Can AI predict walking independence in patients with stroke upon admission to a recovery-phase rehabilitation ward?

Ono K, Takahashi R, Morita K, Ara Y, Abe S, Ito S, Uno S, Abe M, Shirasaka T. Can AI predict walking independence in patients with stroke upon admission to a recovery-phase rehabilitation ward? Jpn J Compr Rehabil Sci 2024; 15: 1-7. Objective: This study aimed to develop a prediction model for walking independence in patients with stroke in the recovery phase at the time of hospital discharge using Prediction One, an artificial intelligence (AI)-based predictive analysis tool, and to examine its utility. Methods: Prediction One was used to develop a prediction model for walking independence for 280 patients with stroke admitted to a rehabilitation ward-based on physical and mental function information at admission. In 134 patients with stroke hospitalized during different periods, accuracy was confirmed by calculating the correct response rate, sensitivity, specificity, and positive and negative predictive values based on the results of AI-based predictions and actual results. Results: The prediction accuracy (area under the curve, AUC) of the proposed model was 91.7%. The correct response rate was 79.9%, sensitivity was 95.7%, specificity was 62.5%, positive predictive value was 73.6%, and negative predictive value was 93.5%. Conclusion: The accuracy of the prediction model developed in this study is not inferior to that of previous studies, and the simplicity of the model makes it highly practical.

Development of a Conversion Table Linking Functional Independence Measure Scores to International Classification of Functioning, Disability, and Health Qualifiers: Insights from a Survey of Healthcare Professionals.

In clinical practice, patient assessments rely on established scales. Integrating data from these scales into the International Classification of Functioning, Disability, and Health (ICF) framework has been suggested; however, a standardized approach is lacking. Herein, we tested a new approach to develop a conversion table translating clinical scale scores into ICF qualifiers based on a clinician survey. The survey queried rehabilitation professionals about which functional independence measure (FIM) item scores (1-7) corresponded to the ICF qualifiers (0-4). A total of 458 rehabilitation professionals participated. The survey findings indicated a general consensus on the equivalence of FIM scores with ICF qualifiers. The median value for each item remained consistent across all item groups. Specifically, FIM 1 had a median value of 4; FIM 2 and 3 both had median values of 3; FIM 4 and 5 both had median values of 2; FIM 6 had a median value of 1; and FIM 7 had a median value of 0. Despite limitations due to the irreconcilable differences between the frameworks of existing scales and the ICF, these results underline the ICF's potential to serve as a central hub for integrating clinical data from various scales.

Stepwise revascularization for prevention of postoperative hyperperfusion.

Abrupt normalization of cerebral blood flow (CBF) after surgical procedures to improve excessive cerebral hypoperfusion can cause irreversible brain parenchymal damage. Such hyperperfusion, which is caused by inflow at normal blood pressure into maximally dilated fine vessels, is an important complication following carotid endarterectomy (CEA). Strict control of blood pressure in the perioperative period can prevent this complication except in a few patients, who have severe cerebral hypoperfusion and poor cerebrovascular reserve due to extremely severe stenosis of the ipsilateral or the bilateral carotid arteries, for which CEA is indicated. The requirement for improved CBF and the risk of postoperative hyperperfusion conflict in the pathogenesis of these patients. We tried to prevent abrupt improvement in perfusion by attempting gradual restoration of CBF. Superficial temporal artery-middle cerebral artery anastomosis was first performed to improve the poor cerebrovascular reserve by allowing insufficient blood flow. A few weeks later, CEA was performed to completely restore CBF. This surgical approach obtained good results without postoperative problems in four patients. The indications of this surgical management and efficacy of stepwise restoration of CBF to prevent postoperative hyperperfusion depend on careful preoperative evaluation of perfusion studies.

Evaluation of carotid distal pressure for prevention of hyperperfusion after carotid endarterectomy.

BACKGROUND: Sometimes preoperative cerebral misery perfusion induces an occurrence of hyperperfusion after carotid endarterectomy (CEA). We intraoperatively measured carotid proximal and distal pressures and evaluated their role in predicting hyperperfusion. METHODS: Twenty-one sites with an indication of CEA were preoperatively assessed based on the bilateral perfusional state of the cerebral blood flow (CBF) and delta CBF by single photon emission computed tomography (SPECT). Postoperative SPECT was performed immediately and on the fifth day after surgery. The distal and proximal pressures were intraoperatively measured through an internal shunt tube, and the evaluated relationship against hyperperfusion was shown on postoperative SPECT. RESULTS: Despite strict control of blood pressure, 7 patients postoperatively showed hyperperfusion on SPECT and 2 of them had transient neurological symptoms. The distal pressure was significantly different between the postoperative hyperperfusion group and the normal one; however, proximal pressure and the difference between proximal and distal pressures were not significantly different. In the hyperperfusion group, delta pressure was apparently higher, and delta CBF and distal pressure were significantly lower than those of the normal group. CONCLUSION: Intraoperative measurement of distal pressure as well as preoperative estimation of the cerebrovascular perfusion and the reserve is of importance in predicting postoperative hyperperfusion.

Repeated thrombus formation immediately following carotid endarterectomy.

A 56-year-old male presented with thrombus formation manifesting as cerebral embolic infarction suspected to be caused by hemostasis at the carotid bifurcation, not by the intimal abnormalities or hematological disorders. Thrombus repeatedly and reproducibly appeared at the same area in spite of carotid endarterectomy (CEA). Ultrasonography demonstrated a stenotic lesion of the cervical carotid bifurcation. Medical treatment reduced the stenosis, but the thrombus was repeatedly formed at the same area of the cervical carotid bifurcation. CEA was performed. Histological examination of the specimen found only the underlying thin intima consisting of mild fibrous atheromatic change without ulceration or vascular dissection. Ultrasonography following CEA showed reduced blood flow, indicating hemostasis, and moyamoya appearance in that area. The thrombus had recurred in spite of the medical treatment with anti-platelet agent. This repeated thrombus was gradually dissolved and reduced with anticoagulant therapy. Thrombus causing cerebral embolic stroke and originating at the cervical carotid bifurcation is usually due to the intimal atherosclerotic change such as ulcer formation or vascular dissection. The thrombus in this case was probably formed by hemostasis at the cervical carotid bifurcation and CEA was not effective to prevent recurrence.

Cilostazol may prevent cerebral vasospasm following subarachnoid hemorrhage.

Cilostazol is an antiplatelet aggregation inhibitor drug associated with increased cerebral blood flow and inflammation suppression. This study evaluated administration of cilostazol to prevent cerebral vasospasm following subarachnoid hemorrhage (SAH) in 50 patients treated surgically from December 2004 to November 2006. All patients, excluding those with Hunt and Kosnik grade 5 or who had undergone late surgery, were classified into two groups: 26 patients who received 200 mg/day cilostazol from postoperative day 1 to day 14 and 24 control patients. The frequency and the degree of cerebral vasospasm, occurrence of ischemic lesion, and clinical symptoms due to vasospasm were compared between the two groups. The appearance of severe vasospasm on angiography, persistent symptomatic spasm, and new cerebral infarction due to vasospasm demonstrated by neuroimaging were apparently lower in the cilostazol group than in the control group, suggesting that cilostazol may significantly suppress cerebral vasospasm following SAH.