Nozomi Nori

Simultaneous Modeling of Multiple Diseases for Mortality Prediction in Acute Hospital Care

Acute hospital care as performed in the intensive care unit (ICU) is characterized by its frequent, but short-term interventions for patients who are severely ill. Because clinicians have to attend to more than one patient at a time and make decisions in a limited time in acute hospital care environments, the accurate prediction of the in-hospital mortality risk could assist them to pay more attention to patients with a higher in-hospital mortality risk, thereby improving the quality and efficiency of the care. One of the salient features of ICU is the diversity of patients: clinicians are faced by patients with a wide variety of diseases. However, mortality prediction for ICU patients has typically been conducted by building one common predictive model for all the diseases. In this paper, we incorporate disease-specific contexts into mortality modeling by formulating the mortality prediction problem as a multi-task learning problem in which a task corresponds to a disease. Our method effectively integrates medical domain knowledge relating to the similarity among diseases and the similarity among Electronic Health Records (EHRs) into a data-driven approach by incorporating graph Laplacians into the regularization term to encode these similarities. The experimental results on a real dataset from a hospital corroborate the effectiveness of the proposed method. The AUCs of several baselines were improved, including logistic regression without multi-task learning and several multi-task learning methods that do not incorporate the domain knowledge. In addition, we illustrate some interesting results pertaining to disease-specific predictive features, some of which are not only consistent with existing medical domain knowledge, but also contain suggestive hypotheses that could be validated by further investigations in the medical domain.

Crowdsourced data analytics: A case study of a predictive modeling competition

Predictive modeling competitions provide a new data mining approach that leverages crowds of data scientists to examine a wide variety of predictive models and build the best performance model. Competition hosts, who provide their own dataset and specify the problem to be solved, are not only able to obtain the best model from among those submitted but also to aggregate the submitted models to obtain one that outperforms the rest. In this paper, we report the results of a study conducted on CrowdSolving, a platform for predictive modeling competitions in Japan. We hosted a competition on a link prediction task and observed that (i) the prediction performance of the winner significantly outperformed that of a state-of-the-art method, (ii) the aggregated model constructed from all submitted models further improved the final performance, and (iii) the performance of the aggregated model built only from early submissions nevertheless overtook the final performance of the winner. Our results show the power of crowds for predictive modeling, not only in the quality of the obtained model, but also in its speed to achieve it. Furthermore, they demonstrate the possibilities of combining human insights and machine learning in data analytics.

Empirical Study of Conversational Community Using Linguistic Expression and Profile Information

The popularization of social media exposes the structure of people’s conversation - what kind of people speak with whom, on what topics and with what kinds of words. In this paper, we propose a new approach to mining conversational network by community analysis, which exploits users’ profile information, interaction network and linguistic usage. Using our framework, we conducted empirical analysis on the complex relation among people’s profile information, social network, and language network using a large dataset from Twitter, which covers more than 7M people. Our findings include (1) we can extract a community composed of people who use the same kinds of slangs by exploiting information from both the social network and word usage, (2) when we focus on similarity among communities in terms of both interaction and word usage, we can find specific patterns based on the people’s profile information including their attributes and interests.