MétaCan
Menu
Back to cohort
Record W2977964590 · doi:10.2196/15229

A Smartphone App for Patients With End-Stage Liver Disease Can Detect Behavioral Changes That Predict Liver-Related Events

2019· article· en· W2977964590 on OpenAlexvenueno aff
Jordan Sack, Todd G. Reid, Eric Schlossberg, Nikroo Hashemi

Bibliographic record

VenueIproceedings · 2019
Typearticle
Languageen
FieldMedicine
TopicLiver Disease and Transplantation
Canadian institutionsnot available
Fundersnot available
KeywordsMedicineLiver diseaseHepatic encephalopathyDiseaseStage (stratigraphy)Patient portalModel for End-Stage Liver DiseaseProspective cohort studyInternal medicineEmergency medicineHealth careCirrhosisLiver transplantation

Abstract

fetched live from OpenAlex

Background Patients with end-stage liver disease have significant morbidity and mortality. The 90-day readmission rate for these patients is up to 53% at a cost of $4.45 billion annually. Healthcare delivery for these patients is often fragmented and inadequate. Smartphone-based remote health monitoring may reduce hospitalizations by earlier detection of premonitory warning signs associated with liver-related complications. Hepatic encephalopathy which is a common cause of hospitalization and sleep disturbance and subtle/sub-clinical behavioral changes are early warning signs. Objective In this pilot study of patients with end-stage liver disease, we assessed the feasibility of our smartphone app to detect physiologic and behavioral changes during the 7 days prior to liver-related hospitalizations or urgent visits. Methods This is a prospective multicenter pilot study of patients with end-stage liver disease who were enrolled at three academic centers to receive our smartphone app for a 180-day period. English speaking patients age ≥18 years who receive liver care at one of the study sites, do not actively use alcohol or drugs, have had a liver-related complication in the previous 3 months (ascites, hepatic encephalopathy, variceal bleeding, bacterial peritonitis), and own an Android smartphone with internet connectivity were eligible. The smartphone app solicits emotions daily and collects passive data on activity, sleep, and social interactions. Patients received monthly in-app questions about how many liver-related events they had over the preceding month. Surveys on sociodemographic characteristics and health status were collected at baseline, 90 days, and 180 days. Clinical data on liver-related hospitalizations or urgent visits (“events”) were collected prospectively through chart review. Smartphone data on activity, sleep, social interactions, and emotions were analyzed during the 7-day period preceding a liver event and compared to the average over the study period. Statistical analyses were performed with Mann-Whitney U test. Results An interim analysis of the 40 enrolled patients who met all eligibility criteria found that 15 patients had 27 liver-related events during the study period. These patients were predominantly men with a median age of 56 years. 61% of these patients responded to the monthly in-app question about hospitalizations and did so with 100% accuracy. In the 7-day period prior to the event, these patients had more sleep disturbances and changes in activity score (P=.04; P=.04). There was no statistically significant difference in social scores during the 7-day period prior to the event. Emoji selection among this group was too small for analysis. Conclusions The interim analysis of this pilot study suggests that passive data collected from our smartphone app can detect behavioral changes that could be used to predict liver-related events. Specifically, significant changes in smartphone activity and sleep disturbances were identified during the 7-day period prior to a liver-related event. Smartphone-based remote health monitoring appears to be feasible in this patient population and has the potential to reduce hospitalizations through early detection of early warning signs.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.006
Threshold uncertainty score0.796

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.014
GPT teacher head0.231
Teacher spread0.216 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2019
Admission routes1
Has abstractyes

Explore more

Same venueIproceedingsSame topicLiver Disease and TransplantationFrench-language works237,207