25
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      A Kalman Filtering and Nonlinear Penalty Regression Approach for Noninvasive Anemia Detection with Palpebral Conjunctiva Images

      research-article
      1 , 2 , *
      Journal of Healthcare Engineering
      Hindawi

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Noninvasive medical procedures are usually preferable to their invasive counterparts in the medical community. Anemia examining through the palpebral conjunctiva is a convenient noninvasive procedure. The procedure can be automated to reduce the medical cost. We propose an anemia examining approach by using a Kalman filter (KF) and a regression method. The traditional KF is often used in time-dependent applications. Here, we modified the traditional KF for the time-independent data in medical applications. We simply compute the mean value of the red component of the palpebral conjunctiva image as our recognition feature and use a penalty regression algorithm to find a nonlinear curve that best fits the data of feature values and the corresponding levels of hemoglobin (Hb) concentration. To evaluate the proposed approach and several relevant approaches, we propose a risk evaluation scheme, where the entire Hb spectrum is divided into high-risk, low-risk, and doubtful intervals for anemia. The doubtful interval contains the Hb threshold, say 11 g/dL, separating anemia and nonanemia. A suspect sample is the sample falling in the doubtful interval. For the anemia screening purpose, we would like to have as less suspect samples as possible. The experimental results show that the modified KF reduces the number of suspect samples significantly for all the approaches considered here.

          Related collections

          Most cited references36

          • Record: found
          • Abstract: found
          • Article: not found

          Noninvasive diagnosis by Doppler ultrasonography of fetal anemia due to maternal red-cell alloimmunization. Collaborative Group for Doppler Assessment of the Blood Velocity in Anemic Fetuses.

          Invasive techniques such as amniocentesis and cordocentesis are used for diagnosis and treatment in fetuses at risk for anemia due to maternal red-cell alloimmunization. The purpose of our study was to determine the value of noninvasive measurements of the velocity of blood flow in the fetal middle cerebral artery for the diagnosis of fetal anemia. We measured the hemoglobin concentration in blood obtained by cordocentesis and also the peak velocity of systolic blood flow in the middle cerebral artery in 111 fetuses at risk for anemia due to maternal red-cell alloimmunization. Peak systolic velocity was measured by Doppler velocimetry. To identify the fetuses with anemia, the hemoglobin values of those at risk were compared with the values in 265 normal fetuses. Fetal hemoglobin concentrations increased with increasing gestational age in the 265 normal fetuses. Among the 111 fetuses at risk for anemia, 41 fetuses did not have anemia; 35 had mild anemia; 4 had moderate anemia; and 31, including 12 with hydrops, had severe anemia. The sensitivity of an increased peak velocity of systolic blood flow in the middle cerebral artery for the prediction of moderate or severe anemia was 100 percent either in the presence or in the absence of hydrops (95 percent confidence interval, 86 to 100 percent for the 23 fetuses without hydrops), with a false positive rate of 12 percent. In fetuses without hydrops that are at risk because of maternal red-cell alloimmunization, moderate and severe anemia can be detected noninvasively by Doppler ultrasonography on the basis of an increase in the peak velocity of systolic blood flow in the middle cerebral artery.
            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Illusions in regression analysis

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Estimation of Sideslip and Roll Angles of Electric Vehicles Using Lateral Tire Force Sensors Through RLS and Kalman Filter Approaches

                Bookmark

                Author and article information

                Journal
                J Healthc Eng
                J Healthc Eng
                JHE
                Journal of Healthcare Engineering
                Hindawi
                2040-2295
                2040-2309
                2017
                30 July 2017
                : 2017
                : 9580385
                Affiliations
                1Acoustic Science and Technology Laboratory, College of Underwater Acoustic Engineering, Harbin Engineering University, Harbin, China
                2Department of Electronic Engineering, Chung Yuan Christian University, Taoyuan City, Taiwan
                Author notes
                *Shaou-Gang Miaou: miaou@ 123456cycu.edu.tw

                Academic Editor: João Manuel R.S. Tavares

                Author information
                http://orcid.org/0000-0002-5422-6959
                http://orcid.org/0000-0003-0089-7324
                Article
                10.1155/2017/9580385
                5554583
                29065671
                c86f873d-f971-4a3d-b543-2a73097b1c09
                Copyright © 2017 Yi-Ming Chen and Shaou-Gang Miaou.

                This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

                History
                : 14 February 2017
                : 4 May 2017
                : 1 June 2017
                Categories
                Research Article

                Comments

                Comment on this article