Automated characterization and detection of fibromyalgia using slow wave sleep EEG signals with glucose pattern and D'hondt pooling technique

Fibromyalgia is a soft tissue rheumatism with significant qualitative and quantitative impact on sleep macro and micro architecture. The primary objective of this study is to analyze and identify automatically healthy individuals and those with fibromyalgia using sleep electroencephalography (EEG) signals. The study focused on the automatic detection and interpretation of EEG signals obtained from fibromyalgia patients. In this work, the sleep EEG signals are divided into 15-s and a total of 5358 (3411 healthy control and 1947 fibromyalgia) EEG segments are obtained from 16 fibromyalgia and 16 normal subjects. Our developed model has advanced multilevel feature extraction architecture and hence, we used a new feature extractor called GluPat, inspired by the glucose chemical, with a new pooling approach inspired by the D'hondt selection system. Furthermore, our proposed method incorporated feature selection techniques using iterative neighborhood component analysis and iterative Chi2 methods. These selection mechanisms enabled the identification of discriminative features for accurate classification. In the classification phase, we employed a support vector machine and k-nearest neighbor algorithms to classify the EEG signals with leave-one-record-out (LORO) and tenfold cross-validation (CV) techniques. All results are calculated channel-wise and iterative majority voting is used to obtain generalized results. The best results were determined using the greedy algorithm. The developed model achieved a detection accuracy of 100% and 91.83% with a tenfold and LORO CV strategies, respectively using sleep stage (2 + 3) EEG signals. Our generated model is simple and has linear time complexity.

Negative to positive axial thermal expansion switching of an organic crystal: contribution to multistep photoactuation

Materials displaying negative thermal expansion (NTE), in contrast to typical materials with positive thermal expansion (PTE), are attractive for both fundamental research and practical applications, including the development of composites with near-zero thermal expansion. A recent data mining study revealed that approximately 34% of organic crystals may present NTE, indicating that NTE in organic crystals is much more common than generally believed. However, organic crystals that switch from NTE to PTE or vice versa have rarely been reported. Here, we report the crystal of N-3,5-di-tert-butylsalicylide-3-nitroaniline in the enol form (enol-1) as the first organic crystal in which the axial thermal expansion changes from negative to positive at around room temperature. When heated, the crystal shrinks along the a-axis below 30 °C and then it expands above 30 °C. Geometric calculations revealed that below 30 °C, the decrease in the tilt angle of the molecule exceeds the increase in the interplanar distance, causing NTE, whereas above 30 °C, the increase in the interplanar distance outweighs the decrease in the tilt angle, resulting in PTE. By combining photoisomerisation and the NTE-PTE switching induced by the photothermal effect, multistep crystal photoactuation was achieved. Moreover, actuation switching of the same crystal sample by changing atmosphere temperature was realised by utilising the NTE-PTE change. Such NTE-PTE switching without a thermal phase transition provides not only new insight into organic crystals but also a new strategy for designing crystal actuators.

Mechanical properties and peculiarities of molecular crystals

In the last century, molecular crystals functioned predominantly as a means for determining the molecular structures via X-ray diffraction, albeit as the century came to a close the response of molecular crystals to electric, magnetic, and light fields revealed that the physical properties of molecular crystals were as rich as the diversity of molecules themselves. In this century, the mechanical properties of molecular crystals have continued to enhance our understanding of the colligative responses of weakly bound molecules to internal frustration and applied forces. Here, the authors review the main themes of research that have developed in recent decades, prefaced by an overview of the particular considerations that distinguish molecular crystals from traditional materials such as metals and ceramics. Many molecular crystals will deform themselves as they grow under some conditions. Whether they respond to intrinsic stress or external forces or interactions among the fields of growing crystals remains an open question. Photoreactivity in single crystals has been a leading theme in organic solid-state chemistry; however, the focus of research has been traditionally on reaction stereo- and regio-specificity. However, as light-induced chemistry builds stress in crystals anisotropically, all types of motions can be actuated. The correlation between photochemistry and the responses of single crystals-jumping, twisting, fracturing, delaminating, rocking, and rolling-has become a well-defined field of research in its own right: photomechanics. The advancement of our understanding requires theoretical and high-performance computations. Computational crystallography not only supports interpretations of mechanical responses, but predicts the responses itself. This requires the engagement of classical force-field based molecular dynamics simulations, density functional theory-based approaches, and the use of machine learning to divine patterns to which algorithms can be better suited than people. The integration of mechanics with the transport of electrons and photons is considered for practical applications in flexible organic electronics and photonics. Dynamic crystals that respond rapidly and reversibly to heat and light can function as switches and actuators. Progress in identifying efficient shape-shifting crystals is also discussed. Finally, the importance of mechanical properties to milling and tableting of pharmaceuticals in an industry still dominated by active ingredients composed of small molecule crystals is reviewed. A dearth of data on the strength, hardness, Young's modulus, and fracture toughness of molecular crystals underscores the need for refinement of measurement techniques and conceptual tools. The need for benchmark data is emphasized throughout.

Photothermally induced natural vibration for versatile and high-speed actuation of crystals

The flourishing field of soft robotics requires versatile actuation methodology. Natural vibration is a physical phenomenon that can occur in any material. Here, we report high-speed bending of anisole crystals by natural vibration induced by the photothermal effect. Rod-shaped crystal cantilevers undergo small, fast repetitive bending (~0.2°) due to natural vibration accompanied by large photothermal bending (~1°) under ultraviolet light irradiation. The natural vibration is greatly amplified by resonance upon pulsed light irradiation at the natural frequency to realise high frequency (~700 Hz), large bending (~4°), and high energy conversion efficiency from light to mechanical energy. The natural vibration is induced by the thermal load generated by the temperature gradient in the crystal due to the photothermal effect. The bending behaviour is successfully simulated using finite element analysis. Any light-absorbing crystal can be actuated by photothermally induced natural vibration. This finding of versatile crystal actuation can lead to the development of soft robots with high-speed and high-efficient actuation capabilities.

Association between cognitive social capital and all-cause mortality in Great East Japan Earthquake survivors: a prospective cohort study

OBJECTIVES

Cognitive social capital (SC), such as attitude, trust, or norms, may help improve resilience among survivors, thus improving their health. However, the association between cognitive SC and the risk of all-cause mortality among survivors after the natural disaster has never been investigated. The purpose of the present study is to investigate the association between cognitive SC and the risk of all-cause mortality among survivors of the Great East Japan Earthquake (GEJE).

STUDY DESIGN

Prospective cohort study.

METHODS

We conducted a health survey on 1654 residents aged ≥18 years who lived in two areas affected by the GEJE. One year after the GEJE, between June and August 2012, cognitive SC (helping each other, trust, greeting, and solving problems together) was assessed using a self-administrated questionnaire. We divided the subjects into two groups based on response to questionnaire: "high" or "low." We obtained information on death and emigration from the Residential Registration Record and followed up on the participants from June 2012 to November 2020. The Cox proportional hazards regression analysis was used for estimating the multivariate-adjusted hazard ratios (HRs) and 95% confidence intervals (CIs) for the risk of all-cause mortality according to each cognitive SC indicator.

RESULTS

During the 8.5 years of follow-up, 213 subjects died (12.9%). For greeting, compared with subjects who were "high," subjects who were "low" were significantly associated with the risk of all-cause mortality (HR: 2.92, 95% CI: 1.19-7.17). No statistically significant association was observed for helping each other, trust, and solving problems together.

CONCLUSION

Our findings suggest that perception of greeting may be associated with the risk of all-cause mortality in survivors after natural disasters.

A Novel In Vitro Membrane Permeability Methodology Using Three-dimensional Caco-2 Tubules in a Microphysiological System Which Better Mimics In Vivo Physiological Conditions

The aim of this study was to develop an in vitro drug permeability methodology which mimics the gastrointestinal environment more accurately than conventional 2D methodologies through a three-dimensional (3D) Caco-2 tubules using a microphysiological system. Such a system offers significant advantages, including accelerated cellular polarization and more accurate mimicry of the in vivo environment. This methodology was confirmed by measuring the permeability of propranolol as a model compound, and subsequently applied to those of solifenacin and bile acids for a comprehensive understanding of permeability for the drug product in the human gastrointestinal tract. To protect the Caco-2 tubules from bile acid toxicity, a mucus layer was applied on the surface of Caco-2 tubules and it enables to use simulated intestinal fluid. The assessment using propranolol reproduced results equivalent to those obtained from conventional methodology, while that using solifenacin indicated fluctuations in the permeability of solifenacin due to various factors, including interaction with bile acids. We therefore suggest that this model will serve as an alternative testing system for measuring drug absorption in an environment closely resembling that of the human gastrointestinal tract.

Photothermally Driven High-Speed Crystal Actuation and Its Simulation

Mechanically responsive crystals have been increasingly explored, mainly based on photoisomerization. However, photoisomerization has some disadvantages for crystal actuation, such as a slow actuation speed, no actuation of thick crystals, and a narrow wavelength range. Here we report photothermally driven fast-bending actuation and simulation of a salicylideneaniline derivative crystal with an o-amino substituent in enol form. Under ultraviolet (UV) light irradiation, these thin (<20 μm) crystals bent but the thick (>40 μm) crystals did not due to photoisomerization; in contrast, thick crystals bent very quickly (in several milliseconds) due to the photothermal effect, even by visible light. Finally, 500 Hz high-frequency bending was achieved by pulsed UV laser irradiation. The generated photothermal energy was estimated based on the photodynamics using femtosecond transient absorption. Photothermal bending is caused by a nonsteady temperature gradient in the thickness direction due to the heat conduction of photothermal energy generated near the crystal surface. The temperature gradient was calculated based on the one-dimensional nonsteady heat conduction equation to simulate photothermally driven crystal bending successfully. Most crystals that absorb light have their own photothermal effects. It is expected that the creation and design of actuation of almost all crystals will be possible via the photothermal effect, which cannot be realized by photoisomerization, and the potential and versatility of crystals as actuation materials will expand in the near future.

Wide-area multilayered self-assembly of fluorapatite nanorods vertically oriented on a substrate as a non-classical crystal growth

Oriented attachment of homogeneously shaped nanoblocks, such as nanocubes and nanorods, is attracting attention as a fundamental process of non-classical crystal growth to produce specific ordered architectures of functional materials. Although lateral alignments of horizontally oriented nanorod are commonly observed at the air-liquid and liquid-solid interfaces in dispersion systems, the accumulation of vertically oriented nanorods on a substrate has rarely been produced in a wide area over a millimeter-sized flat surface. Here, we achieved homogeneous stacking of vertical fluorapatite nanorods with a large aspect ratio (∼6) in a toluene-hexane mixture system through a gradual decrease in the dispersibility. Micrometer-thick flat films in which the c direction of fluorapatite nanorods was arranged perpendicularly to the surface were deposited on a substrate with a diameter of over 20 mm. The wide-area accumulation of vertical nanorods occurs through the self-assembly of laterally arranged clusters of nanorods covered with a stabilizing agent and subsequent gentle sedimentation on the substrate surface.

Actuation performance of a photo-bending crystal modeled by machine learning-based regression

The bending deflection and blocking force of photo-bending crystals of different sizes were experimentally measured at various light intensities, and then modeled by the machine learning-based regression.

Morphological evolution of carbonated hydroxyapatite to faceted nanorods through intermediate states

On the conversion of a parent calcite nanocrystal, thin low-crystalline nanosheets of carbonated hydroxyapatite are initially grown via the dissolution–reprecipitation route and then evolve into faceted rods covered with stable surfaces.

Preparation of 99mTc-Labeled Mannan-S-Cysteine and Effect of Molecular Size of Mannan on Its Biodistribution

Macrophage mannose receptor (MMR/CD206) is a promising target for the detection and identification of sentinel lymph node (SLN). MMR-targeting probes have been developed using mannosylated dextran, however, impairment of efficient targeting of SLN was often caused because of retention of injection site in which macrophages and dendritic cells exist. In this study, we prepared new MMR-targeting probes from yeast mannan (85 kDa), and its bioditribution was investigated. In-vivo evaluation showed that 11.9% of injected dose of ^99mTc-labeled mannan-S-cysteines (^99mTc-MSCs) was accumulated in popliteal lymph node (the SLN in this model), however, significant level of radioactivity (approximately 80%) was remained in injection site. Interestingly, ^99mTc-labeled low molecular weight mannan-S-cysteine mannan (^99mTc-LSC) prepared from 50 and 25 kDa mannan showed a decreased specific accumulation of ^99mTc-LSC in the popliteal lymph node, while the radioactivity at the injection site remained unchanged. These results suggest that the molecular size, or nature/shape of the sugar chain is important for the specific accumulation of ^99mTc-MSC in popliteal lymph node.

Abstract P2-13-02: Patient-reported outcomes with trastuzumab monotherapy versus trastuzumab plus standard chemotherapy as a postoperative adjuvant therapy in HER2-positive elderly breast cancer patients (RESPECT): A randomized, open-label, phase 3 clinical trial

OBJECTIVE: The RESPECT trial compared 1-year trastuzumab monotherapy with trastuzumab plus standard chemotherapy as a postoperative adjuvant therapy in HER2-positive elderly breast cancer patients. Primary objective of this study was to verify the noninferiority of 1-year trastuzumab monotherapy to trastuzumab plus chemotherapy in terms of disease free survival, and the planned analysis showed that the difference of restricted mean survival time between two groups at 3 years was 0.45 months (reported by Sawaki at ASCO2018). This report assesses the patients-reported outcomes and health-related quality of life (HRQoL).

PATIENTS AND METHODS: The study was done at 99 hospitals in Japan. Elderly women (70 to 80 years old) with HER2-positive, stageI-IIIA invasive breast cancer treated by surgery with clear resection margins were randomly assigned to receive either 1-year trastuzumab or 1-year trastuzumab plus standard chemotherapy, stratified by age, hormone-receptor status, pathological lymph node metastasis and institution. Patients completed questionnaires at baseline, 2 months, 1year, and 3 years after protocol treatment started. The primary outcome was global HRQoL assessed using Functional Assessment of Cancer Therapy-General (FACT-G) total score, and secondary outcomes were chemotherapy-induced peripheral neuropathy (CIPN), instrumental activities of daily living (IADL), anxiety, depression, and subjective happiness. We did the analyses by intention to treat, including patients who completed questionnaires at baseline before start of protocol treatment, and 5point or more change is meaningful in FACT-G total score. This study is registered with ClinicalTrials.gov, NCT01104935.

RESULTS: Between Oct 2009 and Oct 2014, 275 patients were enrolled in the study, of whom 9 patients were excluded: 135 assigned to trastuzumab monotherapy and 131 assigned to trastuzumab plus chemotherapy. We detected significant difference between treatment groups for: clinically meaningful HRQoL deterioration rate at 2 months (31% for trastuzumab monotherapy vs 48% for trastuzumab plus chemotherapy; p=0.016) and at 1year (19% vs 38%; p=0.009), clinically meaningful HRQoL improvement rate at 2 months (38% for trastuzumab monotherapy vs 15% for trastuzumab plus chemotherapy; p&lt;0.01) and at 1year (43% vs 25%; p=0.021), severe sensory CIPN rate at 2months (1.9% for trastuzumab monotherapy vs 14.4% for trastuzumab plus chemotherapy; p=0.001), IADL score at 1year (11.97 for trastuzumab monotherapy vs 11.54 for trastuzumab plus chemotherapy; p&lt;0.042), Hospital Anxiety and Depression Scale score at 2months (8.92 for trastuzumab monotherapy vs 10.79 for trastuzumab plus chemotherapy; p&lt;0.003), and subjective happiness score at 1year (12.8 for trastuzumab monotherapy vs 11.8 for trastuzumab plus chemotherapy; p&lt;0.024).

CONCLUSION: Given the small advantage of adjuvant trastuzumab plus chemotherapy compared to trastuzumab monotherapy for elderly HER-2 positive breast cancer women, decisions about treatment should be informed by the risk for adverse health effects associated with chemotherapy.

Citation Format: Kobayashi K, Taira N, Sawaki M, Sagawa N, Baba S, Saito T, Kawahara T, Hagiwara Y, Uemura Y, Shimozuma K, Ohashi Y, Mukai H. Patient-reported outcomes with trastuzumab monotherapy versus trastuzumab plus standard chemotherapy as a postoperative adjuvant therapy in HER2-positive elderly breast cancer patients (RESPECT): A randomized, open-label, phase 3 clinical trial [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr P2-13-02.

Abstract P1-11-21: Analysis of cognitive function in elderly HER2-positive breast cancer patients receiving either trastuzumab monotherapy or trastuzumab plus chemotherapy as a postoperative adjuvant treatment: A cognitive function sub-study of a randomized, open-label, phase 3 clinical trial (RESPECT trial)

OBJECTIVE: The effect of trastuzumab(Tmab) or chemotherapy on cognitive function has not been fully understood, especially in elderly breast cancer patients. The RESPECT trial compared 1-year(yr) Tmab monotherapy with Tmab plus standard chemotherapy as adjuvant therapy in elderly patients with HER2-positive breast cancer. The primary objective was to verify the noninferiority of 1-yr Tmab monotherapy compared to Tmab plus chemotherapy in terms of disease-free survival, and the planned analysis showed that the difference of restricted mean survival time between two groups at 3 yrs was 0.45 months (Sawaki at ASCO2018). The goal of this report was to assess the impact of the treatment groups on longitudinal cognitive function.

PATIENTS AND METHODS: The study was performed with patients from 99 hospitals in Japan. Elderly women with HER2-positive, stage I-IIIA invasive breast cancer surgery treated with clear resection margins were randomly assigned to either receive 1-yr Tmab or 1-yr Tmab plus standard chemotherapy. 15 institutions participated in the cognitive sub-study. Cognitive function was assessed using the Mini-Mental State Examination (MMSE) at baseline and at 1 and 3 yrs after treatment. The primary outcome was the amount of change in the MMSE score from the baseline. A linear mixed-effects model was used for comparisons of change in the MMSE score between groups, controlling for time and baseline score. Secondary outcomes were the proportion of both suspected mild dementia (MMSE≤27) and dementia (MMSE≤23) at each time point.

RESULTS: Between October 2009 and October 2014, 275 patients were enrolled in the RESPECT trial, and 57 patients were enrolled in the cognitive function sub-study with 2 patients subsequently excluded. The 55-patient sub-study comprised 29 patients assigned to the Tmab monotherapy group and 26 patients assigned to the Tmab plus chemotherapy group. Primary analysis revealed that change in the MMSE score was not significantly different between the two groups (difference −0.6 at 1 yr and −0.9 at 3 yrs; p=0.136), whereas the baseline score was the only significant factor that had an effect on the amount of change in the MMSE score (p&lt;0.001). The proportions of suspected mild dementia at baseline, and at 1 yr and 3 yrs were 15.4, 32.0, and 41.7% in the Tmab monotherapy group, and 45.8, 17.6, and 28.6% in the Tmab plus chemotherapy group. The proportions of suspected mild dementia at baseline were significantly higher in the Tmab plus chemotherapy group (p=0.04). The proportions of suspected dementia at baseline, and at 1 yr and 3 yrs were 0%, 0%, and 4.2% in the Tmab monotherapy group, and 4.2%, 0%, and 4.8% in the Tmab plus chemotherapy group. There were no significant differences in the proportions of suspected dementia between the treatment groups at each time point.

CONCLUSION: Postoperative chemotherapy for elderly breast cancer patients was considered to have little effect on the onset of dementia during the follow-up period of 3 yrs. Further long-term observation is necessary to obtain a significant conclusion.

Citation Format: Takahashi M, Sawaki M, Hagiwara Y, Uemura Y, Kawahara T, Shimozuma K, Ohashi Y, Saito T, Baba S, Kobayashi K, Mukai H, Taira N. Analysis of cognitive function in elderly HER2-positive breast cancer patients receiving either trastuzumab monotherapy or trastuzumab plus chemotherapy as a postoperative adjuvant treatment: A cognitive function sub-study of a randomized, open-label, phase 3 clinical trial (RESPECT trial) [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr P1-11-21.

REVERCE: a randomized phase II study of regorafenib followed by cetuximab versus the reverse sequence for previously treated metastatic colorectal cancer patients

BACKGROUND

The objective of this randomized phase II trial was to evaluate efficacy and safety of the therapeutic sequence of regorafenib followed by cetuximab, compared with cetuximab followed by regorafenib, as the current standard sequence for metastatic colorectal cancer patients.

PATIENTS AND METHODS

Patients with KRAS exon 2 wild-type metastatic colorectal cancer after failure of fluoropyrimidine, oxaliplatin, and irinotecan were randomized to receive sequential treatment with regorafenib followed by cetuximab ± irinotecan (R-C arm), or the reverse sequence [cetuximab ± irinotecan followed by regorafenib (C-R arm)]. The primary end point was overall survival (OS). Key secondary end points included progression-free survival (PFS) with initial treatment (PFS1), PFS with second treatment (PFS2), safety, and quality of life. Exploratory end points included serial biomarker analyses, including oncogenic alterations from circulating tumor DNA or multiple serum or plasma proteins.

RESULTS

One-hundred one patients were randomized and eligible for efficacy analysis. Sequential treatment was successful in 86% patients in both arms. Median OS for R-C and C-R was 17.4 and 11.6 months, respectively (P = 0.0293), with a hazard ratio (HR) of 0.61 for OS [95% confidence interval (CI) 0.39-0.96]. The HR for PFS1 (regorafenib in R-C versus cetuximab in C-R) was 0.97 (95% CI 0.61-1.54), and PFS2 (C in R-C versus R in C-R) was 0.29 (95% CI 0.17-0.50). No unexpected safety signals were observed. The quality of life scores during the entire treatment period was not significantly different between the two arms. Circulating biomarker analyses showed emerging oncogenic alterations in RAS, BRAF, EGFR, HER2, and MET, which were more commonly detected after cetuximab than after regorafenib.

CONCLUSIONS

The therapeutic sequence of regorafenib followed by cetuximab suggests a longer OS than the current standard sequence.

Automated seizure prediction

In the past two decades, significant advances have been made on automated electroencephalogram (EEG)-based diagnosis of epilepsy and seizure detection. A number of innovative algorithms have been introduced that can aid in epilepsy diagnosis with a high degree of accuracy. In recent years, the frontiers of computational epilepsy research have moved to seizure prediction, a more challenging problem. While antiepileptic medication can result in complete seizure freedom in many patients with epilepsy, up to one-third of patients living with epilepsy will have medically intractable epilepsy, where medications reduce seizure frequency but do not completely control seizures. If a seizure can be predicted prior to its clinical manifestation, then there is potential for abortive treatment to be given, either self-administered or via an implanted device administering medication or electrical stimulation. This will have a far-reaching impact on the treatment of epilepsy and patient's quality of life. This paper presents a state-of-the-art review of recent efforts and journal articles on seizure prediction. The technologies developed for epilepsy diagnosis and seizure detection are being adapted and extended for seizure prediction. The paper ends with some novel ideas for seizure prediction using the increasingly ubiquitous machine learning technology, particularly deep neural network machine learning.

Automated detection and classification of liver fibrosis stages using contourlet transform and nonlinear features

BACKGROUND AND OBJECTIVE

Liver fibrosis is a type of chronic liver injury that is characterized by an excessive deposition of extracellular matrix protein. Early detection of liver fibrosis may prevent further growth toward liver cirrhosis and hepatocellular carcinoma. In the past, the only method to assess liver fibrosis was through biopsy, but this examination is invasive, expensive, prone to sampling errors, and may cause complications such as bleeding. Ultrasound-based elastography is a promising tool to measure tissue elasticity in real time; however, this technology requires an upgrade of the ultrasound system and software. In this study, a novel computer-aided diagnosis tool is proposed to automatically detect and classify the various stages of liver fibrosis based upon conventional B-mode ultrasound images.

METHODS

The proposed method uses a 2D contourlet transform and a set of texture features that are efficiently extracted from the transformed image. Then, the combination of a kernel discriminant analysis (KDA)-based feature reduction technique and analysis of variance (ANOVA)-based feature ranking technique was used, and the images were then classified into various stages of liver fibrosis.

RESULTS

Our 2D contourlet transform and texture feature analysis approach achieved a 91.46% accuracy using only four features input to the probabilistic neural network classifier, to classify the five stages of liver fibrosis. It also achieved a 92.16% sensitivity and 88.92% specificity for the same model. The evaluation was done on a database of 762 ultrasound images belonging to five different stages of liver fibrosis.

CONCLUSIONS

The findings suggest that the proposed method can be useful to automatically detect and classify liver fibrosis, which would greatly assist clinicians in making an accurate diagnosis.

Computer-aided diagnosis of glaucoma using fundus images: A review

BACKGROUND AND OBJECTIVES

Glaucoma is an eye condition which leads to permanent blindness when the disease progresses to an advanced stage. It occurs due to inappropriate intraocular pressure within the eye, resulting in damage to the optic nerve. Glaucoma does not exhibit any symptoms in its nascent stage and thus, it is important to diagnose early to prevent blindness. Fundus photography is widely used by ophthalmologists to assist in diagnosis of glaucoma and is cost-effective.

METHODS

The morphological features of the disc that is characteristic of glaucoma are clearly seen in the fundus images. However, manual inspection of the acquired fundus images may be prone to inter-observer variation. Therefore, a computer-aided detection (CAD) system is proposed to make an accurate, reliable and fast diagnosis of glaucoma based on the optic nerve features of fundus imaging. In this paper, we reviewed existing techniques to automatically diagnose glaucoma.

RESULTS

The use of CAD is very effective in the diagnosis of glaucoma and can assist the clinicians to alleviate their workload significantly. We have also discussed the advantages of employing state-of-art techniques, including deep learning (DL), when developing the automated system. The DL methods are effective in glaucoma diagnosis.

CONCLUSIONS

Novel DL algorithms with big data availability are required to develop a reliable CAD system. Such techniques can be employed to diagnose other eye diseases accurately.

Parkinson's disease: Cause factors, measurable indicators, and early diagnosis

Parkinson's disease (PD) is a neurodegenerative disease of the central nervous system caused due to the loss of dopaminergic neurons. It is classified under movement disorder as patients with PD present with tremor, rigidity, postural changes, and a decrease in spontaneous movements. Comorbidities including anxiety, depression, fatigue, and sleep disorders are observed prior to the diagnosis of PD. Gene mutations, exposure to toxic substances, and aging are considered as the causative factors of PD even though its genesis is unknown. This paper reviews PD etiologies, progression, and in particular measurable indicators of PD such as neuroimaging and electrophysiology modalities. In addition to gene therapy, neuroprotective, pharmacological, and neural transplantation treatments, researchers are actively aiming at identifying biological markers of PD with the goal of early diagnosis. Neuroimaging modalities used together with advanced machine learning techniques offer a promising path for the early detection and intervention in PD patients.

Biotransformation of (+)-Carvone and (-)-Carvone by the Common Cutworm Spodoptera litura Larvae

Biotransformation of (+)- and (-)-carvone (1 and 2) by the larvae of common cutworm (Spodoptera litura) has been investigated. (+)-Carvone was transformed to (+)-(4S)-10-hydroxycarvone (1-1), (+)-(4S)-7- hydroxycarvone (1-2), and (-)-(4S)-8,9-dihydroxy-8,9-dihydrocarvone (1-3). (-)-Carvone (2) was transformed to (-)-(4R)-10-hydroxycarvone (2-1), (-)-(4R)-7-hydroxycarvone (2-2), (+)-(4R)-8,9-dihydroxy-8,9- dihydrocarvone (2-3), and (-)-(2R,4R)-10-hydroxycarveol (2-4). The results indicate that the main metabolic reaction of carvones by S. litura larvae is oxidation at vinyl group (C-8 and C-9).

Preoperative oral care and effect on postoperative complications after major cancer surgery

Background

Improving patients' oral hygiene is an option for preventing postoperative pneumonia that may be caused by aspiration of oral and pharyngeal secretions. Whether preoperative oral care by a dentist can decrease postoperative complications remains controversial. A retrospective cohort study was undertaken to assess the association between preoperative oral care and postoperative complications among patients who underwent major cancer surgery.

Methods

The nationwide administrative claims database in Japan was analysed. Patients were identified who underwent resection of head and neck, oesophageal, gastric, colorectal, lung or liver cancer between May 2012 and December 2015. The primary outcomes were postoperative pneumonia and all-cause mortality within 30 days of surgery. Patient background was adjusted for with inverse probability of treatment weighting using propensity scoring.

Results

Of 509 179 patients studied, 81 632 (16·0 per cent) received preoperative oral care from a dentist. A total of 15 724 patients (3·09 per cent) had postoperative pneumonia and 1734 (0·34 per cent) died within 30 days of surgery. After adjustment for potential confounding factors, preoperative oral care by a dentist was significantly associated with a decrease in postoperative pneumonia (3·28 versus 3·76 per cent; risk difference − 0·48 (95 per cent c.i. −0·64 to−0·32) per cent) and all-cause mortality within 30 days of surgery (0·30 versus 0·42 per cent; risk difference − 0·12 (−0·17 to −0·07) per cent).

Conclusion

Preoperative oral care by a dentist significantly reduced postoperative complications in patients who underwent cancer surgery.

Deep learning for healthcare applications based on physiological signals: A review

BACKGROUND AND OBJECTIVE

We have cast the net into the ocean of knowledge to retrieve the latest scientific research on deep learning methods for physiological signals. We found 53 research papers on this topic, published from 01.01.2008 to 31.12.2017.

METHODS

An initial bibliometric analysis shows that the reviewed papers focused on Electromyogram(EMG), Electroencephalogram(EEG), Electrocardiogram(ECG), and Electrooculogram(EOG). These four categories were used to structure the subsequent content review.

RESULTS

During the content review, we understood that deep learning performs better for big and varied datasets than classic analysis and machine classification methods. Deep learning algorithms try to develop the model by using all the available input.

CONCLUSIONS

This review paper depicts the application of various deep learning algorithms used till recently, but in future it will be used for more healthcare areas to improve the quality of diagnosis.

Automated characterization of cardiovascular diseases using relative wavelet nonlinear features extracted from ECG signals

Cardiovascular diseases (CVDs) are the leading cause of deaths worldwide. The rising mortality rate can be reduced by early detection and treatment interventions. Clinically, electrocardiogram (ECG) signal provides useful information about the cardiac abnormalities and hence employed as a diagnostic modality for the detection of various CVDs. However, subtle changes in these time series indicate a particular disease. Therefore, it may be monotonous, time-consuming and stressful to inspect these ECG beats manually. In order to overcome this limitation of manual ECG signal analysis, this paper uses a novel discrete wavelet transform (DWT) method combined with nonlinear features for automated characterization of CVDs. ECG signals of normal, and dilated cardiomyopathy (DCM), hypertrophic cardiomyopathy (HCM) and myocardial infarction (MI) are subjected to five levels of DWT. Relative wavelet of four nonlinear features such as fuzzy entropy, sample entropy, fractal dimension and signal energy are extracted from the DWT coefficients. These features are fed to sequential forward selection (SFS) technique and then ranked using ReliefF method. Our proposed methodology achieved maximum classification accuracy (acc) of 99.27%, sensitivity (sen) of 99.74%, and specificity (spec) of 98.08% with K-nearest neighbor (kNN) classifier using 15 features ranked by the ReliefF method. Our proposed methodology can be used by clinical staff to make faster and accurate diagnosis of CVDs. Thus, the chances of survival can be significantly increased by early detection and treatment of CVDs.

Automated EEG-based screening of depression using deep convolutional neural network

In recent years, advanced neurocomputing and machine learning techniques have been used for Electroencephalogram (EEG)-based diagnosis of various neurological disorders. In this paper, a novel computer model is presented for EEG-based screening of depression using a deep neural network machine learning approach, known as Convolutional Neural Network (CNN). The proposed technique does not require a semi-manually-selected set of features to be fed into a classifier for classification. It learns automatically and adaptively from the input EEG signals to differentiate EEGs obtained from depressive and normal subjects. The model was tested using EEGs obtained from 15 normal and 15 depressed patients. The algorithm attained accuracies of 93.5% and 96.0% using EEG signals from the left and right hemisphere, respectively. It was discovered in this research that the EEG signals from the right hemisphere are more distinctive in depression than those from the left hemisphere. This discovery is consistent with recent research and revelation that the depression is associated with a hyperactive right hemisphere. An exciting extension of this research would be diagnosis of different stages and severity of depression and development of a Depression Severity Index (DSI).

Towards precision medicine: from quantitative imaging to radiomics

Radiology (imaging) and imaging-guided interventions, which provide multi-parametric morphologic and functional information, are playing an increasingly significant role in precision medicine. Radiologists are trained to understand the imaging phenotypes, transcribe those observations (phenotypes) to correlate with underlying diseases and to characterize the images. However, in order to understand and characterize the molecular phenotype (to obtain genomic information) of solid heterogeneous tumours, the advanced sequencing of those tissues using biopsy is required. Thus, radiologists image the tissues from various views and angles in order to have the complete image phenotypes, thereby acquiring a huge amount of data. Deriving meaningful details from all these radiological data becomes challenging and raises the big data issues. Therefore, interest in the application of radiomics has been growing in recent years as it has the potential to provide significant interpretive and predictive information for decision support. Radiomics is a combination of conventional computer-aided diagnosis, deep learning methods, and human skills, and thus can be used for quantitative characterization of tumour phenotypes. This paper discusses the overview of radiomics workflow, the results of various radiomics-based studies conducted using various radiological images such as computed tomography (CT), magnetic resonance imaging (MRI), and positron-emission tomography (PET), the challenges we are facing, and the potential contribution of radiomics towards precision medicine.

Automated retinal health diagnosis using pyramid histogram of visual words and Fisher vector techniques

Untreated age-related macular degeneration (AMD), diabetic retinopathy (DR), and glaucoma may lead to irreversible vision loss. Hence, it is essential to have regular eye screening to detect these eye diseases at an early stage and to offer treatment where appropriate. One of the simplest, non-invasive and cost-effective techniques to screen the eyes is by using fundus photo imaging. But, the manual evaluation of fundus images is tedious and challenging. Further, the diagnosis made by ophthalmologists may be subjective. Therefore, an objective and novel algorithm using the pyramid histogram of visual words (PHOW) and Fisher vectors is proposed for the classification of fundus images into their respective eye conditions (normal, AMD, DR, and glaucoma). The proposed algorithm extracts features which are represented as words. These features are built and encoded into a Fisher vector for classification using random forest classifier. This proposed algorithm is validated with both blindfold and ten-fold cross-validation techniques. An accuracy of 90.06% is achieved with the blindfold method, and highest accuracy of 96.79% is obtained with ten-fold cross-validation. The highest classification performance of our system shows the potential of deploying it in polyclinics to assist healthcare professionals in their initial diagnosis of the eye. Our developed system can reduce the workload of ophthalmologists significantly.

Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals

An encephalogram (EEG) is a commonly used ancillary test to aide in the diagnosis of epilepsy. The EEG signal contains information about the electrical activity of the brain. Traditionally, neurologists employ direct visual inspection to identify epileptiform abnormalities. This technique can be time-consuming, limited by technical artifact, provides variable results secondary to reader expertise level, and is limited in identifying abnormalities. Therefore, it is essential to develop a computer-aided diagnosis (CAD) system to automatically distinguish the class of these EEG signals using machine learning techniques. This is the first study to employ the convolutional neural network (CNN) for analysis of EEG signals. In this work, a 13-layer deep convolutional neural network (CNN) algorithm is implemented to detect normal, preictal, and seizure classes. The proposed technique achieved an accuracy, specificity, and sensitivity of 88.67%, 90.00% and 95.00%, respectively.

Biotransformation of (-)-(1R,4S)-Menthone and (+)-(1S,4R)-Menthone by the Common Cutworm Spodoptera litura Larvae

Using biotransformation as a biocatalytic process has the advantage of being able to proceed under mild conditions and with high regio- and enantioselectivity. This study investigated the biotransformation of (-)-(1R,4S)-menthone (1) and (+)-(1S,4R)-menthone (2) by Spodoptera litura larvae. Compound 1 was converted to (-)-(1R,4S)-7-hydroxymenthone (1-1), (+)-(1R,3S,4S)-7-hydroxyneomenthol (1-2) and (-)-(1R,4S,8R)-p-menth-3-one-9-oic acid (1-3). The metabolism of substrate 2 generated three enantiomers of the above metabolites, designated as 2-1 to 2-3, respectively. The C-9 position of (-)-menthone and (+)-menthone was oxidized to carboxylic acid by S. litura, which is a metabolic pathway not observed in any other example of biocatalysis.

Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions

Thyroid is a small gland situated at the anterior side of the neck and one of the largest glands of the endocrine system. The abrupt cell growth or malignancy in the thyroid gland may cause thyroid cancer. Ultrasound images distinctly represent benign and malignant lesions, but accuracy may be poor due to subjective interpretation. Computer Aided Diagnosis (CAD) can minimize the errors created due to subjective interpretation and assists to make fast accurate diagnosis. In this work, fusion of Spatial Gray Level Dependence Features (SGLDF) and fractal textures are used to decipher the intrinsic structure of benign and malignant thyroid lesions. These features are subjected to graph based Marginal Fisher Analysis (MFA) to reduce the number of features. The reduced features are subjected to various ranking methods and classifiers. We have achieved an average accuracy, sensitivity and specificity of 97.52%, 90.32% and 98.57% respectively using Support Vector Machine (SVM) classifier. The achieved maximum Area Under Curve (AUC) is 0.9445. Finally, Thyroid Clinical Risk Index (TCRI) a single number is developed using two MFA features to discriminate the two classes. This prototype system is ready to be tested with huge diverse database.