scholarly journals Machine Learning Applied to Diagnosis of Human Diseases: A Systematic Review

2020 ◽  
Vol 10 (15) ◽  
pp. 5135
Author(s):  
Nuria Caballé-Cervigón ◽  
José L. Castillo-Sequera ◽  
Juan A. Gómez-Pulido ◽  
José M. Gómez-Pulido ◽  
María L. Polo-Luque
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
English Language ◽  
Data Extraction ◽  
Real Life ◽  
Human Diseases ◽  
Machine Learning Techniques ◽  
Comprehensive Overview ◽  
Advantages And Disadvantages ◽  
Journal Citation Reports

Human healthcare is one of the most important topics for society. It tries to find the correct effective and robust disease detection as soon as possible to patients receipt the appropriate cares. Because this detection is often a difficult task, it becomes necessary medicine field searches support from other fields such as statistics and computer science. These disciplines are facing the challenge of exploring new techniques, going beyond the traditional ones. The large number of techniques that are emerging makes it necessary to provide a comprehensive overview that avoids very particular aspects. To this end, we propose a systematic review dealing with the Machine Learning applied to the diagnosis of human diseases. This review focuses on modern techniques related to the development of Machine Learning applied to diagnosis of human diseases in the medical field, in order to discover interesting patterns, making non-trivial predictions and useful in decision-making. In this way, this work can help researchers to discover and, if necessary, determine the applicability of the machine learning techniques in their particular specialties. We provide some examples of the algorithms used in medicine, analysing some trends that are focused on the goal searched, the algorithm used, and the area of applications. We detail the advantages and disadvantages of each technique to help choose the most appropriate in each real-life situation, as several authors have reported. The authors searched Scopus, Journal Citation Reports (JCR), Google Scholar, and MedLine databases from the last decades (from 1980s approximately) up to the present, with English language restrictions, for studies according to the objectives mentioned above. Based on a protocol for data extraction defined and evaluated by all authors using PRISMA methodology, 141 papers were included in this advanced review.

Machine Learning Based Assembly of Fragments of Ancient Papyrus

2021 ◽  
Vol 14 (3) ◽  
pp. 1-21
Author(s):  
Roy Abitbol ◽  
Ilan Shimshoni ◽  
Jonathan Ben-Dov
Keyword(s):  
Machine Learning ◽  
Spatial Information ◽  
Real Life ◽  
Dead Sea ◽  
Machine Learning Techniques ◽  
Automated Classification ◽  
Learning Techniques ◽  
Test Batch ◽  
Validation Set ◽  
Local Edge

The task of assembling fragments in a puzzle-like manner into a composite picture plays a significant role in the field of archaeology as it supports researchers in their attempt to reconstruct historic artifacts. In this article, we propose a method for matching and assembling pairs of ancient papyrus fragments containing mostly unknown scriptures. Papyrus paper is manufactured from papyrus plants and therefore portrays typical thread patterns resulting from the plant’s stems. The proposed algorithm is founded on the hypothesis that these thread patterns contain unique local attributes such that nearby fragments show similar patterns reflecting the continuations of the threads. We posit that these patterns can be exploited using image processing and machine learning techniques to identify matching fragments. The algorithm and system which we present support the quick and automated classification of matching pairs of papyrus fragments as well as the geometric alignment of the pairs against each other. The algorithm consists of a series of steps and is based on deep-learning and machine learning methods. The first step is to deconstruct the problem of matching fragments into a smaller problem of finding thread continuation matches in local edge areas (squares) between pairs of fragments. This phase is solved using a convolutional neural network ingesting raw images of the edge areas and producing local matching scores. The result of this stage yields very high recall but low precision. Thus, we utilize these scores in order to conclude about the matching of entire fragments pairs by establishing an elaborate voting mechanism. We enhance this voting with geometric alignment techniques from which we extract additional spatial information. Eventually, we feed all the data collected from these steps into a Random Forest classifier in order to produce a higher order classifier capable of predicting whether a pair of fragments is a match. Our algorithm was trained on a batch of fragments which was excavated from the Dead Sea caves and is dated circa the 1st century BCE. The algorithm shows excellent results on a validation set which is of a similar origin and conditions. We then tried to run the algorithm against a real-life set of fragments for which we have no prior knowledge or labeling of matches. This test batch is considered extremely challenging due to its poor condition and the small size of its fragments. Evidently, numerous researchers have tried seeking matches within this batch with very little success. Our algorithm performance on this batch was sub-optimal, returning a relatively large ratio of false positives. However, the algorithm was quite useful by eliminating 98% of the possible matches thus reducing the amount of work needed for manual inspection. Indeed, experts that reviewed the results have identified some positive matches as potentially true and referred them for further investigation.

scholarly journals 3DP Printing of Oral Solid Formulations: A Systematic Review

Pharmaceutics ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 358 ◽  
Author(s):  
Chiara R. M. Brambilla ◽  
Ogochukwu Lilian Okafor-Muo ◽  
Hany Hassanin ◽  
Amr ElShaer
Keyword(s):  
Systematic Review ◽  
Data Extraction ◽  
New Technology ◽  
Three Dimensional ◽  
Extraction Process ◽  
Carcinogenic Risk ◽  
Drug Dissolution ◽  
Dissolution Profile ◽  
Disintegration Time ◽  
Advantages And Disadvantages

Three-dimensional (3D) printing is a recent technology, which gives the possibility to manufacture personalised dosage forms and it has a broad range of applications. One of the most developed, it is the manufacture of oral solid dosage and the four 3DP techniques which have been more used for their manufacture are FDM, inkjet 3DP, SLA and SLS. This systematic review is carried out to statistically analyze the current 3DP techniques employed in manufacturing oral solid formulations and assess the recent trends of this new technology. The work has been organised into four steps, (1) screening of the articles, definition of the inclusion and exclusion criteria and classification of the articles in the two main groups (included/excluded); (2) quantification and characterisation of the included articles; (3) evaluation of the validity of data and data extraction process; (4) data analysis, discussion, and conclusion to define which technique offers the best properties to be applied in the manufacture of oral solid formulations. It has been observed that with SLS 3DP technique, all the characterisation tests required by the BP (drug content, drug dissolution profile, hardness, friability, disintegration time and uniformity of weight) have been performed in the majority of articles, except for the friability test. However, it is not possible to define which of the four 3DP techniques is the most suitable for the manufacture of oral solid formulations, because the selection is affected by different parameters, such as the type of formulation, the physical-mechanical properties to achieve. Moreover, each technique has its specific advantages and disadvantages, such as for FDM the biggest challenge is the degradation of the drug, due to high printing temperature process or for SLA is the toxicity of the carcinogenic risk of the photopolymerising material.

Applicability of machine learning techniques in food intake assessment: A systematic review

2021 ◽  
pp. 1-18
Author(s):  
Larissa Oliveira Chaves ◽  
Ana Luiza Gomes Domingos ◽  
Daniel Louzada Fernandes ◽  
Fabio Ribeiro Cerqueira ◽  
Rodrigo Siqueira-Batista ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Food Intake ◽  
Machine Learning Techniques ◽  
Intake Assessment ◽  
Learning Techniques

Systematic review of interventions to improve gender equity in graduate medicine

2021 ◽  
pp. postgradmedj-2020-138864
Author(s):  
Sinéad Lydon ◽  
Emily O'Dowd ◽  
Chloe Walsh ◽  
Angela O'Dea ◽  
Dara Byrne ◽  
...  
Keyword(s):  
Systematic Review ◽  
Gender Equity ◽  
English Language ◽  
Clinical Medicine ◽  
Data Extraction ◽  
Self Report ◽  
Clinical Settings ◽  
Reference List ◽  
High Quality Research ◽  
Work Settings

Women are substantially underrepresented in senior and leadership positions in medicine and experience gendered challenges in their work settings. This systematic review aimed to synthesise research that has evaluated interventions for improving gender equity in medicine. English language electronic searches were conducted across MEDLINE, CINAHL, Academic Search Complete, PsycINFO and Web of Science. Reference list screening was also undertaken. Peer-reviewed studies published between 2000 and March 2020 that evaluated interventions to improve gender equity, or the experiences of women, in academic or clinical medicine were reviewed. Dual reviewer data extraction on setting, participants, type of intervention, measurement and outcomes was completed. Methodological rigour and strength of findings were evaluated. In total, 34 studies were included. Interventions were typically focused on equipping the woman (82.4%), that is, delivering professional development activities for women. Fewer focused on changing cultures (20.6%), ensuring equal opportunities (23.5%) or increasing the visibility or valuing of women (23.5%). Outcomes were largely positive (87.3%) but measurement typically relied on subjective, self-report data (69.1%). Few interventions were implemented in clinical settings (17.6%). Weak methodological rigour and a low strength of findings was observed. There has been a focus to-date on interventions which Equip the Woman. Interventions addressing systems and culture change require further research consideration. However, institutions cannot wait on high quality research evidence to emerge to take action on gender equity. Data collated suggest a number of recommendations pertaining to research on, and the implementation of, interventions to improve gender equity in academic and clinical settings.

scholarly journals Factors Associated with Disease Severity and Mortality among Patients with Coronavirus Disease 2019: A Systematic Review and Meta-Analysis

2020 ◽  
Author(s):  
Vignesh Chidambaram ◽  
Nyan Lynn Tun ◽  
Waqas Haque ◽  
Marie Gilbert Majella ◽  
Ranjith Kumar Sivakumar ◽  
...  
Keyword(s):  
Systematic Review ◽  
Disease Severity ◽  
English Language ◽  
Clinical Decision Making ◽  
Clinical Laboratory ◽  
Data Extraction ◽  
Meta Analysis ◽  
Severe Disease ◽  
Factors Associated ◽  
Risk Of Mortality

Background: Understanding the factors associated with disease severity and mortality in Coronavirus disease (COVID19) is imperative to effectively triage patients. We performed a systematic review to determine the demographic, clinical, laboratory and radiological factors associated with severity and mortality in COVID-19. Methods: We searched PubMed, Embase and WHO database for English language articles from inception until May 8, 2020. We included Observational studies with direct comparison of clinical characteristics between a) patients who died and those who survived or b) patients with severe disease and those without severe disease. Data extraction and quality assessment were performed by two authors independently. Results: Among 15680 articles from the literature search, 109 articles were included in the analysis. The risk of mortality was higher in patients with increasing age, male gender (RR 1.45; 95%CI 1.23,1.71), dyspnea (RR 2.55; 95%CI 1.88,2.46), diabetes (RR 1.59; 95%CI 1.41,1.78), hypertension (RR 1.90; 95%CI 1.69,2.15). Congestive heart failure (OR 4.76; 95%CI 1.34,16.97), hilar lymphadenopathy (OR 8.34; 95%CI 2.57,27.08), bilateral lung involvement (OR 4.86; 95%CI 3.19,7.39) and reticular pattern (OR 5.54; 95%CI 1.24,24.67) were associated with severe disease. Clinically relevant cut-offs for leukocytosis(>10.0 x109/L), lymphopenia(< 1.1 x109/L), elevated C-reactive protein(>100mg/L), LDH(>250U/L) and D-dimer(>1mg/L) had higher odds of severe disease and greater risk of mortality. Conclusion: Knowledge of the factors associated of disease severity and mortality identified in our study may assist in clinical decision-making and critical-care resource allocation for patients with COVID-19.

scholarly journals Cancer services during the COVID-19 pandemic: systematic review of patients' and caregivers' experiences

2021 ◽  
Author(s):  
Symran Dhada ◽  
Derek Stewart ◽  
Ejaz Cheema ◽  
Muhammed Abdul Hadi ◽  
Vibhu Paudyal
Keyword(s):  
Systematic Review ◽  
Cancer Screening ◽  
Cancer Patients ◽  
English Language ◽  
Resource Constraints ◽  
Data Extraction ◽  
Psychological Wellbeing ◽  
Cancer Services ◽  
Data Extraction Form ◽  
The Impact

Background Cancer patients have faced intersecting crises in the face of COVID-19 pandemic. This review aimed to examine patients' and caregivers' experiences of accessing cancer services during the COVID-19 pandemic and perceived impact of the pandemic on their psychological wellbeing. Methods A protocol-led (CRD42020214906) systematic review was conducted by searching six databases including EMBASE, MEDLINE and CINAHL for articles published in English-language between 1/2020-12/2020. Data were extracted using a pilot-tested, structured data extraction form. Thematic synthesis of data was undertaken and reported as per the PRISMA guideline. Results A total of 1110 articles were screened of which 19 studies met the inclusion criteria. Studies originated from 10 different countries including the US, UK, India and China. Several themes were identified which were categorised into seven categories. Postponement and delays in cancer screening and treatment, drug shortages and inadequate nursing care were commonly experienced by patients. Hospital closures, resource constraints, national lockdowns and patient reluctance to use health services because of infection worries contributed to the delay. Financial and social distress, isolation; and spiritual distress due to the uncertainty of rites as well as fulfilment of last wishes were also commonly reported. Caregivers felt anxious about infecting cancer patients with COVID-19. Conclusions Patients and caregivers experienced extensive impact of COVID-19 on cancer screening, treatment and care, and their own psychological wellbeing. Patient and caregiver views and preferences should be incorporated in ensuring resilient cancer services that can minimise the impact of ongoing and future pandemic on cancer care and mitigate patient fears.

scholarly journals The effective interventions to improve long-term physiotherapy exercise adherence among patients with lower limb osteoarthritis. A systematic review

2021 ◽  
Author(s):  
Pathmanathan Cinthuja ◽  
Nidhya Krishnamoorthy ◽  
Gamalendira Shivapatham
Keyword(s):  
Systematic Review ◽  
Lower Limb ◽  
English Language ◽  
Data Extraction ◽  
Exercise Adherence ◽  
Case Control Studies ◽  
Eligibility Criteria ◽  
Cross Sectional ◽  
Booster Sessions

Abstract Introduction: Osteoarthritis (OA) is a chronic condition that severely effects work life balance impacting psychosocial and socio-economic aspects. Physiotherapy exercise is one of the intervention methods for the management of OA. Adherence to the exercise by patients is essential for the effective management of OA. Objectives: To determine different methods used to enhance physiotherapy exercise adherence for more than 12 months among patients with osteoarthritis and to report the effective method to enhance exercise adherence among people with lower limb osteoarthritis. Design: Systematic review Methods: PubMed, Pedro, Web of Science, and EMBASE databases searched for randomized controlled trials, cohort studies, case-control studies, and cross-sectional studies published in the English language from 2000 to 2020. The date of data extraction was 04 September 2020. Two independent researchers conducted literature search, assessed eligibility, extracted data, conducted methodology quality assessment using the PEDro scale, and conducted risk of bias assessment. A narrative synthesis of key outcomes is presented; preferred Reporting Items for Systematic review was used to report the review. The study protocol was registered in the Prospero (Prospero ID: CRD42020205653). Results: The primary search strategy identified 5839 potentially relevant articles, of which 5157 remained after discarding duplicates. After screening based on title and abstract, 40 papers were potentially eligible for inclusion. Five of these papers met all predefined eligibility criteria. Introducing methods to enhance exercise adherence has caused a significant increase in exercise adherence for the short term (less than six months or 12 months). There were no significant differences, long-term adherence with different methods, reported. The results indicate that booster sessions (89.69%) and telephone-linked communication (86%) had higher percentages for the exercise adherence. Secondary outcomes such as pain, stiffness, function, show positive outcomes with increasing exercise adherence. However, there were no significant differences reported. Conclusion: The booster sessions and telephone-linked communication appear to enhance exercise adherence for more than 12 months among patients with osteoarthritis. However, a number of high-quality studies are inadequate to confirm our findings. Therefore, more studies with higher methodological quality are needed to determine the best strategies to enhance long-term exercise adherence among people with osteoarthritis. Key terms: Osteoarthritis, Long term, Exercise adherence

Reduction of ileocolic intussusception under sedation or anaesthesia: a systematic review of complications

2021 ◽  
pp. archdischild-2021-322706
Author(s):  
Moran Gal ◽  
Shirly Gamsu ◽  
Ron Jacob ◽  
Daniel M Cohen ◽  
Itai Shavit
Keyword(s):  
Systematic Review ◽  
Intestinal Perforation ◽  
English Language ◽  
Data Extraction ◽  
Current Data ◽  
Pulmonary Aspiration ◽  
Ileocolic Intussusception ◽  
Newcastle Ottawa Scale ◽  
Permanent Neurological Deficit ◽  
Ottawa Scale

BackgroundDespite the increased use of sedation in children undergoing stressful procedures, reduction of ileocolic intussusception (RII) is usually performed on awake children without any form of sedation.ObjectiveTo evaluate the incidence of severe complications of RII under sedation or anaesthesia.DesignA systematic review including English language original articles of any date.PatientsChildren undergoing RII (pneumatic or hydrostatic) under sedation or anaesthesia.Data sourcesOvid Embase, Scopus, PubMed, the Cochrane Database of Systematic Reviews and the internet search engine Google Scholar.Data extractionThree authors independently reviewed each article for eligibility. The Newcastle-Ottawa Scale was used to assess the quality of included studies.Main outcome measuresThe primary outcome was the incidence of intestinal perforation during RII. The secondary outcomes were the incidence of sentinel adverse events defined as death, cardiopulmonary resuscitation, permanent neurological deficit and pulmonary aspiration syndrome.ResultsThe search yielded 368 articles. Nine studies with 1391 cases were included in the analysis. Of the nine studies, six had a score of ≤6 stars in the Newcastle-Ottawa Scale assessment, indicating low-to-moderate quality. Propofol-based sedation was used in 849 (59.2%) cases; 5 (0.6%) had intestinal perforation. Intestinal perforation was not reported in patients who were sedated with other sedatives. One patient had pulmonary aspiration syndrome.ConclusionsAlthough caution remains warranted, current data suggest that the incidence of severe complications due to RII under sedation or anaesthesia is low. Due to the lack of prospective data, it is difficult to ascertain the exact incidence of severe complications.

Sign in / Sign up

Export Citation Format

Share Document