arXiv subjects

Thomas Neumuth

Publications and source records attributed to Thomas Neumuth.

8 recordsLinked to original sources

arXiv2026

Using a Stifneck Select Collar$^{\mathrm{TM}}$ for hands-free semiautomatic blood flow measurements: a user study

Objective: The percentage of long-term survival in out of hospital cardiac arrest cases is remarkably low. One approach would be to increase the effectiveness of cardiopulmonary resuscitation (CPR), which is currently not measurable in a quantifiable way. The most significant challenge in providing a mobile solution for CPR evaluation is a mobile, hazard free sensor attachment with high usability. Methods: We present a sensor attachment solution usable for semiautomatic ultrasonic (US) Doppler measurements. Components are attached to a Stifneck Select Collar$^{\mathrm{TM}}$ (Laerdal). An inflatable cushion (TR-Band$^{\mathrm{TM}}$, Terumo) allows adjustable contact pressure. A clinical study was conducted in which the system was evaluated based on comfort, pain, sensor support, the viability of Doppler signals, and the absence of skin irritations. Results: The system was utilized in a prospective study involving 102 healthy probands. On a scale between 1 (Low) and 10 (Intense), ratings were 1.19 (SD 0.46), 6.52 (SD 1.78), and 9.95 (SD 0.32) for pain, comfort, and support, respectively. The average duration of application was 31.19 minutes (SD 16.75 minutes). Audible Doppler signals were achieved in 92.2 % of the probands, and Doppler curve evaluation was usable in 73.5 %. No skin irritations were observed. Conclusion: A hands free sensor attachment for a US probe was developed that caused no significant complaints by healthy study volunteers. Medical users assessed its attachment as robust. Significance: With its adjustable positioning and easy attachment, the Stifneck modification can form a basis for a mobile US Doppler device, capable of evaluating carotid artery flow during CPR.

physics.med-ph↗

arXiv2025

Basis for a hands free blood flow measurement with automated vessel focus

Cardiopulmonary resuscitation (CPR) is an essential tool to ensure oxygen supply during cardiac arrest, yet not quantifiable to this day. Low-quality chest compressions or wrong pressure placement go unnoticed. This paper presents a solution for the quantification of blood flow to guide first responders in their efforts. An approach for automated vessel identification with three different steps was developed, featuring a new sensor probe for ultrasonic measurements with non-symmetrically angled piezo ceramics. The probe was used with prototype ultrasound hardware for Pulsed Wave Doppler (PW Doppler) in a phantom. Initial measurements evaluated sensor vessel alignment at different sensor positions by examining Doppler results with a large sample volume during periodic flow. Afterward, an iterative mode was used for depth-dependent frequency measurements with score calculation of flow periodicity and power. The configuration with the best score was used for a prolonged monitoring mode. Initial mode and iterative mode aligned with ultrasound imaging regarding the best position and vessel depth. Simultaneous flow-sensor data and flow values of monitoring mode calculated via Doppler substitution showed a minimum correlation coefficient of 0.98, a minimum R2 of 0.96, and an average root mean square error of 3.84 ml/s. With the proposed hardware and software solutions, a basis for future developments was made, which could lead to a fully automated vessel identification and blood flow calculation during CPR. When used in emergencies, a miniaturized device could provide vital information about CPR efficiency that has yet to be included in the therapy of people during cardiac arrest.

physics.med-ph↗

arXiv2025

Unsupervised risk factor identification across cancer types and data modalities via explainable artificial intelligence

Risk stratification is a key tool in clinical decision-making, yet current approaches often fail to translate sophisticated survival analysis into actionable clinical criteria. We present a novel method for unsupervised machine learning that directly optimizes for survival heterogeneity across patient clusters through a differentiable adaptation of the multivariate logrank statistic. Unlike most existing methods that rely on proxy metrics, our approach represents novel methodology for training any neural network architecture on any data modality to identify prognostically distinct patient groups. We thoroughly evaluate the method in simulation experiments and demonstrate its utility in practice by applying it to two distinct cancer types: analyzing laboratory parameters from multiple myeloma patients and computed tomography images from non-small cell lung cancer patients, identifying prognostically distinct patient subgroups with significantly different survival outcomes in both cases. Post-hoc explainability analyses uncover clinically meaningful features determining the group assignments which align well with established risk factors and thus lend strong weight to the methods utility. This pan-cancer, model-agnostic approach represents a valuable advancement in clinical risk stratification, enabling the discovery of novel prognostic signatures across diverse data types while providing interpretable results that promise to complement treatment personalization and clinical decision-making in oncology and beyond.

cs.LG↗

arXiv2024

Predicting Progression Events in Multiple Myeloma from Routine Blood Work

The ability to accurately predict disease progression is paramount for optimizing multiple myeloma patient care. This study introduces a hybrid neural network architecture, combining Long Short-Term Memory networks with a Conditional Restricted Boltzmann Machine, to predict future blood work of affected patients from a series of historical laboratory results. We demonstrate that our model can replicate the statistical moments of the time series ($0.95~\pm~0.01~\geq~R^2~\geq~0.83~\pm~0.03$) and forecast future blood work features with high correlation to actual patient data ($0.92\pm0.02~\geq~r~\geq~0.52~\pm~0.09$). Subsequently, a second Long Short-Term Memory network is employed to detect and annotate disease progression events within the forecasted blood work time series. We show that these annotations enable the prediction of progression events with significant reliability (AUROC$~=~0.88~\pm~0.01$), up to 12 months in advance (AUROC($t+12~$mos)$~=0.65~\pm~0.01$). Our system is designed in a modular fashion, featuring separate entities for forecasting and progression event annotation. This structure not only enhances interpretability but also facilitates the integration of additional modules to perform subsequent operations on the generated outputs. Our approach utilizes a minimal set of routine blood work measurements, which avoids the need for expensive or resource-intensive tests and ensures accessibility of the system in clinical routine. This capability allows for individualized risk assessment and making informed treatment decisions tailored to a patient's unique disease kinetics. The represented approach contributes to the development of a scalable and cost-effective virtual human twin system for optimized healthcare resource utilization and improved patient outcomes in multiple myeloma care.

stat.AP↗

arXiv2024

Inadequacy of common stochastic neural networks for reliable clinical decision support

Widespread adoption of AI for medical decision making is still hindered due to ethical and safety-related concerns. For AI-based decision support systems in healthcare settings it is paramount to be reliable and trustworthy. Common deep learning approaches, however, have the tendency towards overconfidence under data shift. Such inappropriate extrapolation beyond evidence-based scenarios may have dire consequences. This highlights the importance of reliable estimation of local uncertainty and its communication to the end user. While stochastic neural networks have been heralded as a potential solution to these issues, this study investigates their actual reliability in clinical applications. We centered our analysis on the exemplary use case of mortality prediction for ICU hospitalizations using EHR from MIMIC3 study. For predictions on the EHR time series, Encoder-Only Transformer models were employed. Stochasticity of model functions was achieved by incorporating common methods such as Bayesian neural network layers and model ensembles. Our models achieve state of the art performance in terms of discrimination performance (AUC ROC: 0.868+-0.011, AUC PR: 0.554+-0.034) and calibration on the mortality prediction benchmark. However, epistemic uncertainty is critically underestimated by the selected stochastic deep learning methods. A heuristic proof for the responsible collapse of the posterior distribution is provided. Our findings reveal the inadequacy of commonly used stochastic deep learning approaches to reliably recognize OoD samples. In both methods, unsubstantiated model confidence is not prevented due to strongly biased functional posteriors, rendering them inappropriate for reliable clinical decision support. This highlights the need for approaches with more strictly enforced or inherent distance-awareness to known data points, e.g., using kernel-based techniques.

cs.LG↗

arXiv2020

Surgical Data Science -- from Concepts toward Clinical Translation

Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical Data Science (SDS) is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of SDS, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. We further complement this technical perspective with (4) a review of currently available SDS products and the translational progress from academia and (5) a roadmap for faster clinical translation and exploitation of the full potential of SDS, based on an international multi-round Delphi process.

cs.CY↗

arXiv2018

Surgical Data Science: A Consensus Perspective

Surgical data science is a scientific discipline with the objective of improving the quality of interventional healthcare and its value through capturing, organization, analysis, and modeling of data. The goal of the 1st workshop on Surgical Data Science was to bring together researchers working on diverse topics in surgical data science in order to discuss existing challenges, potential standards and new research directions in the field. Inspired by current open space and think tank formats, it was organized in June 2016 in Heidelberg. While the first day of the workshop, which was dominated by interactive sessions, was open to the public, the second day was reserved for a board meeting on which the information gathered on the public day was processed by (1) discussing remaining open issues, (2) deriving a joint definition for surgical data science and (3) proposing potential strategies for advancing the field. This document summarizes the key findings.

cs.CY↗

arXiv2017

Surgical Data Science: Enabling Next-Generation Surgery

This paper introduces Surgical Data Science as an emerging scientific discipline. Key perspectives are based on discussions during an intensive two-day international interactive workshop that brought together leading researchers working in the related field of computer and robot assisted interventions. Our consensus opinion is that increasing access to large amounts of complex data, at scale, throughout the patient care process, complemented by advances in data science and machine learning techniques, has set the stage for a new generation of analytics that will support decision-making and quality improvement in interventional medicine. In this article, we provide a consensus definition for Surgical Data Science, identify associated challenges and opportunities and provide a roadmap for advancing the field.

cs.CY↗