Structural causal model with expert augmented knowledge to estimate the effect of oxygen therapy on mortality in the ICU.

Recent advances in causal inference techniques, more specifically, in the theory of structural causal models, provide the framework for identifying causal effects from observational data in cases where the causal graph is identifiable, i.e., the data generation mechanism can be recovered from the joint distribution. However, no such studies have been performed to demonstrate this concept with a clinical example. We present a complete framework to estimate the causal effects from observational data by augmenting expert knowledge in the model development phase and with a practical clinical application. Our clinical application entails a timely and essential research question, the effect of oxygen therapy intervention in the intensive care unit (ICU). The result of this project is helpful in a variety of disease conditions, including severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) patients in the ICU. We used data from the MIMIC-III database, a widely used health care database in the machine learning community with 58,976 admissions from an ICU in Boston, MA, to estimate the oxygen therapy effect on morality. We also identified the model's covariate-specific effect on oxygen therapy for more personalized intervention.

Feasibility and Acceptability of a mHealth Self-Management Intervention for Pediatric Transplant Families.

Families of pediatric solid organ transplant recipients need ongoing education and support in the first 30 days following hospital discharge for the transplantation. The purpose of this report is to describe the feasibility, acceptability, and preliminary efficacy of a mHealth family-self management intervention, (myFAMI), designed to improve post-discharge outcomes of coping, family quality of life, self-efficacy, family self-management, and utilization of health care resources. We enrolled 46 primary family members. myFAMI was feasible and acceptable; 81% (n=17/21) of family members completed the app at least 24/30 days (goal 80% completion rate). Family members generated 134 trigger alerts and received a nurse response within the goal timeframe of < 2 h 99% of the time. Although there were no significant differences between groups, primary outcomes were in the expected direction. The intervention was well received and is feasible for future post-discharge interventions for families of children who receive an organ transplant.

An mHealth App-Based Self-management Intervention for Family Members of Pediatric Transplant Recipients (myFAMI): Framework Design and Development Study.

BACKGROUND: Solid-organ transplantation is the treatment of choice for children with end-stage organ failure. Ongoing recovery and medical management at home after transplant are important for recovery and transition to daily life. Smartphones are widely used and hold the potential for aiding in the establishment of mobile health (mHealth) protocols. Health care providers, nurses, and computer scientists collaboratively designed and developed mHealth family self-management intervention (myFAMI), a smartphone-based intervention app to promote a family self-management intervention for pediatric transplant patients' families. OBJECTIVE: This paper presents outcomes of the design stages and development actions of the myFAMI app framework, along with key challenges, limitations, and strengths. METHODS: The myFAMI app framework is built upon a theory-based intervention for pediatric transplant patients, with aid from the action research (AR) methodology. Based on initially defined design motivation, the team of researchers collaboratively explored 4 research stages (research discussions, feedback and motivations, alpha testing, and deployment and release improvements) and developed features required for successful inauguration of the app in the real-world setting. RESULTS: Deriving from app users and their functionalities, the myFAMI app framework is built with 2 primary components: the web app (for nurses' and superadmin usage) and the smartphone app (for participant/family member usage). The web app stores survey responses and triggers alerts to nurses, when required, based on the family members' response. The smartphone app presents the notifications sent from the server to the participants and captures survey responses. Both the web app and the smartphone app were built upon industry-standard software development frameworks and demonstrate great performance when deployed and used by study participants. CONCLUSIONS: The paper summarizes a successful and efficient mHealth app-building process using a theory-based intervention in nursing and the AR methodology in computer science. Focusing on factors to improve efficiency enabled easy navigation of the app and collection of data. This work lays the foundation for researchers to carefully integrate necessary information (from the literature or experienced clinicians) to provide a robust and efficient solution and evaluate the acceptability, utility, and usability for similar studies in the future. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1002/nur.22010.

Using the Engaging Parents in Education for Discharge (ePED) iPad Application to Improve Parent Discharge Experience.

PURPOSE: The purpose of this study was to evaluate the use of the Engaging Parents in Education for Discharge (ePED) iPad application on parent experiences of hospital discharge teaching and care coordination. Hypotheses were: parents exposed to discharge teaching using ePED will have 1) higher quality of discharge teaching and 2) better care coordination than parents exposed to usual discharge teaching. The secondary purpose examined group differences in the discharge teaching, care coordination, and 30-day readmissions for parents of children with and without a chronic condition. DESIGN/METHODS: Using a quasi-experimental design, ePED was implemented on one inpatient unit (n = 211) and comparison group (n = 184) from a separate unit at a pediatric academic medical center. Patient experience outcome measures collected on day of discharge included Quality of Discharge Teaching Scale-Delivery (QDTS-D) and care coordination measured by Care Transition Measure (CTM). Thirty-day readmission was abstracted from records. RESULTS: Parents taught using ePED reported higher QDTS-D scores than parents without ePED (p = .002). No differences in CTM were found between groups. Correlations between QDTS-D and CTM were small for ePED (r = 0.14, p 0.03) and non-ePED (r = 0.29, p < .001) parent groups. CTM was weakly associated with 30-day readmissions in the ePED group. CONCLUSION: The use of ePED by the discharging nurse enhances parent-reported quality of discharge teaching. PRACTICE IMPLICATIONS: The ePED app is a theory-based structured conversation guide to engage parents in discharge preparation. Nursing implementation of ePED contributes to optimizing the patient/family healthcare experience.

Pilot study protocol of a mHealth self-management intervention for family members of pediatric transplant recipients.

Solid-organ transplantation is the treatment of choice for end-stage organ failure. Parents of pediatric transplant recipients who reported a lack of readiness for discharge had more difficulty coping and managing their child's medically complex care at home. In this paper, we describe the protocol for the pilot study of a mHealth intervention (myFAMI). The myFAMI intervention is based on the Individual and Family Self-Management Theory and focuses on family self-management of pediatric transplant recipients at home. The purpose of the pilot study is to test the feasibility of the myFAMI intervention with family members of pediatric transplant recipients and to test the preliminary efficacy on postdischarge coping through a randomized controlled trial. The sample will include 40 family units, 20 in each arm of the study, from three pediatric transplant centers in the United States. Results from this study may advance nursing science by providing insight for the use of mHealth to facilitate patient/family-nurse communication and family self-management behaviors for family members of pediatric transplant recipients.

SmartHeLP: Smartphone-based Hemoglobin Level Prediction Using an Artificial Neural Network.

Blood hemoglobin level (Hgb) measurement has a vital role in the diagnosis, evaluation, and management of numerous diseases. We describe the use of smartphone video imaging and an artificial neural network (ANN) system to estimate Hgb levels non-invasively. We recorded 10 second-300 frame fingertip videos using a smartphone in 75 adults. Red, green, and blue pixel intensities were estimated for each of 100 area blocks in each frame and the patterns across the 300 frames were described. ANN was then used to develop a model using the extracted video features to predict hemoglobin levels. In our study sample, with patients 20-56 years of age, and gold standard hemoglobin levels of 7.6 to 13.5 g/dL., we observed a 0.93 rank order of correlation between model and gold standard hemoglobin levels. Moreover, we identified specific regions of interest in the video images which reduced the required feature space.