US 11,054,361 B2
Characterization and reproduction of an expert judgement for a binary classification
Josselin Garnier, Paris (FR); Françoise Poggi, Versailles (FR); Gilles Defaux, Ballancourt sur Essonne (FR); Antonio Cosma, Verrieres le Buisson (FR); and Robert Quach, Montreuil (FR)
Appl. No. 15/533,881
Filed by Commissariat A L'Energie Atomique et Aux Energies Alternatives, Paris (FR)
PCT Filed Dec. 11, 2015, PCT No. PCT/FR2015/053452
§ 371(c)(1), (2) Date Jun. 7, 2017,
PCT Pub. No. WO2016/092234, PCT Pub. Date Jun. 16, 2016.
Claims priority of application No. 1462315 (FR), filed on Dec. 12, 2014.
Prior Publication US 2017/0307508 A1, Oct. 26, 2017
Int. Cl. G01N 15/14 (2006.01); G01N 21/64 (2006.01); G01N 15/10 (2006.01)
CPC G01N 15/1459 (2013.01) [G01N 21/6428 (2013.01); G01N 2015/1006 (2013.01); G01N 2015/1402 (2013.01); G01N 2015/1488 (2013.01); G01N 2021/6439 (2013.01)] 5 Claims
OG exemplary drawing
1. An automated analysis method for analysing cells of a blood sample by reacting the cells with at least one specific marker and analyzing fluorescence responses obtained by flow cytometry, the method comprising:
providing a reference sample and an active sample;
providing a rate of false positives (α) in the reference sample characterizing an error rate specific to an expert;
determining a vector coefficient (θ) based on the reference sample and the rate of false positives (α), wherein determining a vector coefficient (θ) comprises:
defining, for each of the markers j, an sj-quantile yjs, quantile of a cumulative distribution function Pjref associated with a smoothed probability distribution function pjref determined by smoothing a marginal distribution of the jth marker in the reference sample;
defining a function F(s) representing a rate of negative cells in the reference sample, increasing from [0,1] to [0,1], by

OG Complex Work Unit Math
where VNs is defined by VNs={i=1, . . . , n such that yijref<yjs for each j=1, . . . , d}, the set of the cells of the reference sample a measured value of which is under the value of the vector coefficient (θ) of the marker corresponding to all the markers;
determining the smallest value of sj such that F(s)>1−α; and
determining the values of the vector coefficient (θ);
determining at least one set (S+) of positive cells in the active sample as a function of the vector coefficient (θ); and
outputting a classification of the analyzed active sample as the set of positive cells (S+) and a set of negative cells (S).