Eliciting relative preferences for the attributes of health insurance schemes among rural consumers in India.

There is a limited understanding of the preferences of rural consumers in India for health insurance schemes. In this article, we investigate the preferences of the rural population for the attributes of a health insurance scheme by implementing a discrete choice experiment (DCE). We identified six attributes through qualitative and quantitative study: enrollment, management, benefit package, coverage, transportation facility, and monthly premium. A D-efficient design of 18 choices has been constructed, each comprising two health insurance choices. We collected the representative sample from 675 household heads of the rural population through personal interviews. The preferences for the attributes and attribute levels were estimated using the multinomial logit (MNL) and random-parameter logit (RPL) models. The analysis shows that all attribute levels significantly affect the choice behavior (P < 0.05). The relative order of preferences for attributes are; enrollment, benefit package, monthly premium, management, coverage, and transportation.

Real-time prediction of smoking activity using machine learning based multi-class classification model.

Smoking cessation efforts can be greatly influenced by providing just-in-time intervention to individuals who are trying to quit smoking. Detecting smoking activity accurately among the confounding activities of daily living (ADLs) being monitored by the wearable device is a challenging and intriguing research problem. This study aims to develop a machine learning based modeling framework to identify the smoking activity among the confounding ADLs in real-time using the streaming data from the wrist-wearable IMU (6-axis inertial measurement unit) sensor. A low-cost wrist-wearable device has been designed and developed to collect raw sensor data from subjects for the activities. A sliding window mechanism has been used to process the streaming raw sensor data and extract several time-domain, frequency-domain, and descriptive features. Hyperparameter tuning and feature selection have been done to identify best hyperparameters and features respectively. Subsequently, multi-class classification models are developed and validated using in-sample and out-of-sample testing. The developed models obtained predictive accuracy (area under receiver operating curve) up to 98.7% for predicting the smoking activity. The findings of this study will lead to a novel application of wearable devices to accurately detect smoking activity in real-time. It will further help the healthcare professionals in monitoring their patients who are smokers by providing just-in-time intervention to help them quit smoking. The application of this framework can be extended to more preventive healthcare use-cases and detection of other activities of interest. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s11042-022-12349-6.

Prediction of Clinical Events in Hemodialysis Patients Using an Artificial Neural Network.

Advanced chronic kidney disease (CKD) requires routine renal replacement therapy (RRT) that involves hemodialysis (HD) which may cause increased risk of muscle spasms, cardiovascular events, and death. We used Artificial Neural Network (ANN) method to predict clinical events during the HD sessions. The vital signs, captured using a non-contact bed-sensor, and demographic information from the electronic medical records for 109 patients enrolled in the study was used. Weka Workbench software was used to train and validate the ANN model. The prediction model was built using a Multilayer perceptron (MLP) algorithm as part of the ANN with 10-fold cross-validation. The model showed mean precision and recall of 93.45% and AUC of 96.7%. Age was the most important variable for static feature and heart rate for dynamic feature. This model can be used to predict the risk of clinical events among HD patients and can support decision-making for healthcare professionals.

Who do the women trust for maternity care: A knowledge network-based study in rural India.

BACKGROUND: Knowledge about the causes of critical ailments and risks during a maternity episode is crucial for women's health. Although maternity-care knowledge is present both in explicit and tacit forms, there is a lack of requisite knowledge among women. Rural women rely on their community for such knowledge. OBJECTIVE: This article sought to analyse knowledge-sharing practices of rural women in India in relation to critical decisions during a maternity episode. METHOD: Primary data were gathered through interview of 306 married women, who had had at least one childbirth during the previous 5 years, and were collected using structured interviews conducted in 10 villages of two districts in West Bengal, India. Their knowledge level of risks and networks of communication was examined for four critical decisions: (i) general health, (ii) choice of delivery method, (iii) antenatal check-up visits and (iv) nutrition. RESULTS: This empirical study using degree-centrality method demonstrated that the pattern of knowledge flow is not uniform for different types of decisions. Many women were not aware of critical danger signs during pregnancy episodes. Only 28% of participants could mention at least three danger signs during pregnancy episodes. For the purposes of this study, these women were considered "knowledgeable." DISCUSSION: Maternal health in the community could be improved by redesigning the knowledge network for sharing the maternity-care knowledge of risks and danger signs. This research highlights the influence of culture on maternity-related knowledge-sharing in rural India and uncovers structural holes in the knowledge network. IMPLICATIONS: Results of this research could be used to design policies and programs to create community-based knowledge networks for maternity care.

Artificial-Intelligence-Based Prediction of Clinical Events among Hemodialysis Patients Using Non-Contact Sensor Data.

Non-contact sensors are gaining popularity in clinical settings to monitor the vital parameters of patients. In this study, we used a non-contact sensor device to monitor vital parameters like the heart rate, respiration rate, and heart rate variability of hemodialysis (HD) patients for a period of 23 weeks during their HD sessions. During these 23 weeks, a total number of 3237 HD sessions were observed. Out of 109 patients enrolled in the study, 78 patients reported clinical events such as muscle spasms, inpatient stays, emergency visits or even death during the study period. We analyzed the sensor data of these two groups of patients, namely an event and no-event group. We found a statistically significant difference in the heart rates, respiration rates, and some heart rate variability parameters among the two groups of patients when their means were compared using an independent sample t-test. We further developed a supervised machine-learning-based prediction model to predict event or no-event based on the sensor data and demographic information. A mean area under curve (ROC AUC) of 90.16% with 96.21% mean precision, and 88.47% mean recall was achieved. Our findings point towards the novel use of non-contact sensors in clinical settings to monitor the vital parameters of patients and the further development of early warning solutions using artificial intelligence (AI) for the prediction of clinical events. These models could assist healthcare professionals in taking decisions and designing better care plans for patients by early detecting changes to vital parameters.

Socioeconomic Determinants of the Utilization of Antenatal Care and Child Vaccination in India.

Antenatal care and child vaccination services are adopted worldwide to reduce the risk of child mortality, maternal mortality, and burden of infectious diseases. This article examines the effect of socioeconomic factors on the utilization of antenatal care and child vaccination services in India. The generalized linear model has been used along with the Indian National Family Health Survey data for the period 2005-2006. The analysis shows that the health insurance plan has a significant effect on the use of antenatal care but not in the child vaccination. Furthermore, there is inequality in the utilization of antenatal care as well as child vaccination services and it is positively related to the wealth. The study suggests that there is a need to improve the socioeconomic status of the financially weaker section of the society for improving the use of child and maternal care services.