PURPOSE: Identify Oropharyngeal cancer (OPC) patients at high-risk of developing long-term severe radiation-associated symptoms using dose volume histograms for organs-at-risk, via unsupervised clustering.
MATERIAL AND METHODS: All patients were treated using radiation therapy for OPC. Dose-volume histograms of organs-at-risk were extracted from patients’ treatment plans. Symptom ratings were collected via the MD Anderson Symptom Inventory (MDASI) given weekly during, and 6 months post-treatment. Drymouth, trouble swallowing, mucus, and vocal dysfunction were selected for analysis in this study. Patient stratifications were obtained by applying Bayesian Mixture Models with three components to patient’s dose histograms for relevant organs. The clusters with the highest total mean doses were translated into dose thresholds using rule mining. Patient stratifications were compared against Tumor staging information using multivariate likelihood ratio tests. Model performance for prediction of moderate/severe symptoms at 6 months was compared against normal tissue complication probability (NTCP) models using cross-validation.
RESULTS: A total of 349 patients were included for long-term symptom prediction. High-risk clusters were significantly correlated with outcomes for severe late drymouth (p <.0001, OR = 2.94), swallow (p = .002, OR = 5.13), mucus (p = .001, OR = 3.18), and voice (p = .009, OR = 8.99). Simplified clusters were also correlated with late severe symptoms for drymouth (p <.001, OR = 2.77), swallow (p = .01, OR = 3.63), mucus (p = .01, OR = 2.37), and voice (p <.001, OR = 19.75). Proposed cluster stratifications show better performance than NTCP models for severe drymouth (AUC.598 vs.559, MCC.143 vs.062), swallow (AUC.631 vs.561, MCC.20 vs -.030), mucus (AUC.596 vs.492, MCC.164 vs -.041), and voice (AUC.681 vs.555, MCC.181 vs -.019). Simplified dose thresholds also show better performance than baseline models for predicting late severe ratings for all symptoms.
CONCLUSION: Our results show that leveraging the 3-D dose histograms from radiation therapy plan improves stratification of patients according to their risk of experiencing long-term severe radiation associated symptoms, beyond existing NTPC models. Our rule-based method can approximate our stratifications with minimal loss of accuracy and can proactively identify risk factors for radiation-associated toxicity.
more »
« less
Improving Prediction of Late Symptoms using LSTM and Patient-reported Outcomes for Head and Neck Cancer Patients
Patient-Reported Outcomes (PRO) are collected directly from the patients using symptom questionnaires. In the case of head and neck cancer patients, PRO surveys are recorded every week during treatment with each patient’s visit to the clinic and at different follow-up times after the treatment has concluded. PRO surveys can be very informative regarding the patient’s status and the effect of treatment on the patient’s quality of life (QoL). Processing PRO data is challenging for several reasons. First, missing data is frequent as patients might skip a question or a questionnaire altogether. Second, PROs are patient-dependent, a rating of 5 for one patient might be a rating of 10 for another patient. Finally, most patients experience severe symptoms during treatment which usually subside over time. However, for some patients, late toxicities persist negatively affecting the patient’s QoL. These long-term severe symptoms are hard to predict and are the focus of this study. In this work, we model PRO data collected from head and neck cancer patients treated at the MD Anderson Cancer Center using the MD Anderson Symptom Inventory (MDASI) questionnaire as time series. We impute missing values with a combination of K nearest neighbor (KNN) and Long Short-Term Memory (LSTM) neural networks, and finally, apply LSTM to predict late symptom severity 12 months after treatment. We compare performance against clinical and ARIMA models. We show that the LSTM model combined with KNN imputation is effective in predicting late-stage symptom ratings for occurrence and severity under the AUC and F1 score metrics.
more »
« less
- Award ID(s):
- 2320261
- PAR ID:
- 10536560
- Publisher / Repository:
- IEEE Xplore
- Date Published:
- ISBN:
- 979-8-3503-0263-9
- Page Range / eLocation ID:
- 292 to 300
- Subject(s) / Keyword(s):
- Long Short-Term Memory (LSTM) Patient Reported Outcomes (PRO) Late Toxicity, Symptom Severity Prediction KNN Baseline Imputation
- Format(s):
- Medium: X
- Location:
- Houston, TX, USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Background Two patient‐reported outcomes (PROs) of swallowing and their correlation to quality of life (QOL) were compared in long‐term survivors of oropharyngeal cancer (OPC).
Methods Scores on the single dysphagia item from the 28‐item, multisymptom MD Anderson Symptom Inventory‐Head and Neck (MDA
S I‐HN‐S) were compared with scores on the dysphagia‐specific composite MD Anderson Dysphagia Inventory (MDAD I) and the EuroQol visual analog scale (EQ‐VAS) in 714 patients who had received definitive radiotherapy ≥12 months before the survey. An MDAS I‐HN‐S score ≥6 and an MDAD I composite score <60 were considered representative of moderate/severe swallowing dysfunction.Results Moderate/severe dysphagia was reported by 17% and 16% of respondents on the MDA
S I‐HN‐S and the composite MDAD I, respectively. Both swallow PROs were predictive of QOL, and the MDAS I‐HN‐S model was slightly more parsimonious for the discrimination of EQ‐VAS scores compared with MDAD I scores (Bayesian information criteria, 6062 vs 6076, respectively). An MDAS I‐HN‐S cutoff score of ≥6 correlated best with a declining EQ‐VAS score (P < .0001) and was associated with increased radiotherapy dose to several normal swallowing structures.Conclusions In this cohort, the single‐item MDA
S I‐HN‐S performed favorably for the discrimination of QOL compared with the multi‐item MDAD I. A time‐efficient model for PRO measurement of swallowing is proposed in which the MDAD I may be reserved for patients who score ≥6 on the MDAS I‐HN‐S. -
Personalized head and neck cancer therapeutics have greatly improved survival rates for patients, but are often leading to understudied long-lasting symptoms which affect quality of life. Sequential rule mining (SRM) is a promising unsupervised machine learning method for predicting longitudinal patterns in temporal data which, however, can output many repetitive patterns that are difficult to interpret without the assistance of visual analytics. We present a data-driven, human-machine analysis visual system developed in collaboration with SRM model builders in cancer symptom research, which facilitates mechanistic knowledge discovery in large scale, multivariate cohort symptom data. Our system supports multivariate predictive modeling of post-treatment symptoms based on during-treatment symptoms. It supports this goal through an SRM, clustering, and aggregation back end, and a custom front end to help develop and tune the predictive models. The system also explains the resulting predictions in the context of therapeutic decisions typical in personalized care delivery. We evaluate the resulting models and system with an interdisciplinary group of modelers and head and neck oncology researchers. The results demonstrate that our system effectively supports clinical and symptom research.more » « less
-
more » « less
Abstract Objective We examined whether eating disorder (ED) outcome trajectories during residential treatment differed for patients screening positive for comorbid borderline personality disorder (BPD) and/or substance use disorders (SUDs) than those who do not.
Method We examined data from patients in a residential ED treatment program. Patients completed validated self‐report surveys to screen for SUDs and BPD on admission, and the ED Examination‐Questionnaire (EDE‐Q) on admission and every 2 weeks until discharge (
N = 479 females).Results Fifty‐four percent screened positive for at least one co‐occurring condition. At admission, patients screening positive for SUD and/or BPD had significantly greater eating pathology than patients screening negative for both (
t [477] = 8.23,p < .001). Patients screening positive for SUD (independent of BPD screening status) had a significantly faster rate of symptom improvement during the initial 4 weeks than patients screening positive for BPD only and those with no comorbidities.Discussion Screening positive for SUD and/or BPD was common in residential ED treatment, and associated with more severe ED symptoms. Screening positive for SUD was associated with faster ED symptom improvement than screening positive for BPD. These findings suggest that intensive ED treatment, even in the absence of intensive SUD treatment, may enhance patient outcomes for those with SUDs.
-
With few exceptions, most research in automated assessment of depression has considered only the patient’s behavior to the exclusion of the therapist’s behavior. We investigated the interpersonal coordination (synchrony) of head movement during patient-therapist clinical interviews. Participants with major depressive disorder were recorded in clinical interviews (Hamilton Rating Scale for Depression, HRSD) at 7-week intervals over a period of 21 weeks. For each session, patient and therapist 3D head movement was tracked from 2D videos. Head angles in the horizontal (pitch) and vertical (yaw) axes were used to measure head movement. Interpersonal coordination of head movement between patients and therapists was measured using windowed cross-correlation. Patterns of coordination in head movement were investigated using the peak picking algorithm. Changes in head movement coordination over the course of treatment were measured using a hierarchical linear model (HLM). The results indicated a strong effect for patient-therapist head movement synchrony. Within-dyad variability in head movement coordination was higher than between-dyad variability, meaning that differences over time in a dyad were higher as compared to the differences between dyads. Head movement synchrony did not change over the course of treatment. To the best of our knowledge, this study is the first attempt to analyze the mutual influence of patient-therapist head movement in relation to depression severity.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICHI57859.2023.00047
