Early Warning of Acute Decompensation in Heart Failure Patients Using a Noncontact Measure of Stability Index

Javed, Faizan; Farrugia, Steven; Colefax, Michael; Schindhelm, Klaus

doi:10.1109/tbme.2015.2463283

Cited by 9 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To achieve better alert signaling performance these signals were merged using a naive Bayesian method and this was used in their ADHF prediction system [72]. The last non-invasive ADHF prediction method we will mention is the work of [56]. The performance of Bayesian online change point detection (BOCPD) and retrospective change point detection (RCPD) methods was evaluated.…”

Section: Non-invasive Prediction Methodsmentioning

confidence: 99%

“…We can call the chosen time interval forward target window, (the descriptiveness of the names assigned to temporal windows depends on the reference context. As an example, in a similar situation the authors in [56] use a different notation) and it should be large enough to cover the mentioned manifestation delays. In the field of CHFS telemedicine, the essence of patient monitoring is a process of recurrent diagnostics.…”

Section: Temporal Properties Of Recurrent Diagnosticsmentioning

confidence: 99%

See 1 more Smart Citation

Clinical Predictive Modeling of Heart Failure: Domain Description, Models’ Characteristics and Literature Review

Odrobina

2024

Diagnostics

View full text Add to dashboard Cite

This study attempts to identify and briefly describe the current directions in applied and theoretical clinical prediction research. Context-rich chronic heart failure syndrome (CHFS) telemedicine provides the medical foundation for this effort. In the chronic stage of heart failure, there are sudden exacerbations of syndromes with subsequent hospitalizations, which are called acute decompensation of heart failure (ADHF). These decompensations are the subject of diagnostic and prognostic predictions. The primary purpose of ADHF predictions is to clarify the current and future health status of patients and subsequently optimize therapeutic responses. We proposed a simplified discrete-state disease model as an attempt at a typical summarization of a medical subject before starting predictive modeling. The study tries also to structure the essential common characteristics of quantitative models in order to understand the issue in an application context. The last part provides an overview of prediction works in the field of CHFS. These three parts provide the reader with a comprehensive view of quantitative clinical predictive modeling in heart failure telemedicine with an emphasis on several key general aspects. The target community is medical researchers seeking to align their clinical studies with prognostic or diagnostic predictive modeling, as well as other predictive researchers. The study was written by a non-medical expert.

show abstract

Section: Non-invasive Prediction Methodsmentioning

confidence: 99%

Section: Temporal Properties Of Recurrent Diagnosticsmentioning

confidence: 99%

Clinical Predictive Modeling of Heart Failure: Domain Description, Models’ Characteristics and Literature Review

Odrobina

2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…The models developed to date can be defined as predictive (models predicting the medium-long term risk of exacerbations, when the patient is in a stable state) or diagnostic (models detecting an exacerbation episode which is already on course). Regarding diagnostic exacerbation models in HF [7,8,9,10,11] and COPD [12,13,14,15,16,17,18,19,20,21], they have shown variable and poor Sn ranging between 40–75%. Ledwidge et al [22] developed a HF diagnostic exacerbation model with higher Sn (82%) though low Sp (68%).…”

Section: Introductionmentioning

confidence: 99%

Effort Oxygen Saturation and Effort Heart Rate to Detect Exacerbations of Chronic Obstructive Pulmonary Disease or Congestive Heart Failure

Gálvez‐Barrón

Álvarez

Ribas

et al. 2019

JCM

View full text Add to dashboard Cite

Background: current algorithms for the detection of heart failure (HF) and chronic obstructive pulmonary disease (COPD) exacerbations have poor performance. Methods: this study was designed as a prospective longitudinal trial. Physiological parameters were evaluated at rest and effort (walking) in patients who were in the exacerbation or stable phases of HF or COPD. Parameters with relevant discriminatory power (sensitivity (Sn) or specificity (Sp) ≥ 80%, and Youden index ≥ 0.2) were integrated into diagnostic algorithms. Results: the study included 127 patients (COPD: 56, HF: 54, both: 17). The best algorithm for COPD included: oxygen saturation (SaO2) decrease ≥ 2% in minutes 1 to 3 of effort, end-of-effort heart rate (HR) increase ≥ 10 beats/min and walking distance decrease ≥ 35 m (presence of one criterion showed Sn: 0.90 (95%, CI(confidence interval): 0.75–0.97), Sp: 0.89 (95%, CI: 0.72–0.96), and area under the curve (AUC): 0.92 (95%, CI: 0.85–0.995)); and for HF: SaO2 decrease ≥ 2% in the mean-of-effort, HR increase ≥ 10 beats/min in the mean-of-effort, and walking distance decrease ≥ 40 m (presence of one criterion showed Sn: 0.85 (95%, CI: 0.69–0.93), Sp: 0.75 (95%, CI: 0.57–0.87) and AUC 0.84 (95%, CI: 0.74–0.94)). Conclusions: effort situations improve the validity of physiological parameters for detection of HF and COPD exacerbation episodes.

show abstract

“…(100) While the individual studies presented in Table 1 are grossly heterogeneous, due to differences in the prediction goal, data collected and methodology, some common trends exist. The majority of the studies feature unbalanced datasets, with few events compared to the number of observations (75,(101)(102)(103)(104). Some studies developed models that included measurements of intrathoracic bioimpedance (105).…”

Section: Prediction Models In Chronic Heart Failurementioning

confidence: 99%

“…Many of the studies did not report the ROC-AUC for their models (106)(107)(108)(109)(110), which makes direct performance comparisons difficult. However, ROC-AUC alone can be misleading in the context of heavily unbalanced data, where a small decrease in specificity might result in numerous false alerts.…”

Section: Prediction Models In Chronic Heart Failurementioning

confidence: 99%

Improving Telemonitoring for Chronic Heart Failure Patients: A Data-driven Investigation into improving Equity and AI models for Telemedicine

Xylander

View full text Add to dashboard Cite

Denne artikel baserede ph.d.-afhandling undersøger potentialet for at forbedre telemonitorering af patienter med kronisk hjertesvigt / hjerteinsufficiens (CHF). Første del af afhandlingen praesenterer årsagerne og epidemiologien for CHF og uddyber den nuvaerende tendens til at anvende telemedicinteknologier i håndteringen af CHF-patienter. Den første artikel, "Does geographical distance impact the effectiveness of supplementary telemedicine for chronic heart failure patients", støtter denne sektion ved at undersøge litteraturen om uligheder i adgangen til sundhedspleje for CHF-patienter og giver kvantitative beviser for, at supplementaer telemedicin kan hjaelpe med at tackle nogle af disse uligheder ved at reducere geografisk afstand som en hindring for sundhedsplejeadgang.Den naeste del af ph.d.-afhandlingen undersøger potentialet for at forbedre telemonitoreringsstrategierne for CHF-patienter, der modtager telemedicin i Region Nordjylland, i forbindelse med "Telecare Nord Hjertesvigt" projektet.Anden artikel, " Weekly Blood Pressure and Weight Measurements shows Potential for Predicting Deterioration in Telemonitored Chronic Heart Failure Patients", er en eksplorativ undersøgelse af hvorvidt ugentlige målinger af biometriske data, herunder blodtryk, vaegt og puls, kan bruges til at skelne mellem stabile perioder og perioder, der fører til indlaeggelse. Dette gøres ved hjaelp af en parret observationsstrategi med 33 begivenheds-og ikke-begivenhedsperioder. Undersøgelsen viser, at inklusion af aendringer i periodiske tendenser af biometriske vaerdier i algoritmen øger modellens diskriminerende praestation.Den tredje artikel, " Prediction of 14-day hospitalization risk in chronic heart failure patients, using interpretable machine learning methods", bygger på resultaterne fra anden artikel og bruger maskinlaeringsalgoritmer til at udvikle kliniske forudsigelsesmodeller, der giver et risikoestimat for ikke-planlagte indlaeggelser inden for den naeste 14-dages periode for hver hjemmemåling udført af patienten. I artiklen anvendes et "supervised learning" design og den inkluderer 11.575 observationer af teleovervågede vaerdier med et label, der angiver tilstedevaerelsen af en ikke-planlagt indlaeggelse i de følgende 14 dage efter observationen. Maskinlaeringsteknikkerne, der er inkluderet i modelleringen, er valgt for deres fortolkelighed for at understøtte klinisk implementering.Afhandlingen er en del af et projekt, der undersøger supplementaer telemedicin for patienter med kronisk obstruktiv lungesygdom og CHF-patienter i Region 17 LIST OF PUBLICATIONS Thesis Papers Paper I Xylander AAP, Cichosz SL, Hejlesen O, et al. Does geographical distance impact the effectiveness of supplementary telemedicine for Chronic Heart Failure patients.

show abstract

Early Warning of Acute Decompensation in Heart Failure Patients Using a Noncontact Measure of Stability Index

Abstract: These results demonstrate that the design and implementation of such a system is a positive step toward developing noncontact systems capable of preventing acute decompensation, reducing readmissions to hospital and ensuring better quality of life for HF patients.

Cited by 9 publications

References 32 publications

Clinical Predictive Modeling of Heart Failure: Domain Description, Models’ Characteristics and Literature Review

Clinical Predictive Modeling of Heart Failure: Domain Description, Models’ Characteristics and Literature Review

Effort Oxygen Saturation and Effort Heart Rate to Detect Exacerbations of Chronic Obstructive Pulmonary Disease or Congestive Heart Failure

Improving Telemonitoring for Chronic Heart Failure Patients: A Data-driven Investigation into improving Equity and AI models for Telemedicine

Contact Info

Product

Resources

About