An official website of the United States government
When training a machine learning algorithm for a supervised-learning task in some clinical applications, uncertainty in the correct labels of some patients may adversely affect the performance of the algorithm. For example, even clinical experts may have less confidence when assigning a medical diagnosis to some patients because of ambiguity in the patient's case or imperfect reliability of the diagnostic criteria. As a result, some cases used in algorithm training may be mis-labeled, adversely affecting the algorithm's performance. However, experts may also be able to quantify their diagnostic uncertainty in these cases. We present a robust method implemented with Support Vector Machines to account for such clinical diagnostic uncertainty when training an algorithm to detect patients who develop the acute respiratory distress syndrome (ARDS). ARDS is a syndrome of the critically ill that is diagnosed using clinical criteria known to be imperfect. We represent uncertainty in the diagnosis of ARDS as a graded weight of confidence associated with each training label. We also performed a novel time-series sampling method to address the problem of inter-correlation among the longitudinal clinical data from each patient used in model training to limit overfitting. Preliminary results show that we can achieve meaningful improvement in the performance of algorithm to detect patients with ARDS on a hold-out sample, when we compare our method that accounts for the uncertainty of training labels with a conventional SVM algorithm.
more »
« less
This content will become publicly available on December 1, 2025
Correlation enhanced distribution adaptation for prediction of fall risk
Abstract With technological advancements in diagnostic imaging, smart sensing, and wearables, a multitude of heterogeneous sources or modalities are available to proactively monitor the health of the elderly. Due to the increasing risks of falls among older adults, an early diagnosis tool is crucial to prevent future falls. However, during the early stage of diagnosis, there is often limited or no labeled data (expert-confirmed diagnostic information) available in the target domain (new cohort) to determine the proper treatment for older adults. Instead, there are multiple related but non-identical domain data with labels from the existing cohort or different institutions. Integrating different data sources with labeled and unlabeled samples to predict a patient's condition poses a significant challenge. Traditional machine learning models assume that data for new patients follow a similar distribution. If the data does not satisfy this assumption, the trained models do not achieve the expected accuracy, leading to potential misdiagnosing risks. To address this issue, we utilize domain adaptation (DA) techniques, which employ labeled data from one or more related source domains. These DA techniques promise to tackle discrepancies in multiple data sources and achieve a robust diagnosis for new patients. In our research, we have developed an unsupervised DA model to align two domains by creating a domain-invariant feature representation. Subsequently, we have built a robust fall-risk prediction model based on these new feature representations. The results from simulation studies and real-world applications demonstrate that our proposed approach outperforms existing models.
more »
« less
- Award ID(s):
- 2137272
- PAR ID:
- 10515958
- Publisher / Repository:
- Scientific Reports
- Date Published:
- Journal Name:
- Scientific Reports
- Volume:
- 14
- Issue:
- 1
- ISSN:
- 2045-2322
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Tracking activities holds great potential to improve the well-being of older adults, yet the accuracy of activity trackers for this demographic remains in question. Evaluating this accuracy requires ground-truth data directly from older adults, which has largely been gathered in controlled laboratory settings or labeled by researchers. Moreover, considering the diversity in older adults' activity engagement and tracking preferences, personalized activity tracking appears necessary. We demonstrate that older adults can benefit from personalized activity trackers by showing that cadence thresholds for stepping intensities vary within this group. However, collecting ground-truth data from older adults in real-world settings poses unique challenges. This paper examines two sources of ground-truth labels for the smartwatch Inertial Measurement Unit (IMU) data collected with older adults. Using verbal self-reports and a thigh-worn activity tracker, we assess their viability as ground-truth sources in natural settings. Additionally, we evaluate the costs and benefits of triangulating these sources as a ground-truth proxy. Our findings reveal two main costs: data shrinkage and notable effort from both contributors and data stewards. Simultaneously, we observe improved data quality and a greater ability to identify error sources when evaluating a trained model.more » « less
-
Abstract Lymphedema is localized swelling due to lymphatic system dysfunction, often affecting arms and legs due to fluid accumulation. It occurs in 20% to 94% of patients within 2–5 years after breast cancer treatment, with around 20% of women developing breast cancer-related lymphedema. This condition involves the accumulation of protein-rich fluid in interstitial spaces, leading to symptoms like swelling, pain, and reduced mobility that significantly impact quality of life. The early diagnosis of lymphedema helps mitigate the risk of deterioration and prevent its progression to more severe stages. Healthcare providers can reduce risks through exercise prescriptions and self-manual lymphatic drainage techniques. Lymphedema diagnosis currently relies on physical examinations and limb volume measurements, but challenges arise from a lack of standardized criteria and difficulties in detecting early stages. Recent advancements in computational imaging and decision support systems have improved diagnostic accuracy through enhanced image reconstruction and real-time data analysis. The aim of this comprehensive review is to provide an in-depth overview of the research landscape in computational diagnostic techniques for lymphedema. The computational techniques primarily include imaging-based, electrical, and machine learning (ML) approaches, which utilize advanced algorithms and data analysis. These modalities were compared based on various parameters to choose the most suitable techniques for their applications. Lymphedema detection faces challenges like subtle symptoms and inconsistent diagnostics. The research identifies bioimpedance spectroscopy (BIS), Kinect sensor and ML integration as the promising modalities for early lymphedema detection. BIS can effectively identify lymphedema as early as four months post-surgery with sensitivity of 44.1% and specificity of 95.4% in diagnosing lymphedema whereas ML and artificial neural network achieved an impressive average cross-validation accuracy of 93.75%, with sensitivity at 95.65% and specificity at 91.03%. ML and imaging can be integrated into clinical practice to enhance diagnostic accuracy and accessibility.more » « less
-
Epidemiological studies link increased fall risk to obesity in older adults, but the mechanism through which obesity increases falls and fall risks is unknown. This study investigates if obesity (Body Mass Index: BMI>30 kg/m2) influenced gait and standing postural characteristics of community dwelling older adults leading to increased risk of falls. One hundred healthy older adults (age 74.0±7.6 years, range of 56-90 years) living independently in a community participated in this study. Participants' history of falls over the previous two years was recorded, with emphasis on frequency and characteristics of falls. Participants with at least two falls in the prior year were classified as fallers. Each individual was assessed for postural stability during quiet stance and gait stability during 10 meters walking. Fall risk parameters of postural sway (COP area, velocity, path-length) were measured utilizing a standard forceplate coupled with an accelerometer affixed at the sternum. Additionally, parameters of gait stability (walking velocity, double support time, and double support time variability) were assessed utilizing an accelerometer affixed at the participant's sternum. Gait and postural stability analyses indicate that obese older adults who fell have significantly altered gait pattern (longer double support time and greater variability) exhibiting a loss of automaticity in walking and, postural instability as compared to their counterparts (i.e., higher sway area and path length, and higher sway velocity) further increasing the risk of a fall given a perturbation. Body weight/BMI is a risk factor for falls in older adults as measured by gait and postural stability parameters.more » « less
-
Objectives: To examine the extent to which older adults’ perceived balance, a balance performance test, and fear of falling (FOF) were associated with falls in the last month. Methods: The Health Belief Model served as the theoretical framework. A retrospective, cross-sectional, secondary analysis using data from the National Health and Aging Trends Study was conducted ( N = 7499). Results: Multiple logistic regression analysis revealed that the odds of reporting a fall in the past month were 3.3 times ( p < .001) greater for participants who self-reported having a balance problem compared to those who did not. The Short Physical Performance Battery and FOF were not uniquely associated with falls. Discussion: Our findings support limited evidence suggesting that older adults’ perceived balance is a better predictor of falls than balance performance. Assessing older adults’ perceived balance may be a new way to assess older adults’ fall risk to prevent future falls.more » « less
