Chunci Medical, an innovative Chinese medical‑device enterprise, globally launched its Lingxi™ Intelligent Intraosseous Puncture System. Centered on an intelligent puncture needle embedded with miniature six‑dimensional force/torque sensors and a fibre‑optic ranging module, the system provides real‑time feedback on resistance changes, insertion angle and depth during puncture. Data is synchronised via Bluetooth to tablet computers or emergency‑vehicle terminals to generate visualised "puncture curves". Clinical studies verify that the system shortens the operational learning curve by 70 % and raises the first‑attempt puncture success rate among junior physicians under guidance to 97 %, equivalent to that of senior specialists.

R&D Background and Clinical Pain Points

Conventional intraosseous puncture is essentially a "black‑box" procedure: operators judge whether the tip has entered the medullary cavity purely by tactile sensation ("give‑way feeling"), leading to significant uncertainty. Major pain points include:

  Steep learning curve: Novices struggle to master tactile feedback, requiring lengthy training and extensive practice using animal bones or simulators.

  Risk of complications: Excessively deep puncture may damage posterior bone tissues (e.g., injuring the epiphyseal plate or penetrating the posterior sternal wall); poor puncture angles may cause needle slippage or impaired infusion.

  Lack of procedural recording: Puncture processes cannot be objectively recorded or reviewed, hindering quality improvement and clinical training.Against the backdrop of medical digitalisation, intraosseous (IO) technology has severely lagged in data‑driven transformation.

Core Technological Innovations

The manufacturer's core innovation lies in equipping conventional puncture needles with sensing and connectivity capabilities:

  Miniaturised sensor integration: MEMS (Micro‑Electro‑Mechanical Systems) sensors are embedded inside the puncture‑needle handle to monitor axial force and rotational torque in real time during insertion. Fibre Bragg gratings detect subtle spectral shifts reflected as the tip penetrates different tissue layers (skin, subcutaneous tissue, bone cortex, medullary cavity), enabling precise tip‑position identification.

  Data visualisation and algorithm interpretation: The supporting app converts sensor data into real‑time scrolling "resistance‑depth" curves. When characteristic sharp rises (bone‑cortex contact) and sudden drops (medullary‑cavity entry) appear, the system triggers visual and tactile (handle vibration) alerts. Algorithms also estimate bone density from initial resistance and intelligently recommend optimal rotation speeds.

  Cloud connectivity and quality‑control platform: Anonymised data from each puncture (duration, force curves, outcomes) is uploaded to hospital quality‑control platforms or the manufacturer's cloud database for cross‑sectional comparison, operational standard audits, and personalised skill‑improvement reports.

Mechanism of Action

By converting mechanical signals into visualised information, the intelligent system establishes a new human‑machine collaboration model:

Six‑dimensional force sensors act as "digital nerves" for operators, quantifying intangible tactile feedback into precise values in Newtons (N) and Newton‑metres (N·m). Operators can "see" excessive applied force or angular deviation.

Fibre‑optic ranging functions similarly to optical radar, calculating real‑time tip depth within tissues at sub‑millimetre precision by analysing optical signals emitted and reflected from the tip, fundamentally eliminating risks of overly deep blind puncture.

Through machine learning on massive datasets of successful and failed punctures, data algorithms identify mechanical‑feature patterns of optimal puncture and issue real‑time warnings when operators apply improper force (e.g., excessive rotation causing thermal bone injury).

Efficacy Validation

A multicentre randomised controlled trial of the system was conducted in emergency departments and ICUs of 15 Grade‑A tertiary hospitals across China.

  Teaching efficacy study: When trained with the intelligent system, medical students and resident physicians reduced average practice attempts required for independent competent operation from 50 to 15, significantly accelerating skill acquisition.

  Safety‑improvement study: No severe complications caused by over‑penetration occurred in 1 000 intelligent‑system‑assisted punctures, whereas 3 cases of mild haematoma or extravasation at puncture sites were recorded in the conventional group (500 cases).

  Decision‑support study: For hard‑to‑puncture obese patients (BMI > 35), the intelligent system identified abnormal resistance curves to pre‑emptively warn of 5 potential bone anomalies or inappropriate puncture‑site selections, guiding operators to switch sites and achieving 100 % successful access establishment.

R&D Strategy and Philosophy

Chunci Medical's R&D strategy is "Data defines standards, intelligence empowers clinical practice". The company believes that in the AI era, the "gold standard" for medical procedures should no longer rely solely on individual expert experience, but on optimised algorithm models trained by massive objective datasets. Partnering with the State Key Laboratory of Artificial Intelligence, it built the world's first intraosseous puncture mechanical‑feature database. Its R&D philosophy emphasises responsible AI: intelligent systems serve to assist and enhance clinical decision‑making rather than replace physicians, with final judgment always remaining with operators.

Future Outlook

Future intelligent puncture systems will evolve into holographic surgical navigation nodes. Manufacturers are exploring integration of intelligent puncture needles with Augmented Reality (AR) glasses: wearing AR glasses, operators view virtually projected optimal puncture points, insertion paths and real‑time 3D insertion animations on the patient's body surface for fluoroscopy‑like operational experience. Furthermore, the system can link with hospital PACS (Picture Archiving and Communication Systems) to automatically retrieve patients' existing X‑ray or CT images for 3D reconstruction and surgical path planning prior to puncture. In the long run, data generated from each intelligent puncture will feed back into the global emergency‑medicine network to predict anatomical variations across populations, ultimately enabling personalised adaptive puncture navigation tailored to individual patients.