Search

Objectives Evaluation of tongue colour is an important approach for assessment of human health in traditional East Asian medicine, which originated in ancient China. However, tongue colour analyses are unreliable due to poor quantification and reproducibility. Given these limitations, the utility of this technique as a clinical index has not been demonstrated. Here, we assessed whether tongue colour evaluations, as performed in Kampo (traditional Japanese) medicine, via an automated image acquisition system were associated with particular indices of patient health. Methods We obtained high colour reproduction tongue images from 816 Japanese subjects and applied a machine-learning analysis approach to the quantification of tongue body colour in them. Data on sex, age, systolic blood pressure, diastolic blood pressure, pulse rate (PR), body temperature, body mass index (BMI), past medical history (PMH), and blood examination results (haemoglobin, Hb; creatinine) were also collected. Results Tongue body colour was influenced by multiple clinical indices, per simple correlation analyses. In particular, sex, age, BMI, PR, and Hb were correlated with tongue body colour. No significant correlation with PMH was found. Conclusions Tongue body colour, as quantified with a machine learning approach, was found to be a clinical predictor of changes in several clinical indices, particularly those related to obesity and haemoglobin concentrations.

In tongue diagnosis, colour information of tongue body has kept valuable information regarding the state of disease and its correlation with the internal organs. Qualitatively, practitioners may have difficulty in their judgement due to the instable lighting condition and naked eye’s ability to capture the exact colour distribution on the tongue especially the tongue with multicolour substance. To overcome this ambiguity, this paper presents a two-stage tongue’s multicolour classification based on a support vector machine (SVM) whose support vectors are reduced by our proposed k-means clustering identifiers and red colour range for precise tongue colour diagnosis. In the first stage, k-means clustering is used to cluster a tongue image into four clusters of image background (black), deep red region, red/light red region, and transitional region. In the second-stage classification, red/light red tongue images are further classified into red tongue or light red tongue based on the red colour range derived in our work. Overall, true rate classification accuracy of the proposed two-stage classification to diagnose red, light red, and deep red tongue colours is 94%. The number of support vectors in SVM is improved by 41.2%, and the execution time for one image is recorded as 48 seconds.

In tongue diagnosis, colour information of tongue body has kept valuable information regarding the state of disease and its correlation with the internal organs. Qualitatively, practitioners may have difficulty in their judgement due to the instable lighting condition and naked eye's ability to capture the exact colour distribution on the tongue especially the tongue with multicolour substance. To overcome this ambiguity, this paper presents a two-stage tongue's multicolour classification based on a support vector machine (SVM) whose support vectors are reduced by our proposed k-means clustering identifiers and red colour range for precise tongue colour diagnosis. In the first stage, k-means clustering is used to cluster a tongue image into four clusters of image background (black), deep red region, red/light red region, and transitional region. In the second-stage classification, red/light red tongue images are further classified into red tongue or light red tongue based on the red colour range derived in our work. Overall, true rate classification accuracy of the proposed two-stage classification to diagnose red, light red, and deep red tongue colours is 94%. The number of support vectors in SVM is improved by 41.2%, and the execution time for one image is recorded as 48 seconds.

The present study examined the efficacy and safety of yokukansan (YKS) in neuropsychiatric symptoms in patients with Parkinson's disease (PD) using the neuropsychiatric inventory (NPI). Twenty-five patients with PD (M:F 14:11; age 72 years) were enrolled and treated with YKS (7.5 g/day) for 12 weeks. The NPI was assessed at 0, 4, 8, 12 and 16 weeks. The patient's motor function and progression were evaluated using the Unified PD Rating Scale part III (UPDRS-III) and Hoehn and Yahr scale, respectively. The serum potassium concentration (sK) and all adverse events were recorded. The median NPI total score significantly decreased from 12 points at baseline to 4.0 points at 12 weeks (p = 0.00003). Within each NPI subscale, significant improvements were observed in hallucinations, anxiety and apathy. These symptoms tended to worsen after the completion of YKS treatment. Delusions, agitation, depression, euphoria, disinhibition, aberrant motor activity tended to improve but irritability showed no change. The median NPI subtotal scores, positive symptoms (delusions-hallucinations-irritability) significantly decreased (p = 0.01660) and negative symptoms (anxiety-apathy) significantly decreased (p = 0.00391). Both UPDRS-III and the Hoehn and Yahr scale showed no significant change. sK decreased mildly from 4.26 ± 0.30 to 4.08 ± 0.33 mEq/L. Two patients showed hypokalemia lower than 3.5 mEq/L without any corresponding symptoms; two patients showed listlessness and one patient showed drug eruption. Each recovered after discontinuation of YKS. YKS improved neuropsychiatric symptoms associated with PD, including hallucinations, anxiety and apathy without severe adverse events and worsening of Parkinsonism.

In computerized tongue diagnostic system, tongue body color has been one of the essential features that contain rich information for diagnosing disease. However, tongue body color measurement can be influenced by the tongue coating color and other ineffective features such as significant coatings, shadows, teeth mark and crackles. This paper presents a fast processing segmentation algorithm using Hue, Saturation and Value (HSV) color space transformation to segment and remove these ineffective features aiming to have an accurate color measurement for online diagnosis. The newly devised Brightness Conformable Multiplier (BCM) has been proposed to automatically adjust the threshold brightness based on three conditions of lower perioral area’s brightness, ; when is smaller than its standard deviation, is greater than its standard deviation and otherwise. Besides, the Modified Sequential Algorithm (MSA) has been proposed to offer fast processing algorithm of 1.445 seconds and better segmentation. The successful segmentation rate was recorded as 90%. Furthermore, color measurement is carried out on the segmented samples and the analysis showed that the dispersion range of tongue body color measurement is small. This indicates a convincing result as the color boundary among light red, red and deep red tongue has been determined precisely.

In ISO TC249 conference, tongue diagnosis has been one of the most active research and their objectifications has become significant with the help of numerous statistical and machine learning algorithm. Color information of substance or tongue body has kept valuable information regarding the state of disease and its correlation with the internal organs. In order to produce high reproducibility of color measurement analysis, tongue images have to undergo several procedures such as color correction, segmentation and tongue’s substance-coating separation. This paper presents a novel method to recognize substance and coating from tongue images and eliminate the tongue coating for accurate substance color measurement for diagnosis. By utilizing Hue, Saturation, Value (HSV) color space, new color-brightness threshold parameters have been devised to improve the efficiency of tongue’s substance and coating separation procedures and eliminate shadows. The algorithm offers fast processing time around 0.98 seconds for 60,000 pixels tongue image. The successful tongue’s substance and coating separation rate reported is 90% compared to the labelled data verified by the practitioners. Using 300 tongue images, the substance Lab color measurement with small standard deviation had revealed the effectiveness of this proposed method in computerized tongue diagnosis system.

Human infection with the dog and cat roundworm, Toxocara anis (T. canis) and Toxocara cati (T. cati), is a result of accidental ngestion of embryonated eggs [1–5]. These roundworms cannot evelop to adult worms in humans, but tissue-migrating larvae may nduce serious complications, such as the visceral larva migrans VLM) or ocular larva migrans (OLM) [1–5]. Although VLM has been ound in various organs, such as the liver, lung, heart, or skin [1–5], nvolvement of the central nervous system (CNS) is extremely rare. here have been several reports of myelitis caused by VLM due to T. anis [2,3]. Here, we report the first patient with myelitis evidently ssociated with VLM due to T. cati infection.

This paper describes a new sensor system for an abdominal palpation procedure in traditional medicine. This sensor system uses a motion capture system and a thin film force/pressure sensor which enables to measuring the depth and the force/pressure at the same time during abdominal palpations. We customised the motion capture system, making it suitable for abdominal palpations, to prevent a physician from being distracted and to eliminate blind spots. We fabricated a detecting circuit for the force/pressure sensor which uses a Bluetooth low energy module and which is powered by a coin cell battery. The circuit enables mounting the detecting circuit on a glove. In addition, we developed a user interface application which is easy to use and which records the information on abdominal palpations on a personal computer. The abdominal palpation sensor system should transfer the diagnostic criteria to young physicians more easily and appropriately in traditional medicine.

A 57-year-old woman suffered sudden onset of thunderclap headache after exposure to phenylpropanolamine (PPA), and subsequently developed posterior reversible encephalopathy syndrome (PRES) complicated by occipital intracranial hemorrhage (ICH) with cerebral vasoconstriction. PPA is well known to be associated with ICH and vasoconstriction, but this case illustrates the association with PRES. The danger of exposure to PPA and subsequent adverse events is quite low at present, but we must consider the possibility of exposure to medical agents in patients with repeated severe headache who have no organic disorder.

Objective To evaluate the efficacy and safety of Yokukansan, a traditional Chinese herbal medicine, for treating behavioral and psychological symptoms of dementia (BPSD) in patients with Parkinson disease (PD; n = 7) and those with PD with dementia (PDD; n = 7). Background BPSD are often seen in patients with senile dementia and have serious deleterious effects on the lives of patients and caregivers. Recent studies indicate that the traditional Chinese herbal medicine Yokukansan may be safe and beneficial for the treatment of BPSD patients. Methods We treated 7 PD and 7 PDD patients for 4 weeks with Yokukansan and observed them without Yokukansan for 4 weeks. Changes in behavioral and psychological symptoms were evaluated every 4 weeks according to the Neuropsychiatric Inventory (NPI) scale. Results Significant improvements in behavioral and psychological symptoms, particularly in the incidence and duration of hallucinations, were observed in most PD and PDD patients after 4 weeks of Yokukansan treatment. No significant changes were observed in the laboratory tests, cognitive function, activities of daily living, or parkinsonism. Conclusion Our results suggest that Yokukansan improves BPSD in both PD and PDD patients without worsening their cognitive function, ability to perform activities of daily living, or parkinsonism.

This paper focuses on the attempt to formulate the prescription prediction logic based on the medical data analysis towards the future computer-assisted-diagnosis for Kampo medicine. We constructed and evaluated prediction models for some frequently-used prescriptions using six kinds of machine learning algorithms including artificial neural network, multinomial logit, random forest, support vector machine, k-nearest neighbor, and decision tree. The possibility of prescription prediction and the necessary amount of data required for robust prediction are clarified.

Economy class stroke syndrome is a cardiovascular complication associated with long periods of travel, only a few cases have been reported after long drives, however. The patient, a 62-year-old professional driver, had driven a truck for 2 days with minimal rest. While driving, he noted left foot paresis and numbness, along with geographical disorientation. Magnetic resonance imaging of the brain revealed multiple cerebral embolisms in the bilateral cerebral hemisphere. The only complications representing a stroke risk in this patient were a patent foramen ovale and an anterior septal aneurysm, as detected by transesophageal echocardiography. The patient was diagnosed with paradoxical cerebral embolism following his long drive. This case report examines the paradoxical cerebral emboli documented in a patient following a long period of driving.

Introduction The evaluation of tongue colour has been an important approach to examine human health in Kampo medicine (traditional Japanese medicine) because the change in tongue colour may suggest physical or mental disorders. Several tongue colour quantification methods have been published to objectify clinical information among East Asian countries. However, reliable tongue colour analysis results among Japanese test persons are limited because of a lack of quantitative evaluation of tongue colour. We aimed to use advances in digital imaging processing to quantify and verify clinical data tongue colour diagnosis by characterising differences intongue features. Methods The DS01-B tongue colour information acquisition system was used to extract tongue images of 1080 Japanese test subjects. Evaluation of tongue colour, body and coating was performed by 10 experienced Kampo medicine physicians. The acquired images were classified into five tongue body colour categories and six tongue coating colour categories based on evaluations from 10 physicians with extensive Kampo medicine experience. K-means clustering algorithm was applied as a machine learning (the study of pattern recognition by computational learning) method to the acquired images to quantify tongue body and coating colour information. Results Tongue body (n = 550) and tongue coating (n = 516) colour samples were classified and analysed. Clusters consisting of five tongue body colour categories and six tongue coating colour categories were experimentally described in the CIELAB colour space. Statistical differences were evident among the clinically primary tongue colours. Conclusions Clinically important tongue colour differences in Kampo medicine can be visualised by applying machine learning to tongue images taken under stable conditions. This has implications for developing globally unified, reliable tongue colour diagnostic criteria which could be used to explore the relevance between clinical status and tongue colour.