AI in evaluating ambulation of stroke patients: severity classification with video and functional ambulation category scale.

BACKGROUND: The evaluation of gait function and severity classification of stroke patients are important to determine the rehabilitation goal and the level of exercise. Physicians often qualitatively evaluate patients' walking ability through visual gait analysis using naked eye, video images, or standardized assessment tools. Gait evaluation through observation relies on the doctor's empirical judgment, potentially introducing subjective opinions. Therefore, conducting research to establish a basis for more objective judgment is crucial. OBJECTIVE: To verify a deep learning model that classifies gait image data of stroke patients according to Functional Ambulation Category (FAC) scale. METHODS: Gait vision data from 203 stroke patients and 182 healthy individuals recruited from six medical institutions were collected to train a deep learning model for classifying gait severity in stroke patients. The recorded videos were processed using OpenPose. The dataset was randomly split into 80% for training and 20% for testing. RESULTS: The deep learning model attained a training accuracy of 0.981 and test accuracy of 0.903. Area Under the Curve(AUC) values of 0.93, 0.95, and 0.96 for discriminating among the mild, moderate, and severe stroke groups, respectively. CONCLUSION: This confirms the potential of utilizing human posture estimation based on vision data not only to develop gait parameter models but also to develop models to classify severity according to the FAC criteria used by physicians. To develop an AI-based severity classification model, a large amount and variety of data is necessary and data collected in non-standardized real environments, not in laboratories, can also be used meaningfully.

Deep learning model for classifying shoulder pain rehabilitation exercises using IMU sensor.

BACKGROUND: Artificial intelligence is being used for rehabilitation, including monitoring exercise compliance through sensor technology. AI classification of shoulder exercise wearing an IMU sensor has only been reported in normal (i.e. painless) subjects. To prove the feasibility of monitoring exercise compliance, we aimed to classify 11 types of shoulder rehabilitation exercises using an AI (artificial intelligence) algorithm in patients with shoulder pain. We had the patients wear an IMU-based sensor, collected data during exercise, and determined the accuracy of exercise classification. METHODS: Data were collected from 58 patients (27 males, 31 females, age range 37-82 years) diagnosed with shoulder diseases such as adhesive capsulitis and rotator cuff disease. 11 types of shoulder pain rehabilitation exercise programs were developed and repeated each exercise ten times per session while wearing an IMU sensor. The study applied the Rectified Linear Unit (ReLU) and the SoftMax as the activation function for hidden layers, the output layer. RESULTS: The acquired data was used to train a DNN model using the multilayer perceptron algorithm. The trained model was used to classify 11 types of shoulder pain rehabilitation exercises. The training accuracy was 0.975 and the test accuracy was 0.925. CONCLUSION: The study demonstrates that IMU sensor data can effectively classify shoulder pain rehabilitation exercises, providing more appropriate feedback for patients. The model can be utilized to establish a system for remotely monitoring patients' exercise performance. The use of deep learning in patient monitoring and rehabilitation has significant potential to bring innovative changes to healthcare service delivery.

Dietary Supplementation With a Bacillus Superoxide Dismutase Protects Against γ-Radiation-induced Oxidative Stress and Ameliorates Dextran Sulphate Sodium-induced Ulcerative Colitis in Mice.

BACKGROUND AND AIMS: Commercial superoxide dismutase [SOD] is derived from melon extract and has a potential as a dietary supplement due to its beneficial antioxidative effects. We aimed to improve the productivity of SOD compared with plant SOD by using a generally regarded as safe [GRAS] microorganism, Bacillus amyloliquefaciens, and assess its antioxidative effect using γ-radiation- and dextransulphate sodium [DSS]-induced oxidative models in mice. METHODS: We identified the sodA gene encoding manganese-containing SODs [Mn-SOD] in B. amyloliquefaciens, constructed a Mn-SOD deficient mutant, and screened a high-SOD-producing strain. We compared the antioxidative effect of orally administered enteric-coated SOD protein partially purified from B. amyloliquefaciens with wild-type and high-SOD-producing strain spores. The effect of SOD on DSS-induced colitis was also investigated. Colonic inflammation was assessed using disease activity index, macroscopic and histological damage scores, antioxidant enzyme activities, and inflammatory cytokines. RESULTS: The SOD activity of B. amyloliquefaciens is derived from secreted Mn-SOD encoded by the sodA gene, as shown by comparing sodA knock-out mutant spores with wild-type and high-SOD-producing spores. Enteric-coated SOD of B. amyloliquefaciens appears to be effective in reducing oxidative stress in γ-radiation- and DSS-induced mouse models. Co-administration of SOD with wild-type B. amyloliquefaciens or high-SOD-producer strain spores showed a synergistic effect. SOD enzyme and B. amyloliquefaciens spores contribute to the reduction of oxidative stress and inflammatory response in DSS-induced colitis. CONCLUSIONS: Mn-SOD of B. amyloliquefaciens could be another source of SOD supplement and may be useful to prevent and treat ulcerative colitis.

Purification, Characterization, and Cloning of a Cold-Adapted Protease from Antarctic Janthinobacterium lividum.

In this study, a 107 kDa protease from psychrophilic Janthinobacterium lividum PAMC 26541 was purified by anion-exchange chromatography. The specific activity of the purified protease was 264 U/mg, and the overall yield was 12.5%. The J. lividum PAMC 25641 protease showed optimal activity at pH 7.0-7.5 and 40°C. Protease activity was inhibited by PMSF, but not by DTT. On the basis of the N-terminal sequence of the purified protease, the gene encoding the cold-adapted protease from J. lividum PAMC 25641 was cloned into the pET-28a(+) vector and heterologously expressed in Escherichia coli BL21(DE3) as an intracellular soluble protein.

Intracorneal melatonin delivery using 2-hydroxypropyl-ß-cyclodextrin ophthalmic solution for granular corneal dystrophy type 2.

Melatonin (MT), an effective antioxidant, has therapeutic implications for granular corneal dystrophy type 2 (GCD2) treatment. Eye drop formulations containing cyclodextrins (CDs) were studied with the objective of improving MT solubility, stability, and ocular absorption, while decreasing eye irritation. MT complexes with αCD, ßCD, γCD, and 2-hydroxypropyl-ßCD (HPßCD) were characterized by phase solubility studies, which demonstrated Higuchi's AL-type phase solubility profiles. The MT/HPßCD complex showed the highest MT solubility (2.75mg/mL). Ocular irritation experiments showed HPßCD inclusion alleviated irritation of the eye. After administration of MT formulations to rabbit corneas, each harvested cornea was separated into corneal epithelium, stroma, and endothelium. MT concentrations in the corneal epithelium, stroma, and endothelium for the F1-treated group were 55.5±9.24, 26.7±2.66, and 21.1±1.77µM while those for the F2-treated group were 127.2±21.01, 43.7±16.93, and 51.0±13.91µM, respectively. Stability studies for 60days showed no significant change in pH, osmolarity, and MT content. In conclusion, MT/HPßCD formulations can lower irritation, enhance MT stability, and improve therapeutic efficacy.

Case series of non-small cell lung cancer treated with mountain Ginseng pharmacopuncture.

This study aims to observe the efficacy of mountain Ginseng (Panax ginseng C.A. Meyer) pharmacopuncture (MGP) on cancer patients using different delivery methods of acupoint injection and intravenous infusion. Six non-small cell lung cancer (NSCLC) patients who met the eligibility criteria were observed. Two patients were continuously infused with MGP (20 mL/day) intravenously, and the other two patients were injected with MGP (10 mL/day) on acupoint LU1 bi-lateral continuously. The remaining two patients received MGP therapy using both methods of delivery. Results were followed by computed tomography (CT) after every cycle; each cycle lasted for 28 days. Two patients infused intravenously showed stable disease and two patients injected on LU1 showed progressive disease. Two patients treated using both methods showed stable disease during the intravenous infusion period and progressive disease during the intraacupuncture injection period. One patient showed progressive disease in the latest chest CT in spite of receiving MGP intravenous infusion. We suggested that MGP may be more effective when used as an intravenous infusion rather than acupoint injection in NSCLC patients.