Machine learning for prediction of schizophrenia based on identifying the primary and interaction effects of minor physical anomalies

In the neurodevelopmental model of schizophrenia, minor physical anomalies (MPAs) are considered neurodevelopmental markers of schizophrenia. To date, there has been no research to evaluate the interaction between MPAs. Our study built and used a machine learning model to predict the risk of schizophrenia based on measurements of MPA items and to investigate the potential primary and interaction effects of MPAs. The study included 470 patients with schizophrenia and 354 healthy controls. The models used are classical statistical model, Logistic Regression (LR), and machine leaning models, Decision Tree (DT) and Random Forest (RF). We also plotted two-dimensional scatter diagrams and three-dimensional linear/quadratic discriminant analysis (LDA/QDA) graphs for comparison with the DT dendritic structure. We found that RF had the highest predictive power for schizophrenia (Full-training AUC = 0.97 and 5-fold cross-validation AUC = 0.75). We identified several primary MPAs, such as the mouth region, high palate, furrowed tongue, skull height and mouth width. Quantitative MPA analysis indicated that the higher skull height and the narrower mouth width, the higher the risk of schizophrenia. In the interaction, we further identified that skull height and mouth width, furrowed tongue and skull height, high palate and skull height, and high palate and furrowed tongue, showed significant two-item interactions with schizophrenia. A weak three-item interaction was found between high palate, skull height, and mouth width. In conclusion, we found that the two machine learning methods showed good predictive ability in assessing the risk of schizophrenia using the primary and interaction effects of MPAs.

Fissured Tongue among Patients Visiting the Department of Oral Medicine and Radiology in a Tertiary Care Centre

Introduction

Examination of the tongue and knowledge of its variation can aid clinicians in correctly assessing the cause of a patient's complaint. Despite World Health Organization recommendations to encourage more epidemiological assessment of oral mucosal variations and lesions, the volume of literature in this area is limited. This study aimed to find out the prevalence of fissured tongues among patients visiting the Department of Oral Medicine and Radiology in a tertiary care centre.

Methods

A descriptive cross-sectional study was conducted among patients visiting the Department of Oral Medicine and Radiology in a tertiary care centre. Data was collected from 12 March 2023 to 10 May 2023 after obtaining ethical approval from the same institute. A convenience sampling method was used. The point estimate was calculated at a 95% Confidence Interval.

Results

Out of 540 patients, the prevalence of fissured tongue was 73 (13.51%) (10.63-16.40, 95% Confidence Interval). A total of 34 (46.57%) were males and 39 (53.42%) were females.

Conclusions

The prevalence of fissured tongue among patients visiting the Department of Oral Medicine and Radiology was higher than other studies done in similar settings.

Keywords

anatomic variation; fissured tongue; Nepal; oral mucosa; prevalence.

Classification of fissured tongue images using deep neural networks

BACKGROUND:

Tongue inspection is vital in traditional Chinese medicine. Fissured tongue is an important feature in tongue diagnosis, and primarily corresponds to three Chinese medicine syndromes: syndrome-related hotness, blood deficiency, and insufficiency of the spleen. Diagnosis of the syndrome is significantly affected by the experience of clinicians, and it is difficult for young doctors to perform accurate diagnoses.

OBJECTIVE:

The syndrome not only depends on the local features based on fissured regions but also on the global features of the whole tongue; therefore, a syndrome diagnosis framework combining the global and local features of a fissured tongue image was developed in the present study to achieve a quantitative and objective diagnosis.

METHODS:

First, we detected the fissured region of a tongue image using a single-shot multibox detector. Second, we extracted the global and local features from a whole tongue image and a fissured region using TongueNet (developed in-house). Third, we developed a classifier to determine the final syndrome.

RESULTS:

Based on an experiment involving 721 fissured tongue images, we discovered that TongueNet affords better feature extraction. The accuracy of TongueNet was 4% (p< 0.05) and 3% (p< 0.05) higher than that of InceptionV3 and ResNet18, respectively, for whole tongue images. Meanwhile, at local fissured regions, the accuracy of TongueNet was 3% (p< 0.05) higher than that of InceptionV3 and equal to that of ResNet18. Finally, the fusion features outperformed the global and local features with a 78% accuracy.

CONCLUSIONS:

Our findings indicate that TongueNet designed with batch normalization and dropout is more suitable for uncomplicated images than InceptionV3 and ResNet18. In addition, compared with the global features, the fusion features supplement the detailed information of the fissures and improve classification accuracy.

Rare diagnosis of Melkersson-Rosenthal syndrome in a paediatric patient

Melkersson-Rosenthal syndrome (MRS) is a rare neurocutaneous syndrome characterised by the triad of recurrent orofacial swelling, facial nerve palsy and fissured tongue. This diagnosis is particularly rare in children. We aim to increase awareness of the syndromic association of these clinical features since most patients present with a monosymptomatic form, reiterating the importance of detailed history and thorough physical examination, for the timely identification of these patients. Not only the recurring of symptoms, but also the association of MRS with other medical conditions, make 'earlier' diagnosis of the Syndrome beneficial. The average delay in diagnosis is 4-9 years. Although most cases resolve without treatment, when treated,steroids are most commonly used. Variable options have been tried for refractory and frequently recurrent cases. We present a case of MRS in a 12-year-old girl, diagnosed 3 years after onset of symptoms. We reviewed updated literature for MRS and associated clinical conditions as well as published treatment options.

[Research progress on the risk factors of geographic tongue]

Geographic tongue, also called benign migratory glossitis, is a common and superficial benign inflammatory disorder that affects the tongue epithelium. The majority of geographic tongue lesions typically manifest as irregular central erythematous patches. These lesions, which are caused by the loss of filiform papillae, are defined by an elevated whitish band-like border that can change location, size, and pattern over a period of time. Histological observations of the oral mucosa affected by geographic tongue revealed nonspecific inflammation. Some reports described cases of migratory stomatitis, wherein lesions simultaneously manifested on the extra lingual oral mucosa. This condition is also called ectopic geographic tongue, which is clinically and histologically similar to the type normally confined to the tongue. In most cases, patients are asymptomatic and do not require treatment. The condition may spontaneously exhibit periods of remission and exacerbation with good prognosis. The specific etiology of geographic tongue remains unknown. Geographic tongue is age-related and is prevalent among young individuals. Various etiological factors that have been suggested in literature include immunological factors, genetic factors, atopic or allergic tendency, emotional stress, tobacco consumption, hormonal disturbances, and zinc deficiency. Geographic tongue may coexist with other disorders, such as fissured tongue, psoriasis, diabetes mellitus, gastroin- testinal diseases, burning mouth syndrome, and Down syndrome. Experts currently disagree on whether geographic tongue is an oral manifestation of psoriasis. Moreover, some scholars suggest that geographic tongue is a prestage of fissured tongue. The objective of this review is to summarize current research on risk factors of geographic tongue.

Tassier cleft no 30 (median cleft from lower lip to manubrium)

One-year-old female presented with cleft of lower lip, mandible, fissured tongue, absent hyoid bone, cleft of manubrium sterni, later is detected clinically by suprasternal bulge at suprasternal region while crying. It is radiologically detected by wide apart medial end of clavicle. This is extremely rare anomaly known as Tassier Cleft no 30.

[Melkersson-Rosenthal syndrome. A case report]

The Melkersson-Rosenthal syndrome is a rare disease of unknown pathogenesis. Classical signs include recurrent facial palsy, lingua plicata and orofacial edema. The diagnosis is often difficult when all features are not present at the same time: in the literature complete triads occurred in 25-30% of the patients. We report a case of Melkersson-Rosenthal syndrome with classical triad of signs in a 13 year old boy. The pathology, clinical features and management of this disease are discussed: the possible role of food allergy or additives intolerance is also examined.

[Lingual innervation in the buffalo]

The lingual and papillary mucosa innervation has been studied in the buffalo by histochemical and immunohistochemical techniques and by gold impregnation method of Ruffini. In lingual mucosa the presence of ganglionic structures has been noticed in which there are numerous cellular bodies and bundles of fibres variously directed. Particularly in the vallate papillae, the papillary stroma contains myelinic and unmyelinated fibres and terminal nerve corpuscles. Along stromal myelinic fibres the presence of the proteins S-100 and NF has been demonstrated.

Cheilitis granulomatosa (Melkersson-Rosenthal syndrome)

An oligosymptomatic manifestation of the Melkersson-Rosenthal syndrome is described. The importance of serial sections of the tissue specimen is emphasized. Satisfactory postoperative results are obtained.