Using AI Systems to Optimize the Clinical Outcome of Stroke Patients

Patients will receive 12 weeks of acupuncture with 3 half-hour sessions weekly. Acupoints will include (1) a basic formula of 8 Bo's abdomen acupoints (paretic side, 0.5cm depth vertically) \[66\]; (2) 12 conventional acupoints (bilateral, opposite to paretic side first, 1-4 cm depth vertically) \[67\]; and (3) 3 scalp acupoints (opposite to paretic side, 0.5-cm depth at 15-30 degrees) \[68\]At most 3 additional supplementary acupoints will be included, depending on the clinician's professional judgement. Sterile needles will be used after skin disinfection. Manual rotating manipulation \[69\] will be performed every 10 minutes on the conventional acupoints to achieve De-qi sensation \[70\]. Abdomen and scalp acupoints do not require De-qi. Subjects will be monitored throughout the course of therapy with face-to-face assessments by blinded and trained clinicians after 0, 4, 8, 12 weeks of intervention. Clinical scales will also be recorded at 0 (A0), 8 (A½), and 12 weeks (A1).

Subjects in this group will receive the typical post-stroke care offered to stroke survivors of Hong Kong. This care emphasizes restoring function and independence through a comprehensive approach. Physical therapy focuses on improving mobility with exercises and training; occupational therapy helps patients relearn essential daily living skills, facilitating a smooth transition back to everyday life. Speech therapy is integral for addressing communication challenges, and psychological support is provided to help patients manage the emotional impact of stroke. All subjects will receive the above care for 8 weeks (≥3 hourly sessions per week). Clinical scales will be recorded at 0 (A0), 4 (A½), and 8 weeks (A1).

For this treatment group, CMC (corticomuscular coherence)-EMG-triggered control will assist wrist extension with hand open and wrist flexion with hand close alternately by mechanical pneumatic support \[60\]. During wrist-hand extension, the pneumatic fingers will assist a hand-open motion with constant inflation till the inner pressure reaches 90kPa; during the wrist-hand flexion, the pneumatic fingers will deflate constantly to assist a hand-close motion. To trigger ENMS assistance, two criteria must be met: (1) the average EMGs of target muscles exceed a pre-defined threshold, and (2) a significant CMC peak value with peak frequency in the beta band is captured. Here, the target muscle groups will be the extensor digitorum and extensor carpi ulnaris (ED-ECU) and flexor digitorum and flexor carpi radialis (FD-FCR), and the EMG and CMC will be evaluated during sustained contraction of these muscles over a 3-sec window.

For this treatment group, constant NMES (70V, 40Hz, 0-300µs square wave bursts \[63\]) will be delivered to the ED-ECU and FD-FCR muscles to assist in wrist-hand extension and flexion, respectively. The pulse width of NMES will be individually adjusted to achieve the maximum muscle contraction with the minimum stimulation intensity. The control strategy of CMC-EMG-triggered NMES will be the same as that used in the robot.