{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T10:43:56Z","timestamp":1763981036843,"version":"3.45.0"},"reference-count":47,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: The management of high-risk pregnancies remains a major clinical challenge, particularly regarding the optimal timing of delivery, which has significant implications for both perinatal outcomes and healthcare costs. In this context, computerized cardiotocography (cCTG) offers an objective, non-invasive and cost-effective method for fetal surveillance, providing quantitative measures of heart rate dynamics that reflect autonomic regulation and oxygenation status. This study aimed to develop and validate regression-based machine learning models capable of predicting the duration of neonatal hospitalization\u2014an objective and quantifiable indicator of neonatal well-being\u2014using cCTG parameters obtained outside of labor, binary clinical variables describing the presence or absence of pregnancy pathologies, and gestational age at monitoring and at delivery. Methods: A total of 694 singleton high-risk pregnancies complicated by gestational diabetes, preexisting diabetes, intrahepatic cholestasis of pregnancy, pregnancy-induced or preexisting hypertension, or fetal growth restriction were enrolled. Twenty clinically relevant features derived from cCTG recordings and perinatal data were used to train and evaluate four regression algorithms: Random Forest, CatBoost, XGBoost, and LightGBM against a linear regression model with Ridge regularization serving as a benchmark. Results: Random Forest achieved the highest generalization performance (test R2 = 0.8226; RMSE = 3.41 days; MAE = 2.02 days), outperforming CatBoost (R2 = 0.7059), XGBoost (R2 = 0.6911), LightGBM (R2 = 0.6851) and the linear regression benchmark with Ridge regularization (R2 = 0.5699) while showing a consistent train\u2013validation\u2013test profile (0.9428 \u2192 0.8042 \u2192 0.8226). The error magnitude (\u22482 days on average) is clinically interpretable for neonatal resource planning, supporting the model\u2019s practical utility. These findings justify selecting Random Forest as the final predictor and its integration into a clinician-facing application for real-time length-of-stay estimation. Conclusions: Machine learning models integrating cCTG features with maternal clinical factors can accurately predict neonatal hospitalization duration in pregnancies complicated by maternal or fetal disease. This approach provides a clinically interpretable and non-invasive decision support tool that may enhance delivery planning, optimize neonatal resource allocation, and improve perinatal care outcomes.<\/jats:p>","DOI":"10.3390\/diagnostics15232964","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T10:24:17Z","timestamp":1763979857000},"page":"2964","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prediction of Neonatal Length of Stay in High-Risk Pregnancies Using Regression-Based Machine Learning on Computerized Cardiotocography Data"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1673-7317","authenticated-orcid":false,"given":"Bianca Mihaela","family":"Danciu","sequence":"first","affiliation":[{"name":"Department of Obstetrics and Gynecology, Carol Davila University of Medicine and Pharmacy, 050474 Bucharest, Romania"},{"name":"Department of Obstetrics, Gynecology and Neonatology, National Institute for Maternal and Child Health \u201cAlfred Rusescu\u201d-Polizu, 127715 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria-Elisabeta","family":"\u0218i\u0219ial\u0103","sequence":"additional","affiliation":[{"name":"Department of Applied Informatics, Military Technical Academy \u201cFerdinand I\u201d of Bucharest, 050141 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreea-Ioana","family":"Dumitru","sequence":"additional","affiliation":[{"name":"Department of Applied Informatics, Military Technical Academy \u201cFerdinand I\u201d of Bucharest, 050141 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9334-0199","authenticated-orcid":false,"given":"Anca Angela","family":"Simionescu","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, Carol Davila University of Medicine and Pharmacy, 050474 Bucharest, Romania"},{"name":"Department of Obstetrics and Gynecology, Filantropia Clinical Hospital, 050474 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6724-2336","authenticated-orcid":false,"given":"Bogdan","family":"Sebacher","sequence":"additional","affiliation":[{"name":"Department of Applied Informatics, Military Technical Academy \u201cFerdinand I\u201d of Bucharest, 050141 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ayres-De-Campos, D. (2016). Obstetric Emergencies, Springer.","DOI":"10.1007\/978-3-319-41656-4"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1111\/j.1365-3016.2007.00774.x","article-title":"Co-Occurrence of Birth Defects and Intellectual Disability","volume":"21","author":"Petterson","year":"2007","journal-title":"Paediatr. Perinat. Epidemiol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102","DOI":"10.5455\/medarh.2014.68.102-105","article-title":"Cardiotocography in the Prognosis of Perinatal Outcome","volume":"68","author":"Bogdanovic","year":"2014","journal-title":"Med. Arch."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Klumper, J., Kaandorp, J.J., Schuit, E., Groenendaal, F., Koopman-Esseboom, C., Mulder, E.J.H., Van Bel, F., Benders, M.J.N.L., Mol, B.W.J., and van Elburg, R.M. (2018). Behavioral and Neurodevelopmental Outcome of Children after Maternal Allopurinol Administration during Suspected Fetal Hypoxia: 5-Year Follow-Up of the ALLO-Trial. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0201063"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"18","DOI":"10.4103\/jcls.jcls_102_17","article-title":"Hypoxic-ischemic encephalopathy and the Apgar scoring system: The experience in a resource-limited setting","volume":"15","author":"Aliyu","year":"2018","journal-title":"J. Clin. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"R1","DOI":"10.1152\/ajpregu.00008.2019","article-title":"Current Paradigms and New Perspectives on Fetal Hypoxia: Implications for Fetal Brain Development in Late Gestation","volume":"317","author":"Wood","year":"2019","journal-title":"Am. J. Physiol.\u2014Regul. Integr. Comp. Physiol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1111\/j.1471-0528.1938.tb11169.x","article-title":"The Human Foetal Electrocardiogram","volume":"45","author":"Bell","year":"1938","journal-title":"BJOG Int. J. Obstet. Gynaecol."},{"key":"ref_8","first-page":"CD006066","article-title":"Continuous Cardiotocography (CTG) as a Form of Electronic Fetal Monitoring (EFM) for Fetal Assessment during Labour","volume":"2","author":"Alfirevic","year":"2017","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Danciu, B.M., and Simionescu, A.A. (2025). Optimizing Fetal Surveillance in Fetal Growth Restriction: A Narrative Review of the Role of the Computerized Cardiotocographic Assessment. J. Clin. Med., 14.","DOI":"10.3390\/jcm14197010"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1159\/000327133","article-title":"Intra- and Interobserver Variability of Intrapartum Cardiotocography: A Multicenter Study Comparing the FIGO Classification with Computer Analysis Software","volume":"72","author":"Schiermeier","year":"2011","journal-title":"Gynecol. Obstet. Investig."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Das, S., Mukherjee, H., Roy, K., and Saha, C.K. (2023). Fetal Health Classification from Cardiotocograph for Both Stages of Labor\u2014A Soft-Computing-Based Approach. Diagnostics, 13.","DOI":"10.3390\/diagnostics13050858"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1111\/1471-0528.13208","article-title":"Antenatal Cardiotocogram Quality and Interpretation Using Computers","volume":"121","author":"Dawes","year":"2014","journal-title":"BJOG Int. J. Obstet. Gynaecol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1111\/1471-0528.17669","article-title":"Prediction of Labour Outcomes Using Prelabour Computeried Cardiotocogram and Maternal and Fetal Doppler Indices: A Prospective Cohort Study","volume":"131","author":"Moungmaithong","year":"2024","journal-title":"BJOG"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"112026","DOI":"10.1109\/ACCESS.2019.2933368","article-title":"Multimodal Convolutional Neural Networks to Detect Fetal Compromise during Labor and Delivery","volume":"7","author":"Petrozziello","year":"2019","journal-title":"IEEE Access"},{"key":"ref_15","unstructured":"Zwertbroek, E., Bernardes, T., Mol, B.W., Battersby, C., Koopmans, C., Broekhuijsen, K., and Chappell, L.C. (2024). Clinical Trial Protocol Evaluating Planned Early Delivery Compared to Expectant Management for Women with Pre-Eclampsia between 34 and 36 Weeks\u2019 Gestation in Low- and Lower-Middle-Income Settings. Systematic Review, AJOG.org. Chapter 7."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1053\/j.semperi.2011.05.009","article-title":"Timing Delivery of the Growth-Restricted Fetus","volume":"35","author":"Galan","year":"2011","journal-title":"Semin. Perinatol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1088\/0967-3334\/32\/10\/004","article-title":"Computerized Fetal Heart Rate Analysis in Labor: Detection of Intervals with Un-Assignable Baseline","volume":"32","author":"Georgieva","year":"2011","journal-title":"Physiol. Meas."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Roozbeh, N., Montazeri, F., Farashah, M.V., Mehrnoush, V., and Darsareh, F. (2025). Proposing a Machine Learning-Based Model for Predicting Nonreassuring Fetal Heart. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-92810-2"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Pardasani, R., Vitullo, R., Harris, S., Yapici, H.O., and Beard, J. (2025). Development of a Novel Artificial Intelligence Algorithm for Interpreting Fetal Heart Rate and Uterine Activity Data in Cardiotocography. Front. Digit. Health, 7.","DOI":"10.3389\/fdgth.2025.1638424"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Aeberhard, J.L., Radan, A.P., Soltani, R.A., Strahm, K.M., Schneider, S., Carri\u00e9, A., Lemay, M., Krauss, J., Delgado-Gonzalo, R., and Surbek, D. (2024). Introducing Artificial Intelligence in Interpretation of Foetal Cardiotocography: Medical Dataset Curation and Preliminary Coding\u2014An Interdisciplinary Project. Methods Protoc., 7.","DOI":"10.3390\/mps7010005"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Park, C.E., Choi, B., Park, R.W., Kwak, D.W., Ko, H.S., Seong, W.J., Cha, H.-H., Kim, H.M., Lee, J., and Seol, H.-J. (2025). Automated Interpretation of Cardiotocography Using Deep Learning in a Nationwide Multicenter Study. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-02849-4"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"16753","DOI":"10.1007\/s00521-025-11343-x","article-title":"Early Detection of Fetal Health Status Based on Cardiotocography Using Artificial Intelligence","volume":"37","author":"Ahmed","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"26005","DOI":"10.1109\/ACCESS.2024.3364755","article-title":"Cardiotocography Data Analysis for Fetal Health Classification Using Machine Learning Models","volume":"12","author":"Salini","year":"2024","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kaliappan, J., Bagepalli, A.R., Almal, S., Mishra, R., Hu, Y.-C., and Srinivasan, K. (2023). Impact of Cross-Validation on Machine Learning Models for Early Detection of Intrauterine Fetal Demise. Diagnostics, 13.","DOI":"10.3390\/diagnostics13101692"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"207","DOI":"10.2298\/SJEE2202207J","article-title":"Experimental Analysis of Filtering-Based Feature Selection Techniques for Fetal Health Classification","volume":"19","author":"Jebadurai","year":"2022","journal-title":"Serbian J. Electr. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, J., and Liu, X. (2021, January 26\u201328). Fetal Health Classification Based on Machine Learning. Proceedings of the 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Nanchang, China.","DOI":"10.1109\/ICBAIE52039.2021.9389902"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"102146","DOI":"10.1109\/ACCESS.2020.2999899","article-title":"Performance Analysis of Classification Algorithms on Birth Dataset","volume":"8","author":"Abbas","year":"2020","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Piri, J., and Mohapatra, P. (2019, January 19\u201321). Exploring Fetal Health Status Using an Association Based Classification Approach. Proceedings of the International Conference on Information Technology (ICIT), Bhubaneswar, India.","DOI":"10.1109\/ICIT48102.2019.00036"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"8564","DOI":"10.35940\/ijrte.D4378.118419","article-title":"Weighted Deep Neural Network Based Clinical Decision Support System for the Determination of Fetal Health","volume":"8","author":"Vani","year":"2019","journal-title":"Int. J. Recent Technol. Eng. (IJRTE)"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/978-3-030-34482-5_7","article-title":"Imbalanced Cardiotocography Multi-Classification for Antenatal Fetal Monitoring Using Weighted Random Forest","volume":"11924","author":"Chen","year":"2019","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_31","unstructured":"Uzun, A., Capa-Kiziltas, E., and Yilmaz, E. (2018, January 11\u201313). Cardiotocography Data Set Classification with Extreme Learning Machine. Proceedings of the International Conference on Advanced Technologies, Computer Engineering and Science (ICATCES\u201918), Safranbolu, Turkey."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.asoc.2015.04.038","article-title":"Classification of the Cardiotocogram Data for Anticipation of Fetal Risks Using Machine Learning Techniques","volume":"33","author":"Sahin","year":"2015","journal-title":"Appl. Soft Comput. J."},{"key":"ref_33","first-page":"262","article-title":"Classification of the Cardiotocogram Data for Anticipation of Fetal Risks Using Bagging Ensemble Classifier","volume":"187","author":"Subasi","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"14433","DOI":"10.1007\/s00521-024-09831-7","article-title":"Machine Learning-Based Prediction of Length of Stay (LoS) in the Neonatal Intensive Care Unit Using Ensemble Methods","volume":"36","author":"Yildirim","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_35","unstructured":"Straathof, B.T. (2020). A Deep Learning Approach to Predicting the Length of Stay of Newborns in the Neonatal Intensive Care Unit. [Master\u2019s Thesis, KTH Royal Institute of Technology]. Available online: https:\/\/www.diva-portal.org\/smash\/get\/diva2:1472280\/FULLTEXT01.pdf."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Jain, R., Singh, M., Rao, A.R., and Garg, R. (2024). Predicting Hospital Length of Stay Using Machine Learning on a Large Open Health Dataset. BMC Health Serv. Res., 24.","DOI":"10.1186\/s12913-024-11238-y"},{"key":"ref_37","unstructured":"Gabitashvili, A., and Kellmeyer, P. (2025). Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"De Silva, D.A., Sauve, R., von Dadelszen, P., Synnes, A., Lee, T., and Magee, L.A. (2017). Timing of Delivery in a High-Risk Obstetric Population: A Clinical Prediction Model. BMC Pregnancy Childbirth, 17.","DOI":"10.1186\/s12884-017-1390-9"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"American College of Obstetricians and Gynecologists (ACOG) (2009). Intrapartum Fetal Heart Rate Monitoring: Nomenclature, Interpretation, and General Management Principles. Obstet. Gynecol., 114, 192\u2013202.","DOI":"10.1097\/AOG.0b013e3181aef106"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.ijgo.2015.06.020","article-title":"FIGO consensus guidelines on intrapartum fetal monitoring: Cardiotocography","volume":"131","author":"Spong","year":"2015","journal-title":"Int. J. Gynecol. Obstet."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Malakooti, N., Mehrnoush, V., Abdi, F., Farashah, M.S.V., and Darsareh, F. (2025). Development of a Machine Learning Model to Identify the Predictors of the Neonatal Intensive Care Unit Admission. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-06651-0"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Singh, H., Cho, S.J., Gupta, S., Kaur, R., Sunidhi, S., Saluja, S., Pandey, A.K., Bennett, M.V., Lee, H.C., and Das, R. (2021). Designing a Bed-Side System for Predicting Length of Stay in a Neonatal Intensive Care Unit. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-82957-z"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1111\/j.1600-0412.2011.01138.x","article-title":"Cost-Effectiveness of Cardiotocography Plus ST Analysis of the Fetal Electrocardiogram Compared with Cardiotocography Only","volume":"90","author":"Vijgen","year":"2011","journal-title":"Acta Obstet. Gynecol. Scand."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"3269","DOI":"10.18203\/2320-1770.ijrcog20213439","article-title":"Admission Cardiotocography versus Doppler Auscultation of Fetal Heart in High-Risk Pregnancy in a Tertiary Health Facility in Nigeria","volume":"10","author":"Abbey","year":"2021","journal-title":"Int. J. Reprod. Contracept. Obstet. Gynecol."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1038\/s44294-024-00015-1","article-title":"Saving Babies and Families from Preventable Harm: A Review of the Current State of Fetoplacental Monitoring and Emerging Opportunities","volume":"2","author":"David","year":"2024","journal-title":"NPJ Women\u2019s Health"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Sato, I., Hirono, Y., Shima, E., Yamamoto, H., Yoshihara, K., Kai, C., Yoshida, A., Uchida, F., Kodama, N., and Kasai, S. (2025). Comparison and Verification of Detection Accuracy for Late Deceleration with and without Uterine Contractions Signals Using Convolutional Neural Networks. Front. Physiol., 16.","DOI":"10.3389\/fphys.2025.1525266"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Gupta, A., Stead, T.S., and Ganti, L. (2024). Determining a Meaningful R-Squared Value in Clinical Medicine. Acad. Med. Surg.","DOI":"10.62186\/001c.125154"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/23\/2964\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T10:41:42Z","timestamp":1763980902000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/23\/2964"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"references-count":47,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["diagnostics15232964"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15232964","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,22]]}}}