Delirium occurs in about 80% of cases in the Intensive Care Unit (ICU) and is associated with an extended hospital stay, increased mortality, and other complications. Delirium lacks biomarker-based diagnosis and is frequently treated with antipsychotic drugs (APD), despite numerous studies debating its efficacy. Since randomized controlled trials (RCT) are expensive and time-consuming, we approach the research question of estimating the efficacy and safety outcomes of APD in treating delirium through retrospective cohort analysis. We employed the Causal inference framework to explore the underlying causal model for Delirium patient cohort. We focus on building a structural causal model for delirium in the ICU using large observational data sets linking various delirium-related covariates. We utilized an extensive electronic health records (EHR) dataset (MIMIC-III) to curate delirium data cohort. Our null hypothesis examines any significant differences in outcomes (30-day mortality and ICU length of stay) among delirium patients under different drug-groups (Haloperidol, other drugs, and no drugs). Our causal exploration presents a specialized pipeline through causal model generation, expert knowledge augmentation and average treatment effect estimation. Through our exploratory, machine learning driven, and causal analysis, we estimate and compare effects of antipsychotic drug groups on patients’ survival timeline and ICU length-of-stay.

Causal inference involving Structural causal models (SCMs) provides a principled approach to identifying causation from observational and experimental data in disciplines ranging from economics to medicine. However, to estimate the underlying causal structure, SCMs need to rely on domain knowledge in addition to available data. Clinical research has a vast collection of well-explored hypotheses, experiments, and publications, rich with underused causal information. A key challenge in this context is the absence (or acceptance) of a systematic and methodological framework for encoding priors (background knowledge) into causal models. We propose an abstraction called causal knowledge hierarchy (CKH) for encoding priors into causal models. Our approach is based on the foundation of "levels of evidence" in medicine, with a focus on confidence in causal information. Using CKH, we present a standardized framework for encoding causal priors from various information sources and combining them to derive an SCM. We evaluate our approach on multiple (simulated and real-world) benchmark datasets and demonstrate overall performance compared to the ground truth causal model.

Diabetic eye diseases, particularly Diabetic Retinopathy, is the leading cause of vision loss worldwide and can be prevented by early diagnosis through annual eye-screenings. However, cost, health care disparities, cultural limitations, etc. are the main barriers against regular screening. Eye-screenings conducted in community events with native-speaking staffs can facilitate regular check-up and development of awareness among underprivileged communities compared to traditional clinical settings. However, there are not sufficient technology support for carrying out the screenings in community settings with collaboration from community partners using native languages. In this paper, we have proposed and discussed the development of our software framework, “Mobile Teleophthalmology in Community Settings (mTOCS)”, that connects the community partners with eye-specialists and the Health Department staffs of respective cities to expedite this screening process. Moreover, we have presented the analysis from our study on the acceptance of community-based screening methods among the community participants as well as on the effectiveness of mTOCS among the community partners. The results have evinced that mTOCS has been capable of providing an improved rate of eye-screenings and better health outcomes.

In this research paper, we analyzed what moments and activities make people happy, based on a collection of happy moments. We are focusing on specific happy moments from a collection of text responses that people have shared through the crowd-sourcing platform: Amazon Mechanical Turk (MTurk). Using crowd-sourcing to collect our data allows us to advance our understanding of the cause of happiness, by focusing on words and real human experiences. Workers of MTurk were asked to reflect on what makes them happy in a given period and share three specific moments in complete sentences. Through text-based analysis, we will look to see what other components have a role in making a specific event happy and further analyze how we can classify such words. Also, we dive deeper into specific subcategories of classifiers in an attempt to form insights about their happiness level based on specific factors. With the goal to extract features from the text in HappyDB, in this study we used the bag of words approach. Through doing so, our results were successful at predicting the happiness category, concerning both accuracy and context. Our models were able to accomplish the goal of understanding a happy moment and fit such a moment into one of the seven ground truth happiness categories we set at the beginning of this study. We finished the article with the ethical perspective of such research works and related social implications.

Risky behavior including violence and aggression, self-injury, anger outburst, domestic violence along with self-injury, sexual abuse, rule-breaking, use of drugs and alcohol, suicide, etc. are alarming issues among US military veterans who return from combat zone deployment in Iraq and Afghanistan. Veterans are exposed to trauma in war zones which affect most of them with post-traumatic stress disorder (PTSD) or other mental health problems to some degree. Studies have shown that veterans have much higher rates of PTSD than civilians and are more likely to engage in risky behavior. One of the forms of displaying and engaging in risky behaviors is through gestures. We collaborated with veterans and social scientists to find the list of 13 gestures that are often used by veterans engaged in risky behaviors. In this research work, we have collected accelerometer data from subjects performing the gestures mentioned above and have tried to detect them using machine learning techniques. This paper describes identifying gesture clusters from the accelerometer coordinate data and development of a predictive model that can classify the gestures resulting in the prediction of risky behaviors among the veterans who suffer from PTSD.

It is necessary for a cancer survivor to have good health behavior. Essential exercise and proper diet are helpful to decrease the risk of recurrence of the disease and the development of a new cancer type. People from low socioeconomic status are more likely to participate in risky health behaviors and have a higher chance of recurrence of cancer. It is important to have a motivational system for cancer survivors that motivates them to perform regular physical activities. In this article, we discuss the development of an mHealth system, which aims to increase physical activity in Native American populations with culturally appropriate motivational text and video messages. The system also includes an e-journal to monitor and maintain proper healthcare. We will also analyze the pilot data to evaluate the usability and the effectiveness of the system.