Temporal case matching with information value maximization for predicting physiological states

Electronic consultation accessibility influence on patient assessments: A case-control study with user-generated tags of physician expertise

Objective

In online health communities (OHCs), patients often list their physicians' expertise by user-generated tags based on their consulted diseases. These expertise tags play an essential role in recommending the match of physicians to future patients. However, few studies have examined the impact of the accessibility of e-consults on patient assessments using marking of the physicians' expertise in OHCs. This study aims to investigate what are the patient assessments of the physicians' expertise if they have e-consult accessibility.

Methods

Through a case-control study, this article examined the effect of e-consult accessibility on patient-generated tags of physician expertise in OHCs. With data collected from the Good Doctor website, the samples consisted of 9841 physicians from 1255 different hospitals widely distributed in China. The breadth of voted expertise (BE) is measured by the number of consulted disease-related labels marked by a physician's served patients (SP). The volume of votes (VV) is measured by the number of a physician's votes given by the SP. The degree of voted diversity (DD) is measured by the information entropy of each physician's service expertise (labeled and voted by patients). The data analysis of e-consult accessibility is conducted by estimating the average treatment effect on the DD of physicians' expertise.

Results

For the BE, its mean was 7.305 for the case group of physicians with e-consults accessible (photo and text queries), while the mean was 9.465 for the control for physicians without e-consults. For the VV, its mean was 39.720 for the case group, while the mean was 84.565 for the control. For the DD, its mean on patient-generated tags was 2.103 for the case group, which is 0.413 lower than the control group.

Conclusion

The availability of e-consults increases the concentration on physician expertise in the patient-generated tags. e-Consults reinforce the increment of the already-received physician expertise (reflected in tags), reducing the tag information diversity.

Physiological Status Prediction Based on a Novel Hybrid Intelligent Scheme

Physiological status plays an important role in clinical diagnosis. However, the temporal physiological data change dynamically with time, and the amount of data is large; furthermore, obtaining a complete history of data has become difficult. We propose a hybrid intelligent scheme for physiological status prediction, which can be effectively utilized to predict the physiological status of patients and provide a reference for clinical diagnosis. Our proposed scheme initially extracted the attribute information of nonlinear dynamic changes in physiological signals. The maximum discriminant feature subset was selected by employing conditional relevance mutual information feature selection. An optimal subset of features was fed into the particle swarm optimization-support vector machine classifier to perform classification. For the prediction task, the proposed hybrid intelligent scheme was tested on the Sleep Heart Health Study dataset for sleep status prediction. Experimental results demonstrate that our proposed intelligent scheme outperforms the conventional machine learning classification methods.

Causal Effect of Honorary Titles on Physicians' Service Volumes in Online Health Communities: Retrospective Study

Background

An OHC online health community (OHC) is an interactive platform for virtual communication between patients and physicians. Patients can typically search, seek, and share their experience and rate physicians, who may be involved in giving advice. Some OHC providers provide incentives in form of honorary titles to encourage the web-based involvement of physicians, but it is unclear whether the award of honorary titles has an impact on their consultation volume in an OHC.

Objective

This study is designed to identify the differential treatment effect of the incentive policy on the service volumes for the subgroups of treatment and control in an OHC. This study aims to answer the following questions: Does an honorary title for physicians impact their service volumes in an OHC? During the period of discontinuity, can we identify the sharp effect of the incentive award on the outcomes of physicians’ service volumes?

Methods

We acquired the targeted samples based on treatment, namely, physicians with an honorary title or not and outcomes measured before and after the award of the 2 subgroups. A regression discontinuity design was applied to investigate the impact of the honorary titles incentive as a treatment in an OHC. There was a sharply discontinuous effect of treatment on physicians’ online health service performance. The experimental data set consisted of 346 physicians in the treatment group (with honorary titles). Applying the propensity score matching method, the same size of physicians (n=346) was matched and selected as the control group.

Results

A sharp discontinuity was found at the time of the physician receiving the honorary title. The results showed that the parametric estimates of the coefficient were significantly positively (P<.001) associated with monthly home page views. The jump in the monthly volumes of home page views was much sharper than that of the monthly consultations.

Conclusions

The changes in the volumes of monthly consultations and home page views reflect the differential treatment effect of honorary titles on physicians’ service volumes. The effect of the incentive policy with honorary titles is objectively estimated from both the perspective of online and offline medical services in an OHC. Being named with honorary titles significantly multiplied monthly home page views, yet it did not significantly impact monthly consultations. This may be because consultation capacity is limited by the physician's schedule for consultations.

Understanding a Nonlinear Causal Relationship Between Rewards and Physicians' Contributions in Online Health Care Communities: Longitudinal Study

Background

The online health care community is not just a place for the public to share physician reviews or medical knowledge, but also a physician-patient communication platform. The medical resources of developing countries are relatively inadequate, and the online health care community is a potential solution to alleviate the phenomenon of long hospital queues and the lack of medical resources in rural areas. However, the success of the online health care community depends on online contributions by physicians.

Objective

The aim of this study is to examine the effect of incentive mechanisms on physician’s online contribution behavior in the online health community. We addressed the following questions: (1) from which specialty area are physicians more likely to participate in online health care community activities, (2) what are the factors affecting physician online contributions, and (3) do incentive mechanisms, including psychological and material rewards, result in differences of physician online contributions?

Methods

We designed a longitudinal study involving a data sample in three waves. All data were collected from the Good Doctor website, which is the largest online health care community in China. We first used descriptive statistics to investigate the physician online contribution behavior in its entirety. Then multiple linear and quadratic regression models were applied to verify the causal relationship between rewards and physician online contribution.

Results

Our sample included 40,300 physicians from 3607 different hospitals, 10 different major specialty areas, and 31 different provinces or municipalities. Based on the multiple quadratic regression model, we found that the coefficients of the control variables, past physician online contributions, doctor review rating, clinic title, hospital level, and city level, were .415, .189, –.099, –.106, and –.143, respectively. For the psychological (or material) rewards, the standardized coefficient of the main effect was 0.261 (or 0.688) and the standardized coefficient of the quadratic effect was –0.015 (or –0.049). All estimates were statistically significant (P<.001).

Conclusions

Physicians with more past physician online contribution, with higher review ratings, coming from lower level clinics, not coming from tertiary hospitals, and not coming from big cities were more willing to participate in online health care community activities. To promote physician online contribution, it is necessary to establish an appropriate incentive mechanism including psychological and material rewards. Finally, our findings suggest two guidelines for designing a useful incentive mechanism to facilitate physician online contribution. First, material reward is more useful than psychological reward. Second, as indicated by the concave-down-increasing causal relationship between rewards and physician online contribution, although an appropriate reward is effective in encouraging willingness on the part of physicians to contribute to the online health care community, the effect of additional rewards is limited.

Electronic Health Record Driven Prediction for Gestational Diabetes Mellitus in Early Pregnancy

Gestational diabetes mellitus (GDM) is conventionally confirmed with oral glucose tolerance test (OGTT) in 24 to 28 weeks of gestation, but it is still uncertain whether it can be predicted with secondary use of electronic health records (EHRs) in early pregnancy. To this purpose, the cost-sensitive hybrid model (CSHM) and five conventional machine learning methods are used to construct the predictive models, capturing the future risks of GDM in the temporally aggregated EHRs. The experimental data sources from a nested case-control study cohort, containing 33,935 gestational women in West China Second Hospital. After data cleaning, 4,378 cases and 50 attributes are stored and collected for the data set. Through selecting the most feasible method, the cost parameter of CSHM is adapted to deal with imbalance of the dataset. In the experiment, 3940 samples are used for training and the rest 438 samples for testing. Although the accuracy of positive samples is barely acceptable (62.16%), the results suggest that the vast majority (98.4%) of those predicted positive instances are real positives. To our knowledge, this is the first study to apply machine learning models with EHRs to predict GDM, which will facilitate personalized medicine in maternal health management in the future.