Unsupervised denoising of the non-invasive fetal electrocardiogram with sparse domain Kalman filtering and vectorcardiographic loop alignment.

Even though the electrocardiogram (ECG) has potential to be used as a monitoring or diagnostic tool for fetuses, the use of non-invasive fetal ECG is complicated by relatively high amounts of noise and fetal movement during the measurement. Moreover, machine learning-based solutions to this problem struggle with the lack of clean reference data, which is difficult to obtain. To solve these problems, this work aims to incorporate fetal rotation correction with electrocardiogram denoising into a single unsupervised end-to-end trainable method. This method uses the vectorcardiogram (VCG), a 3-dimensional representation of the ECG, as an input and extends the previously introduced Kalman-LISTA method with a Kalman filter for the estimation of fetal rotation, applying denoising to the rotation-corrected VCG. The resulting method was shown to outperform denoising auto-encoders by more than 3dB while achieving a rotation tracking error of less than 33°. Furthermore, the method was shown to be robust to a difference in signal to noise ratio between electrocardiographic leads and different rotational velocities. Future work should aim at improving the method's generalizability and evaluation of the method's value in research and clinical use. This value might not only derive from the denoised fetal ECG, but from the method's objective measure for fetal rotation as well due to it's potential for early detection of fetal complications.

Artificial intelligence based cardiotocogram assessment during labor.

OBJECTIVE: To assess whether artificial intelligence, inspired by clinical decision-making procedures in delivery rooms, can correctly interpret cardiotocographic tracings and distinguish between normal and pathological events. STUDY DESIGN: A method based on artificial intelligence was developed to determine whether a cardiotocogram shows a normal response of the fetal heart rate to uterine activity (UA). For a given fetus and given the UA and previous FHR, the method predicts a fetal heart rate response, under the assumption that the fetus is still in good condition and based on how that specific fetus has responded so far. We hypothesize that this method, when having only learned from fetuses born in good condition, is incapable of predicting the response of a compromised fetus or an episode of transient fetal distress. The (in)capability of the method to predict the fetal heart rate response would then yield a method that can help to assess fetal condition when the obstetrician is in doubt. Cardiotocographic data of 678 deliveries during labor were selected based on a healthy outcome just after birth. The method was trained on the cardiotocographic data of 548 fetuses of this group to learn their heart rate response. Subsequently it was evaluated on 87 fetuses, by assessing whether the method was able to predict their heart rate responses. The remaining 43 cardiotocograms were segment-by-segment annotated by three experienced gynecologists, indicating normal, suspicious, and pathological segments, while having access to the full recording and neonatal outcome. This future knowledge makes the expert annotations of a quality that is unachievable during live interpretation. RESULTS: The comparison between abnormalities detected by the method (only using past and present input) and the annotated CTG segments by gynecologists (also looking at future input) yields an area under the curve of 0.96 for the distinction between normal and pathological events in majority-voted annotations. CONCLUSION: The developed method can distinguish between normal and pathological events in near real-time, with a performance close to the agreement between three gynecologists with access to the entire CTG tracing and fetal outcome. The method has a strong potential to support clinicians in assessing fetal condition in clinical practice.

Point-of-care therapeutic drug monitoring of tumour necrosis factor-α inhibitors using a single step immunoassay.

Therapeutic drug monitoring (TDM) of tumor necrosis factor-α (TNFα)-inhibitors adalimumab and infliximab is important to establish optimal drug dose and maximize treatment efficacy. Currently, TDM is primarily performed with ELISA techniques in clinical laboratories, resulting in a long sample-to-result workflow. Point-of-care (POC) detection of these therapeutic antibodies could significantly decrease turnaround times and allow for user-friendly home-testing. Here, we adapted the recently developed bioluminescent dRAPPID (dimeric Ratiometric Plug-and-Play Immunodiagnostics) sensor platform to allow POC TDM of infliximab and adalimumab. We applied the two best performing dRAPPID sensors, with limit-of-detections of 1 pM and 17 pM, to measure the infliximab and adalimumab levels in 49 and 40 patient serum samples, respectively. The analytical performance of dRAPPID was benchmarked with commercial ELISAs and yielded Pearson's correlation coefficients of 0.93 and 0.94 for infliximab and adalimumab, respectively. Furthermore, a dedicated bioluminescence reader was fabricated and used as a readout device for the TDM dRAPPID sensors. Subsequently, infliximab and adalimumab patient serum samples were measured with the TDM dRAPPID sensors and bioluminescence reader, yielding Pearson's correlation coefficients of 0.97 and 0.86 for infliximab and adalimumab, respectively, and small proportional differences with ELISA (slope was 0.97 ± 0.09 and 0.96 ± 0.20, respectively). The adalimumab and infliximab dRAPPID sensors, in combination with the dedicated bioluminescence reader, allow for ease-of-use TDM with a fast turnaround time and show potential for POC TDM outside of clinical laboratories.

Fetal electrocardiography and artificial intelligence for prenatal detection of congenital heart disease.

INTRODUCTION: This study aims to investigate non-invasive electrocardiography as a method for the detection of congenital heart disease (CHD) with the help of artificial intelligence. MATERIAL AND METHODS: An artificial neural network was trained for the identification of CHD using non-invasively obtained fetal electrocardiograms. With the help of a Bayesian updating rule, multiple electrocardiographs were used to increase the algorithm's performance. RESULTS: Using 122 measurements containing 65 healthy and 57 CHD cases, the accuracy, sensitivity, and specificity were found to be 71%, 63%, and 77%, respectively. The sensitivity was however 75% and 69% for CHD cases requiring an intervention in the neonatal period and first year of life, respectively. Furthermore, a positive effect of measurement length on the detection performance was observed, reaching optimal performance when using 14 electrocardiography segments (37.5 min) or more. A small negative trend between gestational age and accuracy was found. CONCLUSIONS: The proposed method combining recent advances in obtaining non-invasive fetal electrocardiography with artificial intelligence for the automatic detection of CHD achieved a detection rate of 63% for all CHD and 75% for critical CHD. This feasibility study shows that detection rates of CHD might improve by using electrocardiography-based screening complementary to the standard ultrasound-based screening. More research is required to improve performance and determine the benefits to clinical practice.