Causality Refined Diagnostic Prediction

نویسندگان

  • Marcus Klasson
  • Kun Zhang
  • Bo C. Bertilson
  • Cheng Zhang
  • Hedvig Kjellström
چکیده

Applying machine learning in the health care domain has shown promising results in recent years. Interpretable outputs from learning algorithms are desirable for decision making by health care personnel. In this work, we explore the possibility of utilizing causal relationships to refine diagnostic prediction. We focus on the task of diagnostic prediction using discomfort drawings, and explore two ways to employ causal identification to improve the diagnostic results. Firstly, we use causal identification to infer the causal relationships among diagnostic labels which, by itself, provides interpretable results to aid the decision making and training of health care personnel. Secondly, we suggest a post-processing approach where the inferred causal relationships are used to refine the prediction accuracy of a multi-view probabilistic model. Experimental results show firstly that causal identification is capable of detecting the causal relationships among diagnostic labels correctly, and secondly that there is potential for improving pain diagnostics prediction accuracy using the causal relationships.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Errors in Text and Conversion Factors in: Validation and Refinement of a Prediction Rule to Identify Children at Low Risk for Acute Appendicitis.

OBJECTIVE To validate and refine a clinical prediction rule to identify which children with acute abdominal pain are at low risk for appendicitis (Low-Risk Appendicitis Rule). DESIGN Prospective, multicenter, cross-sectional study. SETTING Ten pediatric emergency departments. PARTICIPANTS Children and adolescents aged 3 to 18 years who presented with suspected appendicitis from March 1, 2...

متن کامل

A New Three-Dimensional Refined Higher-Order Theory for Free Vibration Analysis of Composite Circular Cylindrical Shells

A new closed form formulation of three-dimensional (3-D) refined higher-order shell theory (RHOST) to analyze the free vibration of composite circular cylindrical shells has been presented in this article. The shell is considered to be laminated with orthotropic layers and simply supported boundary conditions. The proposed theory is used to investigate the effects of the in-plane and rotary ine...

متن کامل

In silico Prediction and Docking of Tertiary Structure of LuxI, an Inducer Synthase of Vibrio fischeri

Background: LuxI is a component of the quorum sensing signaling pathway in Vibrio fischeri responsible for the inducer synthesis that is essential for bioluminescence. Methods: Homology modeling of LuxI was carried out using Phyre2 and refined with the GalaxyWEB server. Five models were generated and evaluated by ERRAT, ANOLEA, QMEAN6, and Procheck. Results: Five refined models were gener...

متن کامل

A Rational Model of Elemental Diagnostic Inference

Whereas the traditional normative benchmark for diagnostic reasoning from effects to causes is provided by purely statistical norms, we here approach the task from the perspective of rational causal inference. The core feature of the presented model is the assumption that diagnostic inferences are constrained by hypotheses about the causal texture of the domain. As a consequence, the model’s pr...

متن کامل

Diagnostic Value of Risk Nomogram for the Prediction of Postpartum Hemorrhage Following Vaginal Delivery

Background: Postpartum hemorrhage (PPH) is considered as one of the major causes of maternal mortality worldwide. The most effective risk factors have been suggested in various studies on risk nomogram for the prediction of PPH. Aim: This study aimed to determine the diagnostic value of the risk nomogram for the prediction of PPH. Method: Thi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1711.10915  شماره 

صفحات  -

تاریخ انتشار 2017