Predicting Physician Consultations for Low Back Pain Using Claims Data and Population-Based Cohort Data-An Interpretable Machine Learning Approach.
Ontology highlight
ABSTRACT:
SUBMITTER: Richter A
PROVIDER: S-EPMC8622753 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Patients with drug-resistant epilepsy (DRE) are at high risk of morbidity and mortality, yet their referral to specialist care is frequently delayed. The ability to identify patients at high risk of DRE at the time of treatment initiation, and to subsequently steer their treatment pathway toward more personalized interventions, has high clinical utility. Here, we aim to demonstrate the feasibility of developing algorithms for predicting DRE using machine learning methods. Longitudinal, intersected data sourced from US pharmacy, medical, and adjudicated hospital claims from 1,376,756 patients from 2006 to 2015 were analyzed; 292,892 met inclusion criteria for epilepsy, and 38,382 were classified as having DRE using a proxy measure for drug resistance. Patients were characterized using 1270 features reflecting demographics, comorbidities, medications, procedures, epilepsy status, and payer status. Data from 175,735 randomly selected patients were used to train three algorithms and from the remainder to assess the trained models' predictive power. A model with only age and sex was used as a benchmark. The best model, random forest, achieved an area under the receiver operating characteristic curve (95% confidence interval [CI]) of 0.764 (0.759, 0.770), compared with 0.657 (0.651, 0.663) for the benchmark model. Moreover, predicted probabilities for DRE were well-calibrated with the observed frequencies in the data. The model predicted drug resistance approximately 2 years before patients in the test dataset had failed two antiepileptic drugs (AEDs). Machine learning models constructed using claims data predicted which patients are likely to fail ≥3 AEDs and are at risk of developing DRE at the time of the first AED prescription. The use of such models can ensure that patients with predicted DRE receive specialist care with potentially more aggressive therapeutic interventions from diagnosis, to help reduce the serious sequelae of DRE.
| S-EPMC6461470 | biostudies-literature
Project description:Machine learning (ML) may be used to predict mortality. We used claims data from one large German insurer to develop and test differently complex ML prediction models, comparing them for their (balanced) accuracy, but also the importance of different predictors, the relevance of the follow-up period before death (i.e. the amount of accumulated data) and the time distance of the data used for prediction and death. A sample of 373,077 insured very old, aged 75 years or above, living in the Northeast of Germany in 2012 was drawn and followed over 6 years. Our outcome was whether an individual died in one of the years of interest (2013-2017) or not; the primary metric was (balanced) accuracy in a hold-out test dataset. From the 86,326 potential variables, we used the 30 most important ones for modeling. We trained a total of 45 model combinations: (1) Three different ML models were used; logistic regression (LR), random forest (RF), extreme gradient boosting (XGB); (2) Different periods of follow-up were employed for training; 1-5 years; (3) Different time distances between data used for prediction and the time of the event (death/survival) were set; 0-4 years. The mortality rate was 9.15% in mean per year. The models showed (balanced) accuracy between 65 and 93%. A longer follow-up period showed limited to no advantage, but models with short time distance from the event were more accurate than models trained on more distant data. RF and XGB were more accurate than LR. For RF and XGB sensitivity and specificity were similar, while for LR sensitivity was significantly lower than specificity. For all three models, the positive-predictive-value was below 62% (and even dropped to below 20% for longer time distances from death), while the negative-predictive-value significantly exceeded 90% for all analyses. The utilization of and costs for emergency transport as well as emergency and any hospital visits as well as the utilization of conventional outpatient care and laboratory services were consistently found most relevant for predicting mortality. All models showed useful accuracies, and more complex models showed advantages. The variables employed for prediction were consistent across models and with medical reasoning. Identifying individuals at risk could assist tailored decision-making and interventions.
| S-EPMC9581892 | biostudies-literature
Project description:ObjectiveTo screen for predictive obesity factors in overweight populations using an optimal and interpretable machine learning algorithm.MethodsThis cross-sectional study was conducted between June 2011 and January 2012. The participants were randomly selected using a simple random sampling technique. Seven commonly used machine learning methods were employed to construct obesity risk prediction models. A total of 5,236 Chinese participants from Ningde City, Fujian Province, Southeast China, participated in this study. The best model was selected through appropriate verification and validation and suitably explained. Subsequently, a minimal set of significant predictors was identified. The Shapley additive explanation force plot was used to illustrate the model at the individual level.ResultsMachine learning models for predicting obesity have demonstrated strong performance, with CatBoost emerging as the most effective in both model validity and net clinical benefit. Specifically, the CatBoost algorithm yielded the highest scores, registering 0.91 in the training set and an impressive 0.83 in the test set. This was further corroborated by the area under the curve (AUC) metrics, where CatBoost achieved 0.95 for the training set and 0.87 for the test set. In a rigorous five-fold cross-validation, the AUC for the CatBoost model ranged between 0.84 and 0.91, with an average AUC of ROC at 0.87 ± 0.022. Key predictors identified within these models included waist circumference, hip circumference, female gender, and systolic blood pressure.ConclusionCatBoost may be the best machine learning method for prediction. Combining Shapley's additive explanation and machine learning methods can be effective in identifying disease risk factors for prevention and control.
| S-EPMC10693451 | biostudies-literature
Project description:BackgroundBack pain is one of the most frequent causes of health-related work absence. In Germany, more than 70% of adults suffer from at least one back pain episode per annum. It has strong impact on health care costs and patients' quality of life. Patients increasingly seek health information on the internet. However, judging its trustworthiness is difficult. In addition, physicians who are being confronted with this type of information often experience it to complicate the physician-patient interaction. The GAP trial aims to develop, implement and evaluate an evidence-based, easy-to-understand and trustworthy internet information portal on lower back pain to be used by general practitioners and patients during and after the consultation. Effectiveness of GAP portal use compared to routine consultation on improving communication and informedness of both physicians and patients will be assessed. In addition, effects on health care costs and patients' days of sick leave will be evaluated.MethodsWe will conduct a prospective multi-centre, cluster-randomized parallel group trial including 1500 patients and 150 recruiting general practitioners. The intervention group will have access to the GAP portal. The portal will contain brief guides for patients and physicians on how to improve the consultation as well as information on epidemiology, aetiology, symptoms, benefits and harms of treatment options for acute, sub-acute and chronic lower back pain. The GAP portal will be designed to be user-friendly and present information on back pain tailored for either patients or physicians in form of brief fact sheets, educative videos, info-graphics, animations and glossaries. Physicians and patients will assess their informedness and the physician-patient communication in consultations at baseline and at two time points after the consultations under investigation. Days of sick leave and health care costs related to back pain will be compared between control and intervention group using routine data of company health insurance funds.DiscussionThe GAP-trial intends to improve the communication between physicians and their patients and the informedness of both groups. If proven beneficial, the evidence-based and user-friendly portal will be made accessible for all patients and health professionals in back pain care. Inclusion of further indications might be implemented and evaluated in the long term.Trial registrationGerman Clinical Trials Register DRKS00014279 (registered 27th of April 2018).
| S-EPMC6388488 | biostudies-literature
Project description:BACKGROUND:Adverse drug reactions (ADRs) are unintended and harmful reactions caused by normal uses of drugs. Predicting and preventing ADRs in the early stage of the drug development pipeline can help to enhance drug safety and reduce financial costs. METHODS:In this paper, we developed machine learning models including a deep learning framework which can simultaneously predict ADRs and identify the molecular substructures associated with those ADRs without defining the substructures a-priori. RESULTS:We evaluated the performance of our model with ten different state-of-the-art fingerprint models and found that neural fingerprints from the deep learning model outperformed all other methods in predicting ADRs. Via feature analysis on drug structures, we identified important molecular substructures that are associated with specific ADRs and assessed their associations via statistical analysis. CONCLUSIONS:The deep learning model with feature analysis, substructure identification, and statistical assessment provides a promising solution for identifying risky components within molecular structures and can potentially help to improve drug safety evaluation.
| S-EPMC6300887 | biostudies-other
Project description:Applying deep learning in population genomics is challenging because of computational issues and lack of interpretable models. Here, we propose GenNet, a novel open-source deep learning framework for predicting phenotypes from genetic variants. In this framework, interpretable and memory-efficient neural network architectures are constructed by embedding biologically knowledge from public databases, resulting in neural networks that contain only biologically plausible connections. We applied the framework to seventeen phenotypes and found well-replicated genes such as HERC2 and OCA2 for hair and eye color, and novel genes such as ZNF773 and PCNT for schizophrenia. Additionally, the framework identified ubiquitin mediated proteolysis, endocrine system and viral infectious diseases as most predictive biological pathways for schizophrenia. GenNet is a freely available, end-to-end deep learning framework that allows researchers to develop and use interpretable neural networks to obtain novel insights into the genetic architecture of complex traits and diseases.
| S-EPMC8448759 | biostudies-literature
Project description:Soil moisture is critical to agricultural business, ecosystem health, and certain hydrologically driven natural disasters. Monitoring data, though, is prone to instrumental noise, wide ranging extrema, and nonstationary response to rainfall where ground conditions change. Furthermore, existing soil moisture models generally forecast poorly for time periods greater than a few hours. To improve such forecasts, we introduce two data-driven models, the Naive Accumulative Representation (NAR) and the Additive Exponential Accumulative Representation (AEAR). Both of these models are rooted in deterministic, physically based hydrology, and we study their capabilities in forecasting soil moisture over time periods longer than a few hours. Learned model parameters represent the physically based unsaturated hydrological redistribution processes of gravity and suction. We validate our models using soil moisture and rainfall time series data collected from a steep gradient, post-wildfire site in southern California. Data analysis is complicated by rapid landscape change observed in steep, burned hillslopes in response to even small to moderate rain events. The proposed NAR and AEAR models are, in forecasting experiments, shown to be competitive with several established and state-of-the-art baselines. The AEAR model fits the data well for three distinct soil textures at variable depths below the ground surface (5, 15, and 30 cm). Similar robust results are demonstrated in controlled, laboratory-based experiments. Our AEAR model includes readily interpretable hydrologic parameters and provides more accurate forecasts than existing models for time horizons of 10-24 h. Such extended periods of warning for natural disasters, such as floods and landslides, provide actionable knowledge to reduce loss of life and property.
| S-EPMC9427440 | biostudies-literature
Project description:This SuperSeries is composed of the SubSeries listed below.
2024-01-27 | GSE230012 | GEO
Project description:BackgroundBack pain is a global health problem. Recent research has shown that risk factors that are proximal to the onset of back pain might be important targets for preventive interventions. Rapid communication through social media might be useful for delivering timely interventions that target proximal risk factors. Identifying individuals who are likely to discuss back pain on Twitter could provide useful information to guide online interventions.MethodsWe used a case-crossover study design for a sample of 742 028 tweets about back pain to quantify the risks associated with a new tweet about back pain.ResultsThe odds of tweeting about back pain just after tweeting about selected physical, psychological, and general health factors were 1.83 (95% confidence interval [CI], 1.80-1.85), 1.85 (95% CI: 1.83-1.88), and 1.29 (95% CI, 1.27-1.30), respectively.ConclusionThese findings give directions for future research that could use social media for innovative public health interventions.
| S-EPMC7839924 | biostudies-literature
Project description:BACKGROUND:The impact of telephone consultations between pain specialists and primary care physicians regarding the care of patients with chronic pain is unknown. OBJECTIVES:To evaluate the impact of telephone consultations between pain specialists and primary care physicians regarding the care of patients with chronic pain. METHODS:Patients referred to an interdisciplinary chronic pain service were randomly assigned to either receive usual care by the primary care physician, or to have their case discussed in a telephone consultation between a pain specialist and the referring primary care physician. Patients completed a numerical rating scale for pain, the Pain Disability Index and the Short Form-36 on referral, as well as three and six months later. Primary care physicians completed a brief survey to assess their impressions of the telephone consultation. RESULTS:Eighty patients were randomly assigned to either the usual care group or the standard telephone consultation group, and 67 completed the study protocol. Patients were comparable on baseline pain and demographic characteristics. No differences were found between the groups at six months after referral in regard to pain, disability or quality of life measures. Eighty percent of primary care physicians indicated that they learned new patient care strategies from the telephone consultation, and 97% reported that the consultation answered their questions and helped in the care of their patient. DISCUSSION:Most primary care physicians reported that a telephone consultation with a pain specialist answered their questions, improved their patients' care and resulted in new learning. Differences in patient status compared with a usual care control group were not detectable at six-month follow-up. CONCLUSIONS:While telephone consultations are clearly an acceptable strategy for knowledge translation, additional strategies may be required to actually impact patient outcomes.
| S-EPMC4676497 | biostudies-literature