We could not find descriptions of epidural catheter placement AI-US assisted in parturient with such high BMI value in the available literature. In the case we present, morphological alterations secondary to pregnancy and obesity created difficulties that could not be overcome using traditional landmark palpation nor standard ultrasound techniques. Nevertheless, the implementation of AI-US has determined the first-step success of the procedure [5].

Preprocedural ultrasound of the patient's lumbar region helps with obtaining important information about spine anatomy: midline identification, optimal vertebral level for catheter placement, the inclination of vertebral bodies and processes and the distance from the skin to the epidural space [6].

Pre-puncture ultrasound is well-known to reduce the number of attempts and significantly increase parturients’ satisfaction in regard to the procedure [7].

This technique is even more helpful when applied in those cases with anticipated difficulty, including anatomical alteration of the lumbar spine and a body mass index (BMI) > 33 kg/m2 [8].

However, neuraxial s-US in pregnancy, especially in obese patients, can be tricky as the visibility of the ligamentum flavum, dura mater, and epidural space decreases significantly during pregnancy. In addition, the distance from the skin to the epidural space seems to increase proportionally to BMI [9].

Becoming familiar with the sonoanatomy of the spinal column requires a high level of technical expertise, so that adoption of neuraxial ultrasound has not been widespread.

In recent years, AI and machine learning-based ultrasound image analysis are gaining momentum as research subjects [4, 5, 10]. These technologies may offer a new advantage in improving outcomes and represent a training aid for operators that are not experienced in neuraxial insonation techniques [4].

Several applications of AI-US have been proposed: automatized identification of organ structures and lesions, assessment of disease status and specific categorization [11]. Two natural fields of implementation of neuraxial AI-US are obstetric and orthopaedic anesthesia. Automated landmark identification programs have been shown effective in identifying needle insertion points in obese pregnant women requiring spinal anaesthesia for cesarean Sect.  [5] as well as in epidural catheter positioning in parturients requesting labor epidural analgesia and in combined spinal–epidural anaesthesia for cesarean delivery, showing positive impact on increasing first-attempt success and shortening procedure's duration [4, 10].

When performing spinal anaesthesia in obese patients undergoing orthopaedic procedures, anesthesiologists needed to redirect the needle fewer times when AI-US was implemented. Of note, interspinous spaces identified as per digital palpation has been shown to be less precise when compared to AI-US; this inconsistency was also particularly evident in our case [12].

In conclusion, benefits brought to the field by AI-US are multiple, all reflected in significantly increased patient satisfaction. In both spinal and epidural anesthesia, AI-US increases efficacy of interspinous space location, reduces needle placement time and predicts needle direction for reaching of target structures as well their distances from skin [13, 14].

Neuroaxial s-US is an advanced skill that relies on the operator for providing accurate results.

When compared to s-US, AI-US provides the clinicians more detailed information that can be pivotal in more complex clinical scenarios. In Table 1 are summarized strengths and core features of both techniques.

There is still much room for improvement and we are far from considering AI-US the standard for neuraxial anaesthesia. When ultrasound became available for practical use at the bedside, it led to a change in our clinical practice, for instance, in the way we look at vascular access and at peripheral nerve blocks. This historical turning point came not smoothly. Clinical trials and accumulation of experience and expertise were needed to make practitioners accept the novelties. We do not know if AI-US will become the new paradigm in neuraxial ultrasound. However, we do think it is a powerful tool we must start considering in our algorithms as well as for further investigations, systematic studies on this subject are warranted.