Rule 16. If SI high and AMo high and LTV slow and STV slow, then there is loss of fetal wellbeing.

IF SI↑ AND AMo↑ AND LTV↓ AND STV↓ THEN FETAL DISTRESS.

#### 4. Results

The results of the fuzzy diagnosis for 188 datasets are shown in Figure 8. Two well-defined clusters can be observed, corresponding to those who were clinically diagnosed as healthy pregnancies (+) and those who presented loss of fetal well-being (o). Can be observed that a

Figure 8. Scatter plot for fuzzy outputs of the 188 records.

fuzzy output from a high-risk pregnancy record with fetal distress was incorrectly evaluated by fuzzy system, fuzzy output of 0.183 classifies it as normal pregnancy.

Table 6 shows 6 of the 49 records, the values for their descriptors, the fuzzy output, and the clinical diagnosis. The records N16, N6, FGR6, FGR29, N27 are well evaluated by the fuzzy inference system, but the record FGR20, which corresponds to a fetal growth restricted pregnancy with fetal distress, is classified by fuzzy system as normal pregnancy. The ROC curve and confusion matrix for the 188 cases evaluated are shown in Figure 9.

Of the 188 records, 84 with fetal distress were correctly evaluated (true positives) and only one was diagnosed as normal (false negative). On the other hand, the 103 normal cases were


Table 6. SI, AMo, LTV, and STV values for fuzzy input descriptors, fuzzy assessment, and clinic diagnosis.

Fuzzy Detection of Fetal Distress for Antenatal Monitoring in Pregnancy with Fetal Growth Restriction… 21 http://dx.doi.org/10.5772/intechopen.80223

Figure 9. (a) ROC curve of the overall fuzzy system evaluation and (b) confusion matrix for 188 data evaluated.

diagnosed correctly (true negatives) by the fuzzy system. The global sensitivity was 0.9882 and global specificity was 1.

Finally, fuzzy inference system was evaluated with 21 new records of 30 minutes, classified as distress: D1-D3, and normal pregnancy: N1-N18. Each record was sampled at 2-minute interval. Figure 10 shows the fuzzy evaluation of three records of patients with emergency

Figure 10. Fuzzy evaluation of three 30-minutes records of patients with emergency pregnancy.

Figure 11. Fuzzy evaluation of eighteen 30-minute records of patients with normal pregnancy.

pregnancy. D1 and D2 were classified with fetal distress correctly, but D3 is shown with a normal fetal well-being state.

Figure 11 shows the fuzzy inference of 18 patients with normal pregnancy. Records N2-N4, N6-N16, and N18 show a normal fetal well-being during the 30-minute recording. The record N1 shows an indeterminate state, except for periods of 3–5 and 8–10 minutes, where the assessment of fetal well-being is normal. The record N5 was classified by the fuzzy system as indeterminate. N17 shows fetal distress from minutes 3 to 9, between minutes 15 and 21 the fetal state changes to normal, returning to distress after minute 27.

#### 5. Conclusions

A combination of fetal HRV and CTG descriptors was proposed for discrimination between fetuses with loss of fetal well-being and normal fetuses, both in pregnancies with intrauterine growth restriction and healthy pregnancies.

The feasibility of the selected descriptors, SI, AMo, STV, and LTV was evaluated by sensitivity, specificity, and Spearman's correlation analysis, so that these parameters can be considered as evident markers of fetal well-being status in the case of FGR.

Since SI and AMo are relevant to the sympathetic part of the autonomic regulation, the opinion on the involvement of the sympathetic mechanisms in fetal distress is supported [1]. The predictive value of the parasympathetic regulation variables was lower. The growing activity of this division of the autonomic function is a marker of fetal neurological maturation [5]. The relation found between maternal and fetal HRV parameters was a sign of fetal and maternal coupling in healthy pregnancy. Maternal respiratory sinus arrhythmia was speculated as a reason of this regularity. It was disturbed in preeclampsia [11]. Fetal growth is known to be impacted by maternal organism [6, 13]. The investigation of the possible relations between maternal and fetal HRV and its fractal components will create a novel concept of the management of women with growth-restricted fetuses.

Formerly, the most sensitive and specific for fetal distress T/QRS ratio obtained from fetal noninvasive ECG tracing was found [1, 12]. Since peaks and intervals are detectable on fetalaveraged PQRST complex, the subsequent investigation of their clinical significance is of great prospect. But the study population of the abovementioned research was suffered from preeclampsia. Thus, preeclampsia could change fetal cardiac conductivity. But will T/QRS ratio be of use in diagnosing fetal distress among all pregnant women is still a question?

The main criterion of fetal well-being is a reactivity to its motile activity by accelerating the heart rate during nonstress test [2, 3]. The obtained results could make it possible to think that SI and AMo will become an alternative to the Dawes-Redman criteria. The assessment of shortterm variations (STV) and long-term variations (LTV) was found to be of use in diagnosing fetal compromise. These variables used in CTG monitors are known as the most evident markers of fetal distress [4, 9]. But the duration of the recording should be not less than 1 hour or, at least, 30 minutes. This time interval is known to be associated with better sleep/awake fetal status ratio [2, 4]. Therefore, the application of the proposed fetal HRV variables will help to use fetal noninvasive ECG tracing of the only 10 minutes long. It will be more convenient in clinical practice. Another advantage is the possibility to support or neglect fetal distress in case of negative (areactive) or false-negative nonstress test.

The hypothesis of the intrauterine programming of the diseases determines that any abnormalities during fetal life will have a subsequent clinical manifestation afterward. The cardiac signals proceeding is a convenient approach to the assessment of fetal autonomic maturation [6, 13]. Fetal HRV variables are disturbed in growth-restricted fetuses. Therefore, the investigation of fetal neurobehavioral response in case of intrauterine growth restriction is a possible way for the fetal well-being screening. But fetal growth restriction is not always associated with fetal distress and still stimulating obstetrical aggression in its projections on the term and the mode of delivery. That is why the outcome of our research in future is an advanced protocol of management of pregnant women with fetal growth restriction.

The findings of this work are based on fetal noninvasive ECG investigation. This method is still a challenge for the clinician [9]. The main problem is a low signal-to-noise ratio [1]. But fetal noninvasive ECG could be used for fetal Holter monitoring. The possibility for the creation of the system for fetal wireless distant monitoring will contribute to the better diagnosing of fetal compromise and cardiac arrhythmias.

HRV and CTG proposed descriptors can be used in an assessment system, for discrimination or prediction between fetuses with loss of fetal well-being and normal fetuses, both in pregnancies with intrauterine growth restriction and pregnancies of healthy fetuses.

Finally, a system based on fuzzy logic was designed with these descriptors in order to obtain an evaluation of the fetal well-being status. Only one false negative was obtained in the diagnosis using 188 data, which represents an accuracy of 98.8% in fetal distress prediction, and 100% in healthy pregnancy.

#### Author details

Igor V. Lakhno<sup>1</sup> , Bertha Patricia Guzmán-Velázquez1,2\* and José Alejandro Díaz-Méndez1,2

\*Address all correspondence to: pguzman@inaoep.mx

1 Obstetrics and Gynecology Department of Kharkiv Medical Academy of Postgraduate Education, Kharkiv, Ukraine

2 Electronics Department of National Institute of Astrophysics, Optics and Electronics, Puebla, México

#### References


**Section 3**

**Biomedical Images Analysis**
