早产儿神经行为评估及早期干预的研究进展

doi:10.20274/j.cnki.issn.1674-3865.2026.01.002

摘要/Abstract

摘要：

早产儿由于未能经历足月妊娠的关键神经发育阶段，常常面临神经发育障碍的风险。神经行为评估是指通过新生儿运动检查（如自发运动、姿势控制及反射行为）及量表工具（如新生儿行为神经测定、婴儿运动表现测试、全身运动评估等）早期识别发育风险，为临床提供有效的干预依据。多模态早期干预策略包括脱敏治疗、体位管理、听视觉以及运动训练，这些方法能有效改善早产儿在神经可塑性关键期的发育预后。随着科技的进步，人工智能在神经行为评估及早期干预领域的应用日益普遍。人工智能不仅能辅助神经行为评估及早期干预疗法，还有助于建立神经发育随访机制。尽管已有的临床实践显示出显著的效果，但仍需加强多学科协作，以制定更为合理和有效的干预模式，期待在未来实现更完善的早期干预体系，进一步提高早产儿的神经发育预后。

关键词: 早产儿, 神经发育, 神经行为评估, 早期干预, 人工智能

Abstract:

Premature infants often face the risk of neurodevelopmental disorders because they do not complete the key neurodevelopmental stage of full-term pregnancy. Neurobehavioral assessment refers to the early identification of developmental risks through neonatal motor examination (such as spontaneous movement, postural control and reflex behavior) and scale tools (such as NBNA, TIMP, GMS, etc.), which can provide effective intervention basis for clinical practice. Multimodal early intervention strategies, including desensitization therapy, postural management, audiovisual and exercise training, can effectively improve the developmental prognosis of premature infants in the critical period of neuroplasticity. With the progress in science and technology, artificial intelligence (AI) has been widely used in the field of neurobehavioral assessment and early intervention. AI can not only assist neurobehavioral assessment and early intervention therapy, but also help to establish the system of neurodevelopmental follow-up. Although the existing clinical practice has shown significant results, it is still necessary to strengthen multidisciplinary collaboration to develop a more reasonable and effective intervention model. It is expected to achieve a more perfect early intervention system in the future to further improve the neurodevelopmental prognosis of premature infants.

Key words: Premature infants, Neurodevelopment, Neurobehavioral assessment, Early intervention, Artificial intelligence

中图分类号:

R722.6

曲丹阳, 王雨倩, 杨柳. 早产儿神经行为评估及早期干预的研究进展[J]. 中国中西医结合儿科学, 2026, 18(1): 6-11.

Danyang QU, Yuqian WANG, Liu YANG. Research advances in neurobehavioral assessment and early intervention for preterm infants[J]. Chinese Pediatrics of Integrated Traditional and Western Medicine, 2026, 18(1): 6-11.

参考文献 52

[1]	Deng K, Liang J, Mu Y, et al. Preterm births in China between 2012 and 2018: an observational study of more than 9 million women[J]. Lancet Glob Health， 2021，9(9):e1226-1241.
[2]	Geuens S, Goemans N, Lemiere J, et al. Duchenne muscular dystrophy-associated neurobehavioral difficulties: insights from clinical practice[J]. J Neuromuscul Dis, 2024, 11(4): 791-799.
[3]	Malak R, Wiecheć K, Fechner B, et al. The influence of parent education on the neurobehavior and sucking reflexes of very preterm infants[J]. Brain Sci, 2022, 12(7): 840.
[4]	Merritt VC, Brickell TA, Bailie JM, et al. Low resilience following traumatic brain injury is strongly associated with poor neurobehavioral functioning in U.S. military service members and veterans[J]. Brain Inj, 2022, 36(3): 339-352.
[5]	Grabill M, Smith J, Ibrahim C, et al. Prevalence of early feeding alterations among preterm infants and their relationship to early neurobehavior[J]. Am J Occup Ther, 2023, 77(3): 7703205170.
[6]	Mercuri E, Pera MC, Brogna C. Neonatal hypotonia and neuromuscular conditions[J]. Handb Clin Neurol, 2019, 162: 435-448.
[7]	Hadders-Algra M. General movements: a window for early identification of children at high risk for developmental disorders[J]. J Pediatr, 2004, 145(2 ): S12-18.
[8]	Sohn M, Ahn Y, Lee S. Assessment of primitive reflexes in high-risk newborns[J]. J Clin Med Res, 2011, 3(6): 285-290.
[9]	Perez-Pereira M, Fernandez P, Gómez-Taibo M, et al. Neurobehavioral development of preterm and full term children: biomedical and environmental influences[J]. Early Hum Dev, 2013, 89(6): 401-409.
[10]	全国新生儿行为神经科研协作组,全国新生儿生长发育科研协作组. 中国12城市正常新生儿20项行为神经评价[J]. 中华儿科杂志,1990,28(3):160-162.
[11]	张腾伟,林法涛,宋燕燕,等.晚期早产儿早期智能发育结局的研究[J].中国当代儿科杂志,2017,19(2):142-146.
[12]	Campbell SK, Hedeker D. Validity of the Test of Infant Motor Performance for discriminating among infants with varying risk for poor motor outcome[J]. J Pediatr, 2001, 139(4): 546-551.
[13]	Madayi A, Shi L, Zhu Y, et al. The Test of Infant Motor Performance (TIMP) in very low birth weight infants and outcome at two years of age[J]. J Perinatol, 2021, 41(10): 2432-2441.
[14]	Pires CDS, Marba STM, Caldas JPS, et al. Predictive value of the general movements assessment in preterm infants: a meta-analysis[J]. Rev Paul Pediatr, 2020, 38: e2018286.
[15]	Yang L, Bao Z, Zhang L, et al. Position management on pulmonary function and bronchopulmonary dysplasia in premature infants: study protocol for a randomised controlled trial[J]. BMJ Open, 2022, 12(12): e062291.
[16]	Skelton H, Psaila K, Schmied V, et al. Systematic review of the effects of positioning on nonautonomic outcomes in preterm infants[J]. J Obstet Gynecol Neonatal Nurs, 2023, 52(1): 9-20.
[17]	Gözen D, Erkut Z, Uslubaş R, et al. Effect of different positions on gastric residuals in preterm infants initiating full enteral feeding[J]. Nutr Clin Pract, 2022, 37(4): 945-954.
[18]	Sweeney JK, Gutierrez T. Musculoskeletal implications of preterm infant positioning in the NICU[J]. J Perinat Neonatal Nurs, 2002, 16(1): 58-70.
[19]	Gomes ELFD, Santos CMD, Santos ADCS, et al. Autonomic responses of premature newborns to body position and environmental noise in the neonatal intensive care unit[J]. Rev Bras Ter Intensiva, 2019, 31(3): 296-302.
[20]	He F, Wu N, Ma X, et al. The effects of early combined training on the physical development of preterm infants with different gestational ages[J]. Front Pediatr, 2023, 11: 1066751.
[21]	Filippa M, Della Casa E, D’Amico R, et al. Effects of early vocal contact in the neonatal intensive care unit: study protocol for a multi-centre, randomised clinical trial[J]. Int J Environ Res Public Health, 2021, 18(8): 3915.
[22]	Aita M, De Clifford Faugère G, Lavallée A, et al. Effectiveness of interventions on early neurodevelopment of preterm infants: a systematic review and meta-analysis[J]. BMC Pediatr, 2021, 21(1): 210.
[23]	Perra O, Wass S, McNulty A, et al. Training attention control of very preterm infants: protocol for a feasibility study of the Attention Control Training (ACT)[J]. Pilot Feasibility Stud, 2020, 6: 17.
[24]	Zeraati H, Nasimi F, Rezaeian A, et al. Effect of multi-sensory stimulation on neuromuscular development of premature infants: a randomized clinical trial[J]. Iran J Child Neurol, 2018, 12(3): 32-39.
[25]	Aleman AC, Wang M, Schaeffel F. Reading and myopia: contrast polarity matters[J]. Sci Rep, 2018, 8(1): 10840.
[26]	Nist MD, Pickler RH, Harrison TM, et al. Inflammatory predictors of neurobehavior in very preterm infants[J]. Early Hum Dev, 2020, 147: 105078.
[27]	Helmer CS, Thornberg UB, Mörelius E. An early collaborative intervention focusing on parent-infant interaction in the neonatal period. A descriptive study of the developmental framework[J]. Int J Environ Res Public Health, 2021, 18(12): 6656.
[28]	Wang Y, Zhao T, Zhang Y, et al. Positive effects of kangaroo mother care on long-term breastfeeding rates, growth, and neurodevelopment in preterm infants[J]. Breastfeed Med, 2021, 16(4): 282-291.
[29]	Clarke-Sather AR, Compton C, Roberts K, et al. Systematic review of kangaroo care duration’s impact in neonatal intensive care units on infant-maternal health[J]. Am J Perinatol, 2024, 41(8): 975-987.
[30]	Sivanandan S, Sankar MJ. Kangaroo mother care for preterm or low birth weight infants: a systematic review and meta-analysis[J]. BMJ Glob Health, 2023, 8(6): e010728.
[31]	Le Ray I, Kuhn P, Letouzey M, et al. Early skin-to-skin contact and risk of late-onset-sepsis in very and extremely preterm infants[J]. Pediatr Res, 2023, 93(7): 2091-2100.
[32]	Salim N, Shabani J, Peven K, et al. Kangaroo mother care: en-BIRTH multi-country validation study[J]. BMC Pregnancy Childbirth, 2021, 21(): 231.
[33]	Soleimani F, Azari N, Ghiasvand H, et al. Do NICU developmental care improve cognitive and motor outcomes for preterm infants? A systematic review and meta-analysis[J]. BMC Pediatr, 2020, 20(1): 67.
[34]	Goss KN, Lovering AT. Exercise training improves exercise capacity in preterm-born adults: lessons for clinical trials[J]? Am J Respir Crit Care Med, 2023, 207(9): 1124-1125.
[35]	Guimarães EL, Tudella E. Immediate effect of training at the onset of reaching in preterm infants: randomized clinical trial[J]. J Mot Behav, 2015, 47(6): 535-549.
[36]	Sullivan BA, Beam K, Vesoulis ZA, et al. Transforming neonatal care with artificial intelligence: challenges, ethical consideration, and opportunities[J]. J Perinatol, 2024, 44(1): 1-11.
[37]	Shin HI, Shin HI, Bang MS, et al. Deep learning-based quantitative analyses of spontaneous movements and their association with early neurological development in preterm infants[J]. Sci Rep, 2022, 12(1): 3138.
[38]	Ye DH, Kim TW, Kim SM, et al. Can AI-based video analysis help evaluate the performance of the items in the bayley scales of infant development[J]? Children(Basel), 2025, 12(3): 276.
[39]	Razak A, Johnston E, Sackett V, et al. Early neurodevelopmental assessments for predicting long-term outcomes in infants at high risk of cerebral palsy[J]. JAMA Netw Open, 2024, 7(5): e2413550.
[40]	Bruschetta R, Caruso A, Micai M, et al. Marker-less video analysis of infant movements for early identification of neurodevelopmental disorders[J]. Diagnostics(Basel), 2025, 15(2): 136.
[41]	Nichols JK, Sena MP, Hu JL, et al. A kinect-based movement assessment system: marker position comparison to vicon[J]. Comput Methods Biomech Biomed Engin, 2017, 20(12): 1289-1298.
[42]	Passmore E, Kwong AL, Greenstein S, et al. Automated identification of abnormal infant movements from smart phone videos[J]. PLoS Digit Health, 2024, 3(2): e0000432.
[43]	Kulvicius T, Zhang D, Poustka L, et al. Deep learning empowered sensor fusion boosts infant movement classification[J]. Commun Med(Lond), 2025, 5(1): 16.
[44]	Baker S, Kandasamy Y. Machine learning for understanding and predicting neurodevelopmental outcomes in premature infants: a systematic review[J]. Pediatr Res, 2023, 93(2): 293-299.
[45]	魏鑫鑫,吕智海.机器人辅助步行训练对脑性瘫痪患儿影响的研究进展[J].中国中西医结合儿科学,2024,16(2):107-113.
[46]	Costantini S, Falivene A, Chiappini M, et al. Artificial intelligence tools for engagement prediction in neuromotor disorder patients during rehabilitation[J]. J Neuroeng Rehabil, 2024, 21(1): 215.
[47]	Žarković D, Šorfová M, Tufano JJ, et al. Gait changes following robot-assisted gait training in children with cerebral palsy[J]. Physiol Res, 2021, 70(S3): S397-408.
[48]	Mataki Y, Mutsuzaki H, Kamada H, et al. Effect of the hybrid assistive limb on the gait pattern for cerebral palsy[J]. Medicina(Kaunas), 2020, 56(12): 673.
[49]	Aycardi LF, Cifuentes CA, Múnera M, et al. Evaluation of biomechanical gait parameters of patients with Cerebral Palsy at three different levels of gait assistance using the CPWalker[J]. J Neuroeng Rehabil, 2019, 16(1): 15.
[50]	Bayón C, Lerma S, Ramírez O, et al. Locomotor training through a novel robotic platform for gait rehabilitation in pediatric population: short report[J]. J Neuroeng Rehabil, 2016, 13(1): 98.
[51]	Zhang-James Y, Razavi AS, Hoogman M, et al. Machine learning and MRI-based diagnostic models for ADHD: are we there yet[J]? J Atten Disord, 2023, 27(4): 335-353.
[52]	van Boven MR, Bennis FC, Onland W, et al. Machine learning models for neurocognitive outcome prediction in preterm born infants[J]. Pediatr Res, 2025, 98(3): 942-949.