Two‐stage approach for risk estimation of fetal trisomy 21 and other aneuploidies using computational intelligence systems

Objective To estimate the risk for fetal trisomy 21 (T21) and other chromosomal abnormalities at 11-13 week's gestation using computational intelligence classification methods. Methods As a first step, we train the artificial neural networks with 72054 euploid pregnancies, 295 cases of T21 and 305 of other chromosomal abnormalities (OCA). Then, we sort the cases into two categories of “no-risk” and “risk”. The cases of “no-risk” are no further examined, while the cases with “risk” are forwarded in Stage 2 for further examination where we classify them in three types of risk, namely “no-risk”, “moderate-risk” and “high-risk”. Results Of a total of 36328 unknown to the system pregnancies, in the first Stage, 17512 euploid, 2 T21 and 18 other chromosomal abnormalities are classified as “no-risk”. The remaining 18796 (51.4% FPR) cases are reassigned in Stage 2 where 7895 euploid, 2 T21 and 2 OCA are classified as “no-risk”, 10464 euploid, 83 T21 and 61 OCA as “moderate-risk” and 187 euploid, 50 T21 and 52 OCA as “high-risk”. The sensitivity and the specificity for T21 in Stage 2 are 97.1% and 99.5% respectively, assuming that cell-free DNA test can identify all the euploid and aneuploid cases. Conclusion We propose a method for the early diagnosis of chromosomal abnormalities, which ensures that most of the T21 are classified as “high-risk” at any Stage. At the same time, we minimize the euploid cases that have to undergo invasive or cell-free DNA examinations through a routine procedure offered in two Stages. Our method is minimally invasive and of relatively low cost, highly effective on T21 identification and it performs better than other existing statistical methods.