly associated with levels of RN HPPD ((IRR 0.98, 95% CI 0.96-0.99, p = 0.0001) but not NA HPPD (((IRR 0.99, 95%CI 0.96-1.01, p = 0.238). For patients with NEWS values ≥ 6, no such relationship existed. CONCLUSIONS: RN, but not NA, staffing levels influence the rates of failure to respond for patients with the most abnormal vital signs (NEWS values ≥ 7). These findings offer a possible explanation for the increasingly reported association between low RN staffing and an increased risk of patient death during a hospital admission.

Midwives' views towards women using mHealth and eHealth to self-monitor their pregnancy: A systematic review of the literature.

INTRODUCTION: There are many mobile telephone apps to help women self-monitor aspects of pregnancy and maternal health. This literature review aims to understand midwives' perspectives on women self-monitoring their pregnancy using eHealth and mHealth, and establish gaps in research. METHODS: MEDLINE, PubMed, Scopus, CINAHL and PsycINFO were systematically searched on midwifery, eHealth/mHealth and perspectives. Qualitative, quantitative and mixed-methods studies published in English were considered for inclusion in the review, without geographical limitations. Relevant articles were critically appraised and narrative synthesis was conducted. RESULTS: Twelve relevant papers covering midwives' perspectives of the use of eHealth and mHealth by pregnant women were obtained for inclusion in this review. Seven of these publications focused on midwives' views of eHealth, and five on their perspectives of mHealth interventions. The studies included demonstrate that midwives generally hold ambivalent views towards the use of eHealth and mHealth technologies in antenatal care. Often, midwives acknowledged the potential benefits of such technologies, such as their ability to modernise antenatal care and to help women make more informed decisions about their pregnancy. However, midwives were quick to point out the risks and limitations of these, such as the accuracy of conveyed information, and negative impacts on the patient-professional relationship. CONCLUSIONS: Post-COVID-19, where technology is continuously developing, there is a compelling need for studies that investigate the role of eHealth and mHealth in self-monitoring pregnancy, and the consequences this has for pregnant women, health professionals and organisations, as well as midwifery curricula.

Impact of using data from electronic protocols in nursing performance management: A qualitative interview study.

AIM: To explore the impact of using electronic data in performance management to improve nursing compliance with a protocol. BACKGROUND: Electronic data are increasingly used to monitor protocol compliance but little is known about the impact on nurses' practice in hospital wards. METHOD: Seventeen acute hospital nursing staff participated in semi-structured interviews about compliance with an early warning score (EWS) protocol delivered by a bedside electronic handheld device. RESULTS: Before electronic EWS data was used to monitor compliance, staff combined protocol-led actions with clinical judgement. However, some observations were missed to reduce noise and disruption at night. After compliance monitoring was introduced, observations were sometimes covertly omitted using a loophole. Interviewees described a loss of autonomy but acknowledged the EWS system sometimes flagged unexpected patient deterioration. CONCLUSIONS: Introducing automated electronic systems to support nursing tasks can decrease nursing burden but remove the ability to record legitimate reasons for missing observations. This can result in covert resistance that could reduce patient safety. IMPLICATIONS FOR NURSING MANAGEMENT: Providing the ability to log legitimate reasons for missing observations would allow nurses to balance professional judgement with the use of electronic data in performance management of protocol compliance.

The association between nurse staffing levels and the timeliness of vital signs monitoring: a retrospective observational study in the UK.

OBJECTIVES: Omissions and delays in delivering nursing care are widely reported consequences of staffing shortages, with potentially serious impacts on patients. However, studies so far have relied almost exclusively on nurse self-reporting. Monitoring vital signs is a key part of nursing work and electronic recording provides an opportunity to objectively measure delays in care. This study aimed to determine the association between registered nurse (RN) and nursing assistant (NA) staffing levels and adherence to a vital signs monitoring protocol. DESIGN: Retrospective observational study. SETTING: 32 medical and surgical wards in an acute general hospital in England. PARTICIPANTS: 538 238 nursing shifts taken over 30 982 ward days. PRIMARY AND SECONDARY OUTCOME MEASURES: Vital signs observations were scheduled according to a protocol based on the National Early Warning Score (NEWS). The primary outcome was the daily rate of missed vital signs (overdue by ≥67% of the expected time to next observation). The secondary outcome was the daily rate of late vital signs observations (overdue by ≥33%). We undertook subgroup analysis by stratifying observations into low, medium and high acuity using NEWS. RESULTS: Late and missed observations were frequent, particularly in high acuity patients (median=44%). Higher levels of RN staffing, measured in hours per patient per day (HPPD), were associated with a lower rate of missed observations in all (IRR 0.983, 95% CI 0.979 to 0.987) and high acuity patients (0.982, 95% CI 0.972 to 0.992). However, levels of NA staffing were only associated with the daily rate (0.954, CI 0.949 to 0.958) of all missed observations. CONCLUSIONS: Adherence to vital signs monitoring protocols is sensitive to levels of nurse and NA staffing, although high acuity observations appeared unaffected by levels of NAs. We demonstrate that objectively measured omissions in care are related to nurse staffing levels, although the absolute effects are small. STUDY REGISTRATION: The data and analyses presented here were part of the larger Missed Care study (ISRCTN registration: 17930973).

The response to patient deterioration in the UK National Health Service - A survey of acute hospital policies.

BACKGROUND: The assessment of acute-illness severity in adult non-pregnant patients in the United Kingdom is based on early warning score (EWS) values that determine the urgency and nature of the response to patient deterioration. This study aimed to describe, and identify variations in, the expected clinical response outlined in 'deteriorating patient' policies/guidelines in acute NHS hospitals. METHODS: A copy of the local 'deteriorating patient' policy/guideline was requested from 152 hospitals. Each was analysed against pre-determined areas of interest, e.g., minimum expected vital sign observations frequency, expected response and expected staff response times. RESULTS: In the 55 responding hospitals (36.2%), the documented structure and process of the response to deterioration varied considerably. All hospitals used a 12-hourly minimum vital signs measurement frequency. Thereafter, for a low-risk patient, the minimum frequency varied from '6-12 hourly' to 'hourly'. Frequencies were higher for higher risk categories. Expected escalation responses were highly individualised between hospitals. Other than repeat observations, only nine (16.4%) documents described specific clinical actions for ward staff to consider/perform whilst awaiting responding personnel. Maximum permitted response times for medium-risk and high-risk patients varied widely, even when based on the same EWS. Only 33/55 documents (60%) gave clear instructions regarding who to contact 'out of hours'. CONCLUSIONS: The 'deteriorating patient' policies of the hospitals studied varied in their contents and often omitted precise instructions for staff. We recommend that individual hospitals review these documents, and that research and/or consensus are used to develop a national algorithm regarding the response to patient deterioration.

A comparison of the ability of the National Early Warning Score and the National Early Warning Score 2 to identify patients at risk of in-hospital mortality: A multi-centre database study.

AIMS: To compare the ability of the National Early Warning Score (NEWS) and the National Early Warning Score 2 (NEWS2) to identify patients at risk of in-hospital mortality and other adverse outcomes. METHODS: We undertook a multi-centre retrospective observational study at five acute hospitals from two UK NHS Trusts. Data were obtained from completed adult admissions who were not fit enough to be discharged alive on the day of admission. Diagnostic coding and oxygen prescriptions were used to identify patients with type II respiratory failure (T2RF). The primary outcome was in-hospital mortality within 24 h of a vital signs observation. Secondary outcomes included unanticipated intensive care unit admission or cardiac arrest within 24 h of a vital signs observation. Discrimination was assessed using the c-statistic. RESULTS: Among 251,266 adult admissions, 48,898 were identified to be at risk of T2RF by diagnostic coding. In this group, NEWS2 showed statistically significant lower discrimination (c-statistic, 95% CI) for identifying in-hospital mortality within 24 h (0.860, 0.857-0.864) than NEWS (0.881, 0.878-0.884). For 1394 admissions with documented T2RF, discrimination was similar for both systems: NEWS2 (0.841, 0.827-0.855), NEWS (0.862, 0.848-0.875). For all secondary endpoints, NEWS2 showed no improvements in discrimination. CONCLUSIONS: NEWS2 modifications to NEWS do not improve discrimination of adverse outcomes in patients with documented T2RF and decrease discrimination in patients at risk of T2RF. Further evaluation of the relationship between SpO2 values, oxygen therapy and risk should be investigated further before wide-scale adoption of NEWS2.

Nurse staffing, nursing assistants and hospital mortality: retrospective longitudinal cohort study.

OBJECTIVE: To determine the association between daily levels of registered nurse (RN) and nursing assistant staffing and hospital mortality. DESIGN: This is a retrospective longitudinal observational study using routinely collected data. We used multilevel/hierarchical mixed-effects regression models to explore the association between patient outcomes and daily variation in RN and nursing assistant staffing, measured as hours per patient per day relative to ward mean. Analyses were controlled for ward and patient risk. PARTICIPANTS: 138 133 adult patients spending >1 days on general wards between 1 April 2012 and 31 March 2015. OUTCOMES: In-hospital deaths. RESULTS: Hospital mortality was 4.1%. The hazard of death was increased by 3% for every day a patient experienced RN staffing below ward mean (adjusted HR (aHR) 1.03, 95% CI 1.01 to 1.05). Relative to ward mean, each additional hour of RN care available over the first 5 days of a patient's stay was associated with 3% reduction in the hazard of death (aHR 0.97, 95% CI 0.94 to 1.0). Days where admissions per RN exceeded 125% of the ward mean were associated with an increased hazard of death (aHR 1.05, 95% CI 1.01 1.09). Although low nursing assistant staffing was associated with increases in mortality, high nursing assistant staffing was also associated with increased mortality. CONCLUSION: Lower RN staffing and higher levels of admissions per RN are associated with increased risk of death during an admission to hospital. These findings highlight the possible consequences of reduced nurse staffing and do not give support to policies that encourage the use of nursing assistants to compensate for shortages of RNs.

Relationships between healthcare staff characteristics and the conduct of vital signs observations at night: Results of a survey and factor analysis.

AIM: To explore the association of healthcare staff with factors relevant to completing observations at night. DESIGN: Online survey conducted with registered nurses, midwives, healthcare support staff and student nurses who had worked at least one night shift in a National Health Service hospital in England. METHODS: Exploratory factor analysis and mixed effects regression model adjusting for role, number of night shifts worked, experience and shift patterns. RESULTS: Survey items were summarized into four factors: (a) workload and resources; (b) prioritization; (c) safety culture; (d) responsibility and control. Staff experience and role were associated with conducting surveillance tasks. Nurses with greater experience associated workload and resources with capacity to complete work at night. Responses of student nurses and midwives showed higher propensity to follow the protocol for conducting observations. Respondents working night shifts either exclusively or occasionally perceived that professional knowledge rather than protocol guided care tasks during night shifts.

Predicting in-hospital mortality and unanticipated admissions to the intensive care unit using routinely collected blood tests and vital signs: Development and validation of a multivariable model.

AIM: The National Early Warning System (NEWS) is based on vital signs; the Laboratory Decision Tree Early Warning Score (LDT-EWS) on laboratory test results. We aimed to develop and validate a new EWS (the LDTEWS:NEWS risk index) by combining the two and evaluating the discrimination of the primary outcome of unanticipated intensive care unit (ICU) admission or in-hospital mortality, within 24 h. METHODS: We studied emergency medical admissions, aged 16 years or over, admitted to Oxford University Hospitals (OUH) and Portsmouth Hospitals (PH). Each admission had vital signs and laboratory tests measured within their hospital stay. We combined LDT-EWS and NEWS values using a linear time-decay weighting function imposed on the most recent blood tests. The LDTEWS:NEWS risk index was developed using data from 5 years of admissions to PH, and validated on a year of data from both PH and OUH. We tested the risk index's ability to discriminate the primary outcome using the c-statistic. RESULTS: The development cohort contained 97,933 admissions (median age = 73 years) of which 4723 (4.8%) resulted inhospital death and 1078 (1.1%) in unanticipated ICU admission. We validated the risk index using data from PH (n = 21,028) and OUH (n = 16,383). The risk index showed a higher discrimination in the validation sets (c-statistic value (95% CI)) (PH, 0.901 (0.898-0.905); OUH, 0.916 (0.911-0.921)), than NEWS alone (PH, 0.877 (0.873-0.882); OUH, 0.898 (0.893-0.904)). CONCLUSIONS: The LDTEWS:NEWS risk index increases the ability to identify patients at risk of deterioration, compared to NEWS alone.