Digital Care for Chronic Musculoskeletal Pain: 10,000 Participant Longitudinal Cohort Study.

BACKGROUND: Chronic musculoskeletal pain has a vast global prevalence and economic burden. Conservative therapies are universally recommended but require patient engagement and self-management to be effective. OBJECTIVE: This study aimed to evaluate the efficacy of a 12-week digital care program (DCP) in a large population of patients with chronic knee and back pain. METHODS: A longitudinal observational study was conducted using a remote DCP available through a mobile app. Subjects participated in a 12-week multimodal DCP incorporating education, sensor-guided exercise therapy (ET), and behavioral health support with 1-on-1 remote health coaching. The primary outcome was pain measured by the visual analog scale (VAS). Secondary measures included engagement levels, program completion, program satisfaction, condition-specific pain measures, depression, anxiety, and work productivity. RESULTS: A total of 10,264 adults with either knee (n=3796) or low back (n=6468) pain for at least three months were included in the study. Participants experienced a 68.45% average improvement in VAS pain between baseline intake and 12 weeks. In all, 73.04% (7497/10,264) participants completed the DCP into the final month. In total, 78.60% (5893/7497) of program completers (7144/10,264, 69.60% of all participants) achieved minimally important change in pain. Furthermore, the number of ET sessions and coaching interactions were both positively associated with improvement in pain, suggesting that the amount of engagement influenced outcomes. Secondary outcomes included a 57.9% and 58.3% decrease in depression and anxiety scores, respectively, and 61.5% improvement in work productivity. Finally, 3 distinct clusters of pain response trajectories were identified, which could be predicted with a mean 76% accuracy using baseline measures. CONCLUSIONS: These results support the efficacy and scalability of a DCP for chronic low back and knee pain in a large, diverse, real-world population. Participants demonstrated high completion and engagement rates and a significant positive relationship between engagement and pain reduction was identified, a finding that has not been previously demonstrated in a DCP. Furthermore, the large sample size allowed for the identification of distinct pain response subgroups, which may prove beneficial in predicting recovery and tailoring future interventions. This is the first longitudinal digital health study to analyze pain outcomes in a sample of this magnitude, and it supports the prospect for DCPs to serve the overwhelming number of musculoskeletal pain sufferers worldwide.

Impact of Predicting Health Care Utilization Via Web Search Behavior: A Data-Driven Analysis.

BACKGROUND: By recent estimates, the steady rise in health care costs has deprived more than 45 million Americans of health care services and has encouraged health care providers to better understand the key drivers of health care utilization from a population health management perspective. Prior studies suggest the feasibility of mining population-level patterns of health care resource utilization from observational analysis of Internet search logs; however, the utility of the endeavor to the various stakeholders in a health ecosystem remains unclear. OBJECTIVE: The aim was to carry out a closed-loop evaluation of the utility of health care use predictions using the conversion rates of advertisements that were displayed to the predicted future utilizers as a surrogate. The statistical models to predict the probability of user's future visit to a medical facility were built using effective predictors of health care resource utilization, extracted from a deidentified dataset of geotagged mobile Internet search logs representing searches made by users of the Baidu search engine between March 2015 and May 2015. METHODS: We inferred presence within the geofence of a medical facility from location and duration information from users' search logs and putatively assigned medical facility visit labels to qualifying search logs. We constructed a matrix of general, semantic, and location-based features from search logs of users that had 42 or more search days preceding a medical facility visit as well as from search logs of users that had no medical visits and trained statistical learners for predicting future medical visits. We then carried out a closed-loop evaluation of the utility of health care use predictions using the show conversion rates of advertisements displayed to the predicted future utilizers. In the context of behaviorally targeted advertising, wherein health care providers are interested in minimizing their cost per conversion, the association between show conversion rate and predicted utilization score, served as a surrogate measure of the model's utility. RESULTS: We obtained the highest area under the curve (0.796) in medical visit prediction with our random forests model and daywise features. Ablating feature categories one at a time showed that the model performance worsened the most when location features were dropped. An online evaluation in which advertisements were served to users who had a high predicted probability of a future medical visit showed a 3.96% increase in the show conversion rate. CONCLUSIONS: Results from our experiments done in a research setting suggest that it is possible to accurately predict future patient visits from geotagged mobile search logs. Results from the offline and online experiments on the utility of health utilization predictions suggest that such prediction can have utility for health care providers.

Simultaneous monitoring of disease and microbe dynamics through plasma DNA sequencing in pediatric patients with acute lymphoblastic leukemia.

Treatment of acute lymphoblastic leukemia (ALL) necessitates continuous risk assessment of leukemic disease burden and infections that arise in the setting of immunosuppression. This study was performed to assess the feasibility of a hybrid capture next-generation sequencing panel to longitudinally measure molecular leukemic disease clearance and microbial species abundance in 20 pediatric patients with ALL throughout induction chemotherapy. This proof of concept helps establish a technical and conceptual framework that we anticipate will be expanded and applied to additional patients with leukemia, as well as extended to additional cancer types. Molecular monitoring can help accelerate the attainment of insights into the temporal biology of host-microbe-leukemia interactions, including how those changes correlate with and alter anticancer therapy efficacy. We also anticipate that fewer invasive bone marrow examinations will be required, as these methods improve with standardization and are validated for clinical use.

Influence of patient-specific factors when comparing multifidus fat infiltration between chronic low back pain patients and asymptomatic controls.

Introduction: Many studies have attempted to link multifidus (MF) fat infiltration with muscle quality and chronic low back pain (cLBP), but there is no consensus on these relationships. Methods: In this cross-sectional cohort study, 39 cLBP patients and 18 asymptomatic controls were included. The MF muscle was manually segmented at each lumbar disc level and fat fraction (FF) measurements were taken from the corresponding advanced imaging water-fat images. We assessed the distribution patterns of MF fat from L1L2 to L5S1 and compared these patterns between groups. The sample was stratified by age, sex, body mass index (BMI), subject-reported pain intensity (VAS), and subject-reported low back pain disability (oswestry disability index, ODI). Results: Older patients had significantly different MF FF distribution patterns compared to older controls (p < 0.0001). Male patients had 34.8% higher mean lumbar spine MF FF compared to male controls (p = 0.0006), significantly different MF FF distribution patterns (p = 0.028), 53.7% higher mean MF FF measurements at L2L3 (p = 0.037), and 50.6% higher mean MF FF measurements at L3L4 (p = 0.041). Low BMI patients had 29.7% higher mean lumbar spine MF FF compared to low BMI controls (p = 0.0077). High BMI patients only had 4% higher mean lumbar spine MF FF compared to high BMI controls (p = 0.7933). However, high BMI patients had significantly different MF FF distribution patterns compared to high BMI controls (p = 0.0324). Low VAS patients did not significantly differ from the control cohort for any of our outcomes of interest; however, high VAS patients had 24.3% higher mean lumbar spine MF FF values (p = 0.0011), significantly different MF FF distribution patterns (p < 0.0001), 34.7% higher mean MF FF at L2L3 (p = 0.040), and 34.6% higher mean MF FF at L3L4 (p = 0.040) compared to the control cohort. Similar trends were observed for ODI. Conclusions: This study suggests that when the presence of paraspinal muscle fat infiltration is not characteristic of an individual's age, sex, and BMI, it may be associated with lower back pain.

Inferring Physical Function From Wearable Activity Monitors: Analysis of Free-Living Activity Data From Patients With Knee Osteoarthritis.

BACKGROUND: Clinical assessments for physical function do not objectively quantify routine daily activities. Wearable activity monitors (WAMs) enable objective measurement of daily activities, but it remains unclear how these map to clinically measured physical function measures. OBJECTIVE: This study aims to derive a representation of physical function from daily measurements of free-living activity obtained through a WAM. In addition, we evaluate our derived measure against objectively measured function using an ordinal classification setup. METHODS: We defined function profiles representing average time spent in a set of pattern classes over consecutive days. We constructed a function profile using minute-level activity data from a WAM available from the Osteoarthritis Initiative. Using the function profile as input, we trained statistical models that classified subjects into quartiles of objective measurements of physical function as measured through the 400-m walk test, 20-m walk test, and 5 times sit-stand test. Furthermore, we evaluated model performance on held-out data. RESULTS: The function profile derived from minute-level activity data can accurately predict physical performance as measured through clinical assessments. Using held-out data, the Goodman-Kruskal Gamma statistic obtained in classifying performance values in the first quartile, interquartile range, and the fourth quartile was 0.62, 0.53, and 0.51 for the 400-m walk, 20-m walk, and 5 times sit-stand tests, respectively. CONCLUSIONS: Function profiles accurately represent physical function, as demonstrated by the relationship between the profiles and clinically measured physical performance. The estimation of physical performance through function profiles derived from free-living activity data may enable remote functional monitoring of patients.

Quantifying the relative change in physical activity after Total Knee Arthroplasty using accelerometer based measurements.

Osteoarthritis is amongst the top five most disabling conditions affecting Americans over 65 years of age and imposes an annual economic burden estimated at $ 89.1 billion. Nearly half of the cost of care of Osteoarthritis is attributable to hospitalizations for total knee arthroplasties (TKA) and total hip arthroplasties (THA). The current clinical practice relies predominantly on subjective assessment of physical function and pain via patient reported outcome measures (PROM) that have proven inadequate for providing a validated, reliable and responsive measure of TKA outcomes. Wearable activity monitors, which produce a trace of regularly monitored physical activity derived from accelerometer measurements, provide a novel opportunity to objectively assess physical functional status in Osteoarthritis patients. Using data from the Osteoarthritis Initiative (OAI), we demonstrate the feasibility of quantifying the relative change in physical activity patterns in Osteoarthritis subjects using accelerometer based measurements of daily physical activity.

LEARNING ATTRIBUTES OF DISEASE PROGRESSION FROM TRAJECTORIES OF SPARSE LAB VALUES.

There is heterogeneity in the manifestation of diseases, therefore it is essential to understand the patterns of progression of a disease in a given population for disease management as well as for clinical research. Disease status is often summarized by repeated recordings of one or more physiological measures. As a result, historical values of these physiological measures for a population sample can be used to characterize disease progression patterns. We use a method for clustering sparse functional data for identifying sub-groups within a cohort of patients with chronic kidney disease (CKD), based on the trajectories of their Creatinine measurements. We demonstrate through a proof-of-principle study how the two sub-groups that display distinct patterns of disease progression may be compared on clinical attributes that correspond to the maximum difference in progression patterns. The key attributes that distinguish the two sub-groups appear to have support in published literature clinical practice related to CKD.

Predicting hospital visits from geo-tagged Internet search logs.

The steady rise in healthcare costs has deprived over 45 million Americans of healthcare services (1, 2) and has encouraged healthcare providers to look for opportunities to improve their operational efficiency. Prior studies have shown that evidence of healthcare seeking intent in Internet searches correlates well with healthcare resource utilization. Given the ubiquitous nature of mobile Internet search, we hypothesized that analyzing geo-tagged mobile search logs could enable us to machine-learn predictors of future patient visits. Using a de-identified dataset of geo-tagged mobile Internet search logs, we mined text and location patterns that are predictors of healthcare resource utilization and built statistical models that predict the probability of a user's future visit to a medical facility. Our efforts will enable the development of innovative methods for modeling and optimizing the use of healthcare resources-a crucial prerequisite for securing healthcare access for everyone in the days to come.

Learning statistical models of phenotypes using noisy labeled training data.

OBJECTIVE: Traditionally, patient groups with a phenotype are selected through rule-based definitions whose creation and validation are time-consuming. Machine learning approaches to electronic phenotyping are limited by the paucity of labeled training datasets. We demonstrate the feasibility of utilizing semi-automatically labeled training sets to create phenotype models via machine learning, using a comprehensive representation of the patient medical record. METHODS: We use a list of keywords specific to the phenotype of interest to generate noisy labeled training data. We train L1 penalized logistic regression models for a chronic and an acute disease and evaluate the performance of the models against a gold standard. RESULTS: Our models for Type 2 diabetes mellitus and myocardial infarction achieve precision and accuracy of 0.90, 0.89, and 0.86, 0.89, respectively. Local implementations of the previously validated rule-based definitions for Type 2 diabetes mellitus and myocardial infarction achieve precision and accuracy of 0.96, 0.92 and 0.84, 0.87, respectively.We have demonstrated feasibility of learning phenotype models using imperfectly labeled data for a chronic and acute phenotype. Further research in feature engineering and in specification of the keyword list can improve the performance of the models and the scalability of the approach. CONCLUSIONS: Our method provides an alternative to manual labeling for creating training sets for statistical models of phenotypes. Such an approach can accelerate research with large observational healthcare datasets and may also be used to create local phenotype models.