FBFilipe Barata

Filipe Barata

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Filipe Barata has a total of 76 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A pilot study on AI-based voice analysis for monitoring patients hospitalized with acute decompensated heart failure

    by Leonhard Riehle, Mariam Fouad, Marcus Hott, Emanuel Heil, Chong Bin Lee, Felix Schoenrath, Soumya Vungarala, Bruce Johnson, Lyle Olson, Aurele Goetz, et al.

    Aims: Monitoring pulmonary congestion in chronic heart failure (HF) reduces decompensation and hospitalization, but conventional methods such as weight and symptom tracking are often unreliable. As fluid accumulation affects the lungs and vocal tract, subtle voice alterations may serve as a non-invasive signal for early detection of worsening HF. Methods and results: The Voice Analysis for Monitoring Patients with HF trial (VAMP-HF, NCT06566911) prospectively enrolled 104 patients hospitalized with acute decompensated HF (ADHF) across two academic centres in the USA and Germany. Daily voice recordings were collected from admission to discharge, with breathing features extracted from speech and acoustic features from sustained vowels. A machine-learning model was trained to classify recordings as admission-phase vs. discharge-phase using leave-one-patient-out. Patients with clinical deterioration, insufficient audio quality, or short length of stay were excluded. Seventy-nine patients were included in the final dataset. The model classified admission and discharge with an F1-score of 0.83 (95% CI: 0.77–0.90; AUC = 0.90). In patients with higher audio volume (N = 54), performance reached 0.89 (95% CI: 0.82–0.94; AUC = 0.91). When applied to intermediate hospitalization days, model-predicted scores showed progressive increases from admission towards discharge. Performance remained robust irrespective of significant weight loss during hospitalization. Conclusion: In this pilot study, structured voice and breathing analysis discriminated hospitalization phase from admission through discharge in patients with ADHF. This non-invasive approach captured progressive changes during the hospital course and warrants further investigation with concurrent objective congestion markers to establish physiological specificity.


  • Open Access

    Smartphone-Enabled Cough Detection in Severely Exacerbated COPD: An Exploratory Pilot Study

    by Maximilian Boesch, Julia Herrmann, Florent Baty, David Cleres, Jonathan Leathers, Elgar Fleisch, Martin H. Brutsche, Filipe Barata, Frank Rassouli

    Chronic obstructive pulmonary disease (COPD) shows rising incidence worldwide. Progressive decline in lung function is characteristic for the disease and results in various signature COPD symptoms. A significant part of COPD-associated morbidity and mortality is due to acute exacerbations, which often require hospital usage, thus disproportionately impacting healthcare expenses. Novel digital health technologies allowing remote patient monitoring are desirable to improve COPD management by tailoring treatment- and follow-up strategies. We here tested the feasibility and biomarker potential of smartphone-enabled cough monitoring during and after AECOPD in hospitalized patients. The study was designed as a single-center, prospective, longitudinal, observational cohort study and enrolled 23 subjects. A contact-free, near real-time, smartphone-enabled cough detection system was used for automated cough detection and quantification based on audio recordings. Cough counts were correlated to various clinical and biochemical markers. Cough levels were highest at study enrollment (approx. 15 coughs per hour) and gradually declined over time toward recovery (to below 5 coughs per hour) (incidence rate ratio (IRR): 0.97 [0.95-0.98], p < 0.001). There was a high degree of intra- and inter-patient variation of cough frequency and evolution. In addition, cough counts underlay significant diurnal regulation, with higher counts during daytime. Cough counts were inversely associated with oxygen saturation (IRR: 0.9 [0.87-0.95], p < 0.001) and correlated positively with body temperature (IRR: 2.00 [1.47-2.73], p < 0.001). Automated, contact-free, smartphone-enabled cough detection was feasible in COPD patients hospitalized for AECOPD. Cough counts declined over time and were associated with relevant clinical and biochemical markers. Our approach enables telemonitoring of AECOPD in near real-time and warrants further development to possibly establish cough count as an early digital biomarker for emerging AECOPD, allowing swift intervention and associated cost reductions.

  • Open Access

    Multimodal Noninvasive Assessment of C-Reactive Protein for Systemic Inflammation in Adults: Cross-Sectional Study

    by Jinjoo Shim, Sinziana Muraru, Vanessa Löw, Caroline Evers, Sandro Riedo, Rucsandra Dobrota, Elgar Fleisch, Oliver Distler, Filipe Barata

    Background: Accurate and accessible measurements of inflammatory biomarkers are crucial for the diagnosis and monitoring of inflammatory diseases. The gold-standard C-reactive protein (CRP) requires venipuncture, which, despite providing high-quality samples, can cause discomfort, anxiety, and pain, particularly in vulnerable populations such as older patients. It is also resource-intensive, is unsuitable for remote or at-home use, and lacks continuous monitoring capability. These limitations limit patient autonomy and self-management, potentially leading to poorer prognosis due to delays in assessment and medical treatments. As digital health technologies advance, there is increasing interest in leveraging digital biomarkers for remote and real-time monitoring of systemic inflammation. Digital biomarkers derived from noninvasive biofluids could provide a scalable solution for tracking inflammatory status, offering a patient-centered alternative to traditional blood-based assessments. To date, however, there is no consensus on the most suitable modality for assessment or its digitization potential. Therefore, a comprehensive evaluation of the feasibility, reliability, and patient acceptability toward noninvasive, digital inflammatory biomarkers is needed. Objective: Our aim is to evaluate the feasibility of various noninvasive methods to assess inflammatory markers and identify the optimal modality for predicting serum CRP levels. Methods: Inflammatory biomarkers were assessed in 20 participants (10 patients with systemic inflammation defined as a CRP level >5 mg/L and 10 controls) using 6 noninvasive samples (urine, sweat, saliva, exhaled breath, core body temperature, and stool samples) alongside serum samples. Patient preferences were retrieved via a questionnaire. Mann-Whitney U test, Spearman correlation, and all-subset regression were conducted to assess the relationships between serum and nonserum biomarkers and identify optimal predictive models for serum CRP levels. Results: CRP levels were significantly elevated in the inflammation group compared to controls in urine (median 4.5, IQR 4.15‐10.3 vs median 0.69, IQR 0.24‐1.39 μg/mmol; P=.001) and saliva (median 4910, IQR 2735-13,275 vs median 473, IQR 309-700 pg/mL; P=.001). Urine and saliva CRP levels strongly correlated with serum CRP (rsp=0.886; P<.001; rsp=0.709; P<.001). The multimodal model using urine and saliva CRP predicted serum CRP levels with 76.1% outperforming single-modality models. Patients favored urine and saliva tests over blood tests. Conclusions: Urine and saliva represent promising noninvasive alternatives to traditional blood tests for assessing CRP, enabling more accessible and less invasive diagnostic and monitoring approaches.


  • Open Access

    GeHirNet: A Gender-Aware Hierarchical Model for Voice Pathology Classification

    by Fan Wu, Kaicheng Zhao, Elgar Fleisch, Filipe Barata

    AI-based voice analysis shows promise for disease diagnostics, but existing classifiers often fail to accurately identify specific pathologies because of gender-related acoustic variations and the scarcity of data for rare diseases. We propose a novel two-stage framework that first identifies gender-specific pathological patterns using ResNet-50 on Mel spectrograms, then performs gender-conditioned disease classification. We address class imbalance through multi-scale resampling and time warping augmentation. Evaluated on a merged dataset from four public repositories, our two-stage architecture with time warping achieves state-of-the-art performance (97.63\% accuracy, 95.25\% MCC), with a 5\% MCC improvement over single-stage baseline. This work advances voice pathology classification while reducing gender bias through hierarchical modeling of vocal characteristics.


  • Open Access

    Towards Digital Biomarkers of Systemic Inflammation Using a Multi-modal Approach: A Feasibility Study (Preprint)

    by Jinjoo Shim, Sinziana Muraru, Vanessa Löw, Caroline Evers, Sandro Riedo, Rucsandra Dobrota, Elgar Fleisch, Oliver Distler, Filipe Barata

    BACKGROUND Accurate and accessible measurements of inflammatory biomarkers are crucial for the diagnosis and monitoring of inflammatory diseases. The gold-standard C-reactive protein (CRP) requires venipuncture, which, despite providing high-quality samples, can cause discomfort, anxiety, and pain, particularly in vulnerable populations such as elderly patients. It is also resource intensive, unsuitable for remote or at-home use, and lacks continuous monitoring capability. These limitations limit patient autonomy and self-management, potentially leading to poorer prognosis due to delays in assessment and medical treatments. As digital health technologies advance, there is increasing interest in leveraging digital biomarkers for remote and real-time monitoring of systemic inflammation (SI). Digital biomarkers derived from non-invasive biofluids could provide a scalable solution for tracking inflammatory status, offering a patient-centered alternative to traditional blood-based assessments. To date, however, there is no consensus on the most suitable modality for assessment or its digitization potential. Therefore, a comprehensive evaluation of the feasibility, reliability, and patient acceptability towards non-invasive, digital inflammatory biomarkers is needed. OBJECTIVE Our aim is to evaluate the feasibility of various non-invasive methods to assess inflammatory markers and identify the optimal modality for predicting serum CRP levels. METHODS Inflammatory biomarkers were assessed in 20 participants (10 patients with SI defined as a CRP level >5 mg/l and 10 controls) using six non-invasive samples (urine, sweat, saliva, exhaled breath, core body temperature, and stool samples) alongside serum samples. Patient preferences were retrieved via a questionnaire. Mann-Whitney U test, Spearman’s correlation, and all-subset regression were conducted to assess the relationships between serum and non-serum biomarkers and to identify optimal predictive models for serum CRP levels. RESULTS CRP levels were significantly elevated in the inflammation group compared to controls in urine (median: 4.5 vs. 0.69 μg/mmol, p=0.001) and saliva (median: 4910 vs. 473 pg/ml, p=0.001). Urine and saliva CRP levels strongly correlated with serum CRP (rsp=0.886, p<0.001; rsp=0.709, p=0.0006). The multi-modal model using urine and saliva CRP predicted serum CRP levels with 76.1% outperforming single-modality models. Patient favored urine and saliva tests over blood tests. CONCLUSIONS Urine and saliva represent promising non-invasive alternatives to traditional blood tests for assessing CRP, enabling more accessible and less invasive diagnostic and monitoring approaches.

  • Open Access

    Moving Beyond the Simulator: Interaction-Based Drunk Driving Detection in a Real Vehicle Using Driver Monitoring Cameras and Real-Time Vehicle Data

    by Robin Deuber, Patrick Langer, Mathias Kraus, Matthias Pfäffli, Matthias Bantle, Filipe Barata, Florian von Wangenheim, Elgar Fleisch, Wolfgang Weinmann, Felix Wortmann


  • Open Access

    Noninvasive, Multimodal Inflammatory Biomarker Discovery for Systemic Inflammation (NOVA Study): Protocol for a Cross-Sectional Study

    by Jinjoo Shim, Sinziana Muraru, Rucsandra Dobrota, Elgar Fleisch, Oliver Distler, Filipe Barata

    Background: Prolonged systemic inflammation is recognized as a major contributor to the development of various chronic inflammatory diseases. Daily measurements of inflammatory biomarkers can significantly improve disease monitoring of systemic inflammation, thus contributing to reducing the burden on patients and the health care system. There exists, however, no scalable, cost-efficient, and noninvasive biomarker for remote assessment of systemic inflammation. To this end, we propose a novel, multimodal, and noninvasive approach for measuring inflammatory biomarkers. Objective: This study aimed to evaluate the relationship between the levels of inflammatory biomarkers in serum (gold standard) and those measured noninvasively in urine, sweat, saliva, exhaled breath, stool, and core body temperature in patients with systemic inflammation. Methods: This study is a single-center, cross-sectional study and includes a total of 20 participants (10 patients with systemic inflammation and 10 control patients). Eligible participants provide serum, urine, sweat, saliva, exhaled breath, and stool samples for biomarker analyses. Core body temperature is measured using a sensor. The primary end point is the level of C-reactive protein (CRP). The secondary end points are interleukin (IL)–1β, IL-6, IL-8, IL-10, and tumor necrosis factor-α levels. The tertiary end points are fractional exhaled nitric oxide, calprotectin, and core body temperature. Samples will be collected in 2 batches, enabling preliminary analysis of the first batch (patients 1-5 from each group). The full analysis will include both batches. CRP and cytokine levels will be measured using enzyme-linked immunosorbent assay and electrochemiluminescence immunoassay. For statistical analysis, the Shapiro-Wilk test will be used to evaluate the normality of the distribution in each variable. We will perform the 2-tailed t test or Wilcoxon rank sum test to compare the levels of inflammatory biomarkers between patients with systemic inflammations and control patients. Pearson and Spearman correlation coefficients will assess the relationship between inflammatory biomarkers from noninvasive methods and serum biomarkers. Using all-subset regression analysis, we will determine the combination of noninvasive methods yielding the highest predictive accuracy for serum CRP levels. Participants’ preferences for sampling methods will be assessed through a questionnaire. Results: The study received ethics approval from the independent research ethics committee of Canton Zurich on October 28, 2022. A total of 20 participants participated in the study measurements. Data collection started on February 22, 2023, and was completed on September 22, 2023. Participants were on average 52.8 (SD 14.4; range 24-82) years of age, and 70% (14/20) of them were women. The analysis results reporting findings are expected to be published in 2025. Conclusions: This study aims to evaluate the feasibility of noninvasive, multimodal assessment of inflammatory biomarkers in patients with systemic inflammation. Promising results could lead to the creation of noninvasive and potentially digital biomarkers for systemic inflammation, enabling continuous monitoring and early diagnosis of inflammatory activity in a remote setting. International Registered Report Identifier (IRRID): DERR1-10.2196/62877


  • Open Access

    Comparative Efficacy of Commercial Wearables for Circadian Rhythm Home Monitoring From Activity, Heart Rate, and Core Body Temperature

    by Fan Wu, Patrick Langer, Jinjoo Shim, Elgar Fleisch, Filipe Barata

    Circadian rhythms govern biological patterns that follow a 24-hour cycle. Dysfunctions in circadian rhythms can contribute to various health problems, such as sleep disorders. Current circadian rhythm assessment methods, often invasive or subjective, limit circadian rhythm monitoring to laboratories. Hence, this study aims to investigate scalable consumer-centric wearables for circadian rhythm monitoring outside traditional laboratories. In a two-week longitudinal study conducted in real-world settings, 36 participants wore an Actigraph, a smartwatch, and a core body temperature sensor to collect activity, temperature, and heart rate data. We evaluated circadian rhythms calculated from commercial wearables by comparing them with circadian rhythm reference measures, i.e., Actigraph activities and chronotype questionnaire scores. The circadian rhythm metric acrophases, determined from commercial wearables using activity, heart rate, and temperature data, significantly correlated with the acrophase derived from Actigraph activities (r=0.96, r=0.87, r=0.79; all p$R^{2}$ =0.64; p<0.001). Our study validates commercial sensors for circadian rhythm assessment, highlighting their potential to support maintaining healthy rhythms and provide scalable and timely health monitoring in real-life scenarios.


  • Open Access

    Noninvasive, Multimodal Inflammatory Biomarker Discovery for Systemic Inflammation (NOVA Study): Protocol for a Cross-Sectional Study (Preprint)

    by Jinjoo Shim, Sinziana Muraru, Rucsandra Dobrota, Elgar Fleisch, Oliver Distler, Filipe Barata

    BACKGROUND Prolonged systemic inflammation is recognized as a major contributor to the development of various chronic inflammatory diseases. Daily measurements of inflammatory biomarkers can significantly improve disease monitoring of systemic inflammation, thus contributing to reducing the burden on patients and the health care system. There exists, however, no scalable, cost-efficient, and noninvasive biomarker for remote assessment of systemic inflammation. To this end, we propose a novel, multimodal, and noninvasive approach for measuring inflammatory biomarkers. OBJECTIVE This study aimed to evaluate the relationship between the levels of inflammatory biomarkers in serum (gold standard) and those measured noninvasively in urine, sweat, saliva, exhaled breath, stool, and core body temperature in patients with systemic inflammation. METHODS This study is a single-center, cross-sectional study and includes a total of 20 participants (10 patients with systemic inflammation and 10 control patients). Eligible participants provide serum, urine, sweat, saliva, exhaled breath, and stool samples for biomarker analyses. Core body temperature is measured using a sensor. The primary end point is the level of C-reactive protein (CRP). The secondary end points are interleukin (IL)–1β, IL-6, IL-8, IL-10, and tumor necrosis factor-α levels. The tertiary end points are fractional exhaled nitric oxide, calprotectin, and core body temperature. Samples will be collected in 2 batches, enabling preliminary analysis of the first batch (patients 1-5 from each group). The full analysis will include both batches. CRP and cytokine levels will be measured using enzyme-linked immunosorbent assay and electrochemiluminescence immunoassay. For statistical analysis, the Shapiro-Wilk test will be used to evaluate the normality of the distribution in each variable. We will perform the 2-tailed t test or Wilcoxon rank sum test to compare the levels of inflammatory biomarkers between patients with systemic inflammations and control patients. Pearson and Spearman correlation coefficients will assess the relationship between inflammatory biomarkers from noninvasive methods and serum biomarkers. Using all-subset regression analysis, we will determine the combination of noninvasive methods yielding the highest predictive accuracy for serum CRP levels. Participants’ preferences for sampling methods will be assessed through a questionnaire. RESULTS The study received ethics approval from the independent research ethics committee of Canton Zurich on October 28, 2022. A total of 20 participants participated in the study measurements. Data collection started on February 22, 2023, and was completed on September 22, 2023. Participants were on average 52.8 (SD 14.4; range 24-82) years of age, and 70% (14/20) of them were women. The analysis results reporting findings are expected to be published in 2025. CONCLUSIONS This study aims to evaluate the feasibility of noninvasive, multimodal assessment of inflammatory biomarkers in patients with systemic inflammation. Promising results could lead to the creation of noninvasive and potentially digital biomarkers for systemic inflammation, enabling continuous monitoring and early diagnosis of inflammatory activity in a remote setting. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/62877

  • Open Access

    Circadian rhythm analysis using wearable-based accelerometry as a digital biomarker of aging and healthspan

    by Jinjoo Shim, Elgar Fleisch, Filipe Barata

    Recognizing the pivotal role of circadian rhythm in the human aging process and its scalability through wearables, we introduce CosinorAge, a digital biomarker of aging developed from wearable-derived circadian rhythmicity from 80,000 midlife and older adults in the UK and US. A one-year increase in CosinorAge corresponded to 8–12% higher all-cause and cause-specific mortality risks and 3–14% increased prospective incidences of age-related diseases. CosinorAge also captured a non-linear decline in resilience and physical functioning, evidenced by an 8–33% reduction in self-rated health and a 3–23% decline in health-related quality of life score, adjusting for covariates and multiple testing. The associations were robust in sensitivity analyses and external validation using an independent cohort from a disparate geographical region using a different wearable device. Moreover, we illustrated a heterogeneous impact of circadian parameters associated with biological aging, with young (65 years). We demonstrated a significant enhancement in the predictive performance when integrating circadian rhythmicity in the estimation of biological aging over physical activity. Our findings underscore CosinorAge’s potential as a scalable, economic, and digital solution for promoting healthy longevity, elucidating the critical and multifaceted circadian rhythmicity in aging processes. Consequently, our research contributes to advancing preventive measures in digital medicine.