New York, An Indian-origin researcher in the US has developed an artificial intelligence (AI) algorithm that promises to accurately diagnose Alzheimer's without the need for expensive scans or in-person testing.
The software not only can diagnose Alzheimer's with more than 95 percent accuracy but is also capable of explaining its conclusions, allowing physicians to double-check the accuracy of its diagnosis. "This is a real breakthrough," said the tool's creator KP Subbalakshmi from the Stevens Institute of Technology in the US.
"We're opening an exciting new field of research, and making it far easier to explain to patients why the AI came to the conclusion that it did while diagnosing patients," she added.
By designing an explainable AI engine that uses attention mechanisms and convolutional neural network, the team was able to develop software that could accurately identify well-known telltale signs of Alzheimer's.
The team trained the algorithm using texts produced by both healthy subjects and known Alzheimer's sufferers as they described a drawing of children stealing cookies from a jar.
Using tools developed by Google, Subbalakshmi and her team converted each individual sentence into a unique numerical sequence, or vector, representing a specific point in a 512-dimensional space.
Such an approach allows even complex sentences to be assigned a concrete numerical value, making it easier to analyse structural and thematic relationships between sentences. By using those vectors along with handcrafted features, the AI system gradually learned to spot similarities and differences between sentences spoken by healthy or unhealthy subjects.
"This is absolutely state-of-the-art. Our AI software is the most accurate diagnostic tool currently available while also being explainable," Subbalakshmi said.
The system can also easily incorporate new criteria that may be identified by other research teams in the future, so it will only get more accurate over time. "We designed our system to be both modular and transparent," Subbalakshmi said
"If other researchers identify new markers of Alzheimer's, we can simply plug those into our architecture to generate even better results," she added. The study was presented at the 19th International Workshop on Data Mining in Bioinformatics at BioKDD.
Sydney, June 29 (IANS) Researchers have found that artificial intelligence (AI) improves skin cancer diagnostic accuracy when used in collaboration with human clinical checks.The research team tested for the first time if a 'real world' collaborative approach involving clinicians assisted by AI improved the accuracy of skin cancer clinical decision making."This is important because AI decision support has slowly started to infiltrate healthcare settings, and yet few studies have tested its performance in the real world settings or how clinicians interact with it," said study researcher Monika Janda from the University of Queensland in Australia.For the findings, published in the journal 'Nature Medicine', the researchers trained and tested an artificial convolutional neural network to analyse pigmented skin lesions, and compared the findings to human evaluations on three types of AI-based decision support.The study found that the highest diagnostic accuracy was achieved when crowd wisdom and AI predictions were combined, suggesting human-AI and crowd-AI collaborations were preferable to individual experts or AI alone.Inexperienced evaluators gained the highest benefit from AI decision support and expert evaluators confident in skin cancer diagnosis achieved modest or no benefit, the researchers said.These findings indicated a combined AI-human approach to skin cancer diagnosis may be the most relevant for clinicians in the future.Although AI diagnostic software has demonstrated expert-level accuracy in several image-based medical studies, researchers have remained unclear on whether its use improved clinical practice."Our study found that good quality AI support was useful to clinicians but needed to be simple, and in accordance with a given task," Janda said."For clinicians of the future, this means that AI-based screening and diagnosis might soon be available to support them on a daily basis," Janda added.Implementation of any AI software needs extensive testing to understand the impact it has on clinical decision making, the study noted.--IANSbu/arm
Hyderabad, June 12 (IANS) A new genetic tool could pave the way for better diagnosis and treatment of diabetes among Indians, shows a study conducted by the CSIR-Centre for Cellular & Molecular Biology (CCMB), Hyderabad.A new publication by researchers at the KEM Hospital, Pune, CSIR-CCMB, and the University of Exeter in the UK shows that a genetic risk score is effective in diagnosing type 1 diabetes in Indians.The genetic risk score, developed by the University of Exeter, considers detailed genetic information known to increase the chance of developing type 1 diabetes. The score may be used at the time of diabetes diagnosis to help decide if someone has type 1 diabetes.The authors found nine genetic areas (called the SNPs) that correlate with type 1 diabetes both in Indian and European populations, and can be used to predict the onset of type 1 diabetes in Indians."It's interesting to note that different SNPs are more abundant among Indian and European patients. This opens up the possibility that environmental factors might be interacting with these SNPs to cause the disease," said G.R. Chandak, the Chief Scientist leading the study at the CSIR-CCMB."Since more than 20 per cent of people with type 1 diabetes below the age of 15 years of age are in India, developing a genetic test kit to reliably detect type 1 from type 2 diabetes holds a lot of significance for the country," said Rakesh K. Mishra, Director at CSIR-CCMB.Until recently, it was widely believed that type 1 diabetes appeared in children and adolescents, and type 2 diabetes in obese and older people (typically after 45 years of age).However, recent findings have shown that type 1 diabetes can occur later in life, while type 2 diabetes is on the rise among younger and thinner Indians.Distinguishing the two types of diabetes has become more complex. The two types follow different treatment regime with type 1 diabetes needing lifelong insulin injection but type 2 diabetes are often managed with proper diet or tablet treatment.In a paper published in Scientific Reports, researchers have analysed whether the European risk score is effective in diagnosing type 1 diabetes in Indians.The team studied people with diabetes from Pune. It analysed 262 people with type 1 diabetes, 352 people with type 2 diabetes, and 334 people without diabetes. All were of Indian (Indo-European) ancestry.The outcomes from the Indian populations were compared to those of Europeans from the Wellcome Trust Case Control Consortium study.The research found that the test is effective in diagnosing the right type of diabetes in Indians, even in its current form, which is based on European data.Authors also found genetic differences between the populations which mean the test could be further improved to enhance outcomes for Indian populations."Diagnosing the right diabetes type is an increasingly difficult challenge for clinicians, as we now know that type 1 diabetes can occur at any age. This task is even harder in India, as more cases of type 2 diabetes occur in people with low BMI. We now know that our genetic risk score is an effective tool for Indians, and can help get people on the treatment they need to avoid life threatening complications such as diabetic ketoacidosis and to achieve the best health outcomes," said Richard Oram of the University of Exeter Medical School."We look forward to using this test in diabetic patients from different parts of India where the physical characteristics of diabetic patients differ from the standard description," said Chittaranjan Yajnik of the KEM Hospital & Research Centre.--IANSms/arm
New Delhi, June 9 (IANS) Scientists in India and Japan have developed a highly accurate machine tool to help clinicians choose the most effective treatment strategy for patients with glioma brain tumour.A new machine learning approach classifies a common type of brain tumour into low or high grades with almost 98 per cent accuracy, researchers reported in the journal IEEE Access. "Our method outperformed other state-of-the-art approaches for predicting glioma grades from brain MRI scans. This is quite considerable," said study researcher Balasubramanian Raman from the Indian Institute of Technology Roorkee (IIT-R).According to the researchers, gliomas are a common type of brain tumour affecting glial cells, which provide support and insulation for neurons.The treatment varies depending on the tumour's aggressiveness, so it's important to get the diagnosis right for each individual. Radiologists obtain a very large amount of data from MRI scans to reconstruct a 3D image of the scanned tissue. Much of the data available in the MRI scans cannot be detected by the naked eye, such as details related to the tumour shape, texture, or the image's intensity. Artificial intelligence (AI) algorithms help extract this data. Medical oncologists have been using this approach, called radiomics, to improve patient diagnoses, but its accuracy still needs to be enhanced.For the current study, Kyoto University's Institute for Integrated Cell-Material Sciences (iCeMS, Japan) bioengineer Ganesh Pandian Namasivayam collaborated with Indian data scientist Raman to develop a machine learning approach that can classify gliomas into low or high grade with 97.54 per cent accuracy.The choice of patient treatment largely depends on being able to determine glioma's grading. The team, including Rahul Kumar, Ankur Gupta and Harkirat Singh Arora, used a dataset from MRI scans belonging to 210 people with high-grade glioma and another 75 with low-grade glioma. They developed an approach called CGHF, which stands for: A computational decision support system for glioma classification using hybrid radiomics and stationary wavelet-based features. They chose specific algorithms for extracting features from some of the MRI scans and then trained another predictive algorithm to process this data and classify the gliomas. They then tested their model on the rest of the MRI scans to assess its accuracy. The method outperformed other approaches for predicting glioma grades from brain MRI scans. "We hope AI helps develop a semi-automatic or automatic machine predictive software model that can help doctors, radiologists, and other medical practitioners tailor the best approaches for their individual patients," Ganesh said.--IANSbu/arm
New Delhi, May 27 (IANS) Union Health Minister Harsh Vardhan on Wednesday said that the CSIR-Indian Institute of Integrative Medicine, Jammu, a constituent lab of the Council of Scientific and Industrial Research (CSIR) is to develop and scale up a new Reverse Transcriptase-Loop Mediated Isothermal Amplification (RT-LAMP) based COVID-19 diagnostic kit.The lab has partnered with Reliance Industries Limited (RIL) for the venture.Taking it to Twitter, the Minister said: "CSIR-Indian Institute of Integrative Medicine, Jammu a constituent lab of @CSIR_IND has partnered with RIL to develop & scale-up a new Reverse Transcriptase-Loop Mediated Isothermal Amplification (RT-LAMP) based #COVID19 diagnostic kit."The Minister also said that the RT-LAMP test is rapid, accurate and cost effective that can be done with indigenous components and set up with minimal expertise and instrumentation. India is constantly ramping up its testing infrastructure, along with indegenous development, validation and production of testing kits for RT-PCR in order to have early and aggressive tracing of the infection by validating TrueNat-based test for COVID-19 and including alternative testing platforms like CBNAAT/GeneXpert and Abott HIV viral load testing machines.--IANSsfm/prs
दुनियाभर में कहर बरपा रहे घातक कोरोनावायरस का प्रकोप देश में गहराने की आशंकाओं के मद्देजनर केंद्र एवं राज्य सरकारों की ओर से एहतियाती कदम उठाने के साथ-साथ वायरस के संक्रमण की जांच की सुविधा बढ़ा दी गई है। केंद्रीय स्वास्थ्य एवं परिवार कल्याण मंत्री डॉ. हर्षवर्धन की अध्यक्षता में मंत्रिसमूह द्वारा इसकी लगातार निगरानी की जा रही है। भारतीय आयुर्विज्ञान अनुसंधान परिषद (आईसीएमआर) ने देशभर में अपनी 72 प्रयोगशालाओं में जांच की सुविधा बहरहाल मुहैया करवाई है।
देश में अब तक कोरोना वायरस के संक्रमण के 150 मामले सामने आ चुके हैं और इस घातक वायरस ने भारत में तीन लोगों की जान ले ली है। भारत में कोरोनावायरस के संक्रमण से मौत का पहला मामला कर्नाटक के कलबुर्गी में आया था, जहां लोगों में काफी घबराहट है। कलबुर्गी में कोरोनावायरस के संक्रमण से 76 साल के एक बुजुर्ग की मौत हो गई थी।
कलबुर्गी से सांसद डॉ. उमेश जी. जाधव वहां कोरोनावायरस संक्रमण की जांच के लिए स्थानीय प्रयोगशाला में सुविधा मुहैया करवाने के सिलसिले में आईसीएमआर पहुंचे थे। उन्होंने आईएएनएस को बताया कि इस घटना के बाद उनके क्षेत्र के लोगों में घबराहट है इसलिए वायरस की रोकथाम के मद्देनजर वह वायरस के परीक्षण की सुविधा जल्द उपलब्ध करवाना चाहते हैं।
भारत में अब तक जो मामले सामने आए हैं उनमें से ऐसे मरीज हैं जो या तो विदेशों की यात्रा से लौटे हैं या उनके निकट संपर्क में लोग हैं। मगर आशंका जताई जा रही है कि अगर इस वायरस का संचार देश में सामुदायिक स्तर पर होता है तो वह ज्यादा घातक स्थिति होगी।
आईसीएमआर से मिली जानकारी के अनुसार, इसके अलावा वैज्ञानिक एवं औद्योगिक अनुसंधान परिषद (सीएसआईआर) और बायोटेक्नोलोजी विभाग (डीबीटी), रक्षा अनुसंधान एवं विकास संगठन (डीआरडीओ) की 49 प्रयोशालाओं में भी कोरोनावायरस संक्रमण की जांच की सुविधा इस सप्ताह उपलब्ध करवाई जाएगी। इस प्रकार रोजाना 1,400 सैंपल की जांच की जा सकेगी।
आईसीएमआर उच्च गुणवत्ता युक्त निजी प्रयोगशालाओं में इसकी जांच की सुविधा मुहैया करवाने पर भी विचार कर रही है, जिनमें नेशनल एक्रिडेशन बोर्ड फॉर टेस्टिंग एंड कैलिब्रेशन लेबोरेटरीज को शामिल किया जा सकता है।
रीजनल मेडिकल रिसर्च सेंटर (आरएमआरसी), गोरखपुर के निदेशक एवं आईसीएमआर के रिसर्च मैनेजमेंट, पॉलिसी प्लानिंग एंड बायोमेडिकल कम्युनिकेशन प्रमुख डॉ. रजनीकांत श्रीवास्तव आईएएनएस से बातचीत में कहा कि कोरोनावायरस (कोविड-19) नई बीमारी है इसके संक्रमण के कारणों का अभी तक पता नहीं चला है, लेकिन संक्रमण चार चरणों में होता है। भारत में बहरहाल दूसरे चरण में है। उन्होंने कहा कि इसकी रोकथाम के लिए लोगों में जागरूकता काफी अहम है, जिससे इसके प्रसार पर रोक लगाई जा सकती है।
इसके अलावा देश में सांस की गंभीर बीमारी यानी सीवियर एक्यूट रेस्पिरेटरी इन्फेक्शन (एसएआरआई) व इन्फ्लूएंजा जैसी बीमारी से पीड़ित मरीजों की भी निगरानी की जा रही है ताकि सामुदायिक स्तर पर इस वायरस के प्रसार को रोका जा सके। इसके लिए 27 राज्यों में स्थित 52 क्षेत्रीय प्रयोगशालाओं में हर सप्ताह 20 सैंपल इकट्ठा कर उनमें कोरोना वायरस की जांच की जा रही है।
चीन से पैदा हुआ कोरोनावायरस का प्रकोप पूरी दुनिया में कहर बरपा रहा है और इस वायरस से चीन के बाद सबसे ज्यादा प्रभावित इटली हुआ है जहां 2,500 से अधिक लोगों की मौत हो चुकी है जबकि 31,500 से ज्यादा मामले सामने आए हैं। दुनिया के तकरीब 140 देशों में कोरोना वायरस से संक्रमित लोगों की तादाद तकरीबन 1,84,900 हो गई है जबकि 7,500 से अधिक लोगों की मौत हो चुकी है। (एजेंसी)
Dear Patron, Please provide additional information to validate your profile and continue to participate in engagement activities and purchase medicine.