Deep Q-learning for Predicting Asthma Attack with Considering Personalized Environmental Triggers' Risk Scores

The purpose of our present study was to develop a forecasting method that would help asthmatic individuals to take evasive action when the probability of an attack was at THEIR PERSONAL THRESHOLD levels. The results are encouraging. Risk factor analysis helps improve the agent's performance (by allowing it to consider personalized risk score of asthma attack triggers while making a decision and being able to ignore the non-triggers), increasing transparency of deep reinforcement learning in medicine applications (by using the results of analyzing risk factors and its association to take actions), and increase accuracy over time since the association risk factor indicators are also changing over time with more accuracy rate. It also brings the possibility of including population-based health in personalized health, which could support a more efficient self-management of chronic diseases.

Personalized Prediction of Asthma Severity and Asthma Attack for a Personalized Treatment Regimen

Control of asthma is critical for disease management and quality of life. Asthma treatment depends on the patient demographic information (e.g., age), and disease severity, which is determined by: (1) how symptoms affect a patient's daily life, (2) measured lung function, and (3) estimated risk of having an asthma attack. In this paper, we will present the Tensorflow Text Classification (TC) method to classify a patient's asthma severity level. We will also propose a Qlearning method to train an agent through trials and errors to improve the prediction accuracy and create a personalized treatment regimen for asthma patients.

Faster clinical response to the onset of adverse events: A wearable metacognitive attention aid for nurse triage of clinical alarms

Objective

This study evaluates the potential for improving patient safety by introducing a metacognitive attention aid that enables clinicians to more easily access and use existing alarm/alert information. It is hypothesized that this introduction will enable clinicians to easily triage alarm/alert events and quickly recognize emergent opportunities to adapt care delivery. The resulting faster response to clinically important alarms/alerts has the potential to prevent adverse events and reduce healthcare costs.

Materials and methods

A randomized within-subjects single-factor clinical experiment was conducted in a high-fidelity 20-bed simulated acute care hospital unit. Sixteen registered nurses, four at a time, cared for five simulated patients each. A two-part highly realistic clinical scenario was used that included representative: tasking; information; and alarms/alerts. The treatment condition introduced an integrated wearable attention aid that leveraged metacognition methods from proven military systems. The primary metric was time for nurses to respond to important alarms/alerts.

Results

Use of the wearable attention aid resulted in a median relative within-subject improvement for individual nurses of 118% (W = 183, p = 0.006). The top quarter of relative improvement was 3,303% faster (mean; 17.76 minutes reduced to 1.33). For all unit sessions, there was an overall 148% median faster response time to important alarms (8.12 minutes reduced to 3.27; U = 2.401, p = 0.016), with 153% median improvement in consistency across nurses (F = 11.670, p = 0.001).

Discussion and conclusion

Existing device-centric alarm/alert notification solutions can require too much time and effort for nurses to access and understand. As a result, nurses may ignore alarms/alerts as they focus on other important work. There has been extensive research on reducing alarm frequency in healthcare. However, alarm safety remains a top problem. Empirical observations reported here highlight the potential of improving patient safety by supporting the meta-work of checking alarms.

Microbiology Education in Nursing Practice

Nurses must have sufficient education and training in microbiology to perform many roles within clinical nursing practice (e.g., administering antibiotics, collecting specimens, preparing specimens for transport and delivery, educating patients and families, communicating results to the healthcare team, and developing care plans based on results of microbiology studies and patient immunological status). It is unclear whether the current microbiology courses required of nursing students in the United States focus on the topics that are most relevant to nursing practice. To gauge the relevance of current microbiology education to nursing practice, we created a confidential, web-based survey that asked nurses about their past microbiology education, the types of microbiology specimens they collect, their duties that require knowledge of microbiology, and how frequently they encounter infectious diseases in practice. We used the survey responses to develop data-driven recommendations for educators who teach microbiology to pre-nursing and nursing students. Two hundred ninety-six Registered Nurses (RNs) completed the survey. The topics they deemed most relevant to current practice were infection control, hospital-acquired infections, disease transmission, and collection and handling of patient specimens. Topics deemed least relevant were the Gram stain procedure and microscope use. In addition, RNs expressed little interest in molecular testing methods. This may reflect a gap in their understanding of the uses of these tests, which could be bridged in a microbiology course. We now have data in support of anecdotal evidence that nurses are most engaged when learning about microbiology topics that have the greatest impact on patient care. Information from this survey will be used to shift the focus of microbiology courses at our university to topics more relevant to nursing practice. Further, these findings may also support an effort to evolve national recommendations for microbiology education in pre-nursing and nursing curricula.

The Hidden Lives of Nurses' Cognitive Artifacts

BACKGROUND

Standardizing nursing handoffs at shift change is recommended to improve communication, with electronic tools as the primary approach. However, nurses continue to rely on personally created paper-based cognitive artifacts - their "paper brains" - to support handoffs, indicating a deficiency in available electronic versions.

OBJECTIVE

The purpose of this qualitative study was to develop a deep understanding of nurses' paper-based cognitive artifacts in the context of a cancer specialty hospital.

METHODS

After completing 73 hours of hospital unit field observations, 13 medical oncology nurses were purposively sampled, shadowed for a single shift and interviewed using a semi-structured technique. An interpretive descriptive study design guided analysis of the data corpus of field notes, transcribed interviews, images of nurses' paper-based cognitive artifacts, and analytic memos.

RESULTS

Findings suggest nurses' paper brains are personal, dynamic, living objects that undergo a life cycle during each shift and evolve over the course of a nurse's career. The life cycle has four phases: Creation, Application, Reproduction, and Destruction. Evolution in a nurse's individually styled, paper brain is triggered by a change in the nurse's environment that reshapes cognitive needs. If a paper brain no longer provides cognitive support in the new environment, it is modified into (adapted) or abandoned (made extinct) for a different format that will provide the necessary support.

CONCLUSIONS

The "hidden lives" - the life cycle and evolution - of paper brains have implications for the design of successful electronic tools to support nursing practice, including handoff. Nurses' paper brains provide cognitive support beyond the context of handoff. Information retrieval during handoff is undoubtedly an important function of nurses' paper brains, but tools designed to standardize handoff communication without accounting for cognitive needs during all phases of the paper brain life cycle or the ability to evolve with changes to those cognitive needs will be underutilized.

Information Content Across Types of Nurse Cognitive Artifacts

Acute care nurses commonly use personalized cognitive artifacts to organize information during a shift. The purpose of this content analysis is to compare information content across three formats of cognitive artifacts used by acute care nurses in a medical oncology unit: hand-made free-form, preprinted skeleton, and EHR-generated. Information contained in free-form and skeleton artifacts is more tailored to specific patient context than the NSR. Free-form and skeleton artifacts provide a space for synthesizing information to construct a "story of the patient" that is missing in the NSR. Future design of standardized handoff tools will need to take these differences into account for successful adoption by acute care nurses, including tailoring of information by patient, not just unit type, and allowing a space for nurses to construct a narrative describing the patients "story."

The Symbolic Functions of Nurses' Cognitive Artifacts on a Medical Oncology Unit

Acute care nurses continue to rely on personally created paper-based tools-their "paper brains"-to support work during a shift, although standardized handoff tools are recommended. This interpretive descriptive study examines the functions these paper brains serve beyond handoff in the medical oncology unit at a cancer specialty hospital. Thirteen medical oncology nurses were each shadowed for a single shift and interviewed afterward using a semistructured technique. Field notes, transcribed interviews, images of nurses' paper brains, and analytic memos were inductively coded, and analysis revealed paper brains are symbols of patient and nurse identity. Caution is necessary when attempting to standardize nurses' paper brains as nurses may be resistant to such changes due to their pride in constructing personal artifacts to support themselves and their patients.

The Safety of Hospital Beds: Ingress, Egress, and In-Bed Mobility

To explore the safety of the standard and the low hospital bed, we report on a microanalysis of 15 patients' ability to ingress, move about the bed, and egress. The 15 participants were purposefully selected with various disabilities. Bed conditions were randomized with side rails up or down and one low bed with side rails down. We explored the patients' use of the side rails, bed height, ability to lift their legs onto the mattress, and ability to turn, egress, and walk back to the chair. The standard bed was too high for some participants, both for ingress and egress. Side rails were used by most participants when entering, turning in bed, and exiting. We recommend that side rails be reconsidered as a means to facilitate in-bed movement, ingress, and egress. Furthermore, single deck height settings for all patients are not optimal. Low beds as a safety measure must be re-evaluated.

Collaborative Learning Using Nursing Student Dyads in the Clinical Setting

Formal pairing of student nurses to work collaboratively on one patient assignment is a strategy for improving the quality and efficiency of clinical instruction while better utilizing the limited resources at clinical agencies. The aim of this qualitative study was to explore the student nurse and patient experiences of collaborative learning when peer dyads are used in clinical nursing education. Interviews were conducted with 11 students and 9 patients. Students described the process of collaborative learning as information sharing, cross-checking when making clinical decisions, and group processing when assessing the outcomes of nursing interventions. Positive outcomes reported by students and patients included reduced student anxiety, increased confidence and task efficiency. Students’ primary concern was reduced opportunity to perform hands-on skills which had to be negotiated within each dyad. Meeting the present and future challenges of educating nurses will require innovative models of clinical instruction such as collaborative learning using student peer dyads.

Evaluation of an integrated graphical display to promote acute change detection in ICU patients

OBJECTIVE

The purpose of this study was to evaluate ICU nurses' ability to detect patient change using an integrated graphical information display (IGID) versus a conventional tabular ICU patient information display (i.e. electronic chart).

DESIGN

Using participants from two different sites, we conducted a repeated measures simulator-based experiment to assess ICU nurses' ability to detect abnormal patient variables using a novel IGID versus a conventional tabular information display. Patient scenarios and display presentations were fully counterbalanced.

MEASUREMENTS

We measured percent correct detection of abnormal patient variables, nurses' perceived workload (NASA-TLX), and display usability ratings.

RESULTS

32 ICU nurses (87% female, median age of 29 years, and median ICU experience of 2.5 years) using the IGID detected more abnormal variables compared to the tabular display [F(1, 119)=13.0, p<0.05]. There was a significant main effect of site [F(1, 119)=14.2], with development site participants doing better. There were no significant differences in nurses' perceived workload. The IGID display was rated as more usable than the conventional display [F(1, 60)=31.7].

CONCLUSION

Overall, nurses reported more important physiological information with the novel IGID than tabular display. Moreover, the finding of site differences may reflect local influences in work practice and involvement in iterative display design methodology. Information displays developed using user-centered design should accommodate the full diversity of the intended user population across use sites.

Impaired parasympathetic response to feeding in ventilated preterm babies

BACKGROUND

Premature very low birthweight (VLBW) infants are born with an underdeveloped parasympathetic nervous system (PNS) which may limit their ability to respond adequately to feeding and may limit their capacities for extrauterine growth and development.

OBJECTIVES

To describe the patterns of autonomic response to feeding and identify relationships between change in heart period variability measures over time with selected infant characteristics.

METHODS

Individual growth curve analysis techniques were used to describe the patterns of change over time in sympathetic and parasympathetic tone as measured by low and high frequency heart period power.

RESULTS

Sixteen mechanically ventilated VLBW infants with a mean corrected gestational age of 30.4 weeks participated in the study. The low frequency (LF) power slope was -17.67 (p = 0.0002) and the high frequency (HF) power slope was -0.92 (0.0003). There was a significant relationship between HF slope and birth gestational age (r = -0.49, p = 0.05).

CONCLUSIONS

HF power, representing primarily parasympathetic activity, did not increase with enteral feeding as anticipated. LF power, an indicator of sympathetic tone, decreased during and after feeding suggesting the anticipated effect of inhibition of the sympathetic nervous system in response to the gut stimulus. Critically ill VLBW infants possess an overriding sympathetic response, but may not have adequate PNS tone development.

Characteristics of heart period variability in intubated very low birth weight infants with respiratory disease

BACKGROUND

Heart period variability provides a measure of balance between the sympathetic nervous system (SNS) and parasympathetic nervous system (PNS). Since the PNS develops during the final weeks of gestation, premature infants have an overriding SNS. Spectral power analysis of heart period variability reveals two main frequency regions, the low frequency region (LF) representing primarily SNS activity and the high frequency region (HF) representing PNS activity.

OBJECTIVES

To identify the characteristics of heart period power in the LF and HF regions in very low birth weight (VLBW) infants in the neonatal intensive care unit across gestational age groups and between sleep and awake states.

METHODS

Data were collected from 16 intubated and mechanically ventilated VLBW infants with respiratory disease. Using spectral analysis techniques, heart period power in the two main frequency regions was extracted.

RESULTS

HF power did not improve with gestational age as expected. LF power did increase with age, albeit nonsignificantly. LF and HF power were not significantly different between awake and sleep states.

CONCLUSIONS

The results of this preliminary study suggest that PNS tone does not improve with gestational age in VLBW infants with respiratory disease. The intensive care environment may stimulate a sympathetic response in these infants and disrupt normal PNS development.