Diagnose Archives - InnoHEALTH magazine

Advanced AI for medical image analysis to detect and diagnose the early stages of critical diseases

InnoHEALTH magazine digital team — Fri, 08 Jul 2022 04:45:00 +0000

According to the report published in 2021 by global cancer statistics, the world’s new cancer cases have reached 19.3 million, and lung cancer is the second largest cause of cancer after female breast cancer.

Among all the other deadliest diseases, cancer is the most lethal cause of death, which may occur in various types and regions inside the human body. It arises due to uncontrolled cellular functionality that happens when cells start working independently and performing odd behaviors compared to their surrounding structures. When it occurs in the lung region, it creates a severe condition, as lung cancer’s survival rate is lowest compared to other types of cancer. According to the report published in 2021 by global cancer statistics, the world’s new cancer cases have reached 19.3 million, and lung cancer is the second largest cause of cancer after female breast cancer. In various research studies, it has been found that early cancer detection may increase the chances of long-term survival.

Furthermore, studies have indicated that a low dose CT scan and its automated analysis can be the best way of early cancer detection. It works without putting the human body in harm compared to other invasive procedures. Analyzing CT images to get insights into internal structure and abnormality has been vastly carried out by experts and radiologists in previous days. But due to the consistent efforts of researchers, artificial intelligence (AI) based disease detection systems have been gaining the direct attention of clinical practitioners and medical institutes for the past two decades. With increasing structured data in the medical field, more opportunities for finding precise and straightforward methods of diagnosis are opening. The modern world where we live now is just embarking on the long and exciting data science journey that can lead us towards unimaginable peaks of automated technological solutions. It is yet unclear how precise the medical technology would be in detecting and diagnosing diseases at their early stage. Perhaps, the advanced algorithm defines the upcoming health issues before their occurrence in the human body. It allows someone to take corrective feedback in an ongoing lifestyle to prevent the forthcoming critical situation. Everything we imagined today may be possible in the near future but that requires consistent efforts to develop efficient techniques and algorithms.

With the collaborative or individual efforts of various scientific and research groups, algorithms are rapidly getting advanced by adopting the most trustworthy and less time-consuming methodologies. Deep learning and fine-tuned neural networks play an essential role in that context as they open new ways to modify existing techniques to obtain promising results. Inside the deep neural network, it’s hard to know how they behave and interact, but by employing systematic hyperparameters and fine-tuning, outcomes and performance can be improved. Some key hyperparameters are learning rate, optimization algorithm, activation function, number of hidden layers, number of activation units, kernel size, pooling size, batch size, and number of epochs.

Apart from the hyperparameter, the most crucial point is to decide a number of layers for the optimal and best performance of the network. Creating balance with all these parameters is complex and requires multiple testing and experiments. It takes a lot of effort and time to maintain a balance between two different quantities for the increased performance of a deep learning network. This problem can be addressed by employing an additional algorithm responsible for performing the required analysis to choose the best hyperparameter and values to establish a fully automated and self-improving deep learning network. Maybe the better strategy is to implement the most adaptive and high-performance AI algorithm, which helps detect and diagnose diseases on the individual and societal scale.

With this article, I would like to propose a “partial naturally randomized deep learning layers (PNRDL)” for the advanced performance of an automated detection system. The procedure is not tested yet, but the inclusion of optimization with a little bit of relaxing parameter in the form of partial naturally randomized weights may provide better human-level performance for the analysis of CT images to detect lung cancer or its early signs. In general, relaxing situations are when someone takes a break from the process to achieve the desired goal and spends some time doing other activities. Many philosophical studies discuss this period as the best period for finding new innovative, astonishing ideas that revolutionize the actual path of moving towards the desired goal. Sometimes it gives better outcomes than expected results that someone never imagined. I considered this not a coincidence but a part of natural computing through which anyone and everyone are connected. Billions of neurons continuously acquire weights inside the human brain by taking insights or parametric values. These values or parameters are generated by nature that add up with the brain as essential insights for the computation of various tasks, which sometimes reveal exceptional outcomes.

I believe it is a substantial phenomenon that is seemingly random but not actually random as everything inside nature runs by natural computing. To introduce a relaxing period inside the machine, I propose a relaxed parameter-based, “partial naturally randomized deep learning layers” that takes random values for deep learning weight updation. Random values used in these experiments will be directly obtained from the naturally randomized numbers that are randomized and obtained during individual image analysis. After such procedures, it may be possible to get a deeper connection to the automated detection system through natural computing, where the randomization of parameters works as a relaxing situation in the case of the human being. By going through this procedure, I believe the development of automated disease detection systems has become more realistic and precise. Maybe the idea of making this type of system works fine, and the procedure discussed for disease detection render outstanding results if employed in other research and development purposes. Figure 1 below is showing a short description of the development of the proposed algorithm.

The experimental scope of this research focuses on taking a machine into the time-space where some of its weight functions process the very subtle event of the natural parameter to extract essential values.

Figure 1 Short description of the proposed algorithm

However, the proposed model is still under exploration as the procedure to obtain an utterly randomized number is still in the experimental stage. The first few tries to generate random values are conducted by taking never-repeating decimal digits of “pi”. Although, they are also finite at any given period. Further trials to generate a natural randomized number to introduce relaxation sessions inside machine-learning operations are ongoing. The study aims to take insights from nature, always trying to say something to us regarding any event and situation. An American biologist, Barry Commoner once said that “everything is connected to everything else”.

It means the present case, past conditions, and future outcomes are not distinct. It is just our inability not to process the subtle insights of the surroundings and ignore them by considering them as random non-valuable information. Processing every element of information is not possible, but taking a small piece and extracting valuable insights is the way to achieve desired outcomes. The experimental scope of this research focuses on taking a machine into the time-space where some of its weight functions process the very subtle event of the natural parameter to extract essential values. The outcome of this process will generate a piece of information that helps to implement all-inclusive nature-driven algorithmic results. Unlike the existing computation system, it performs its task by combining insights of input data and instincts of current surroundings. It is an entirely radical approach to using AI techniques that can be time-consuming but taking a chance to develop and work upon this methodology may undoubtedly be helpful. After its successful implementation, it may be possible to implement a deeper bond with nature and harness the power of robust natural computing or actual computing.

Deep learning in AI also suggests that deeper and closely connected nodes are the one who dominates the outcomes. Similarly, the more dominant one around us (nature) should be deeply and strongly connected to every possible node (eg. deep learning algorithms and layers) to obtain the best possible results today and in the near future.

Composed by: “Mr. Resham Raj Shivwanshi is pursuing PhD at the Department of Biomedical Engineering, NIT Raipur. He is currently working upon medical imaging, CT scan analysis,Machine learning and AI methodologies.”

The post Advanced AI for medical image analysis to detect and diagnose the early stages of critical diseases appeared first on InnoHEALTH magazine.

CSIR-CDRI scientists develop RT-PCR kit for Omicron variant

InnoHEALTH magazine digital team — Thu, 27 Jan 2022 04:28:14 +0000

New Delhi, Jan 24 (India Science Wire): As the Coronavirus continues to mutate, it has become challenging to diagnose and treat different variants of concern. Some like the Omicron, though milder in symptoms and fatality, are a super spreader and are propagating like wildfire across the world.

Currently, detection of this variant depends upon tests like the S-gene dropout or by NGS (nextgen sequencing) of the whole viral genome. While the S-gene dropout method is not specific to pinpoint the type of variant, the NGS method has its limitations in terms of expense, turnaround, and the number of centres that can provide such service.

A team of scientists at CSIR-Central Drug Research Institute (CDRI), Lucknow, have developed an indigenous RT PCR Kit for the specific detection of the Omicron variant in collaboration with their industrial partner, Biotech Desk Pvt. Ltd., Hyderabad. The kit has been named INDICoV-Om^TM.

Dr. Atul Goel, the team leader said that the kit provides for quick and cost-effective detection of the Omicron variant. It can also be aligned for the detection of other emerging variants of COVID infection and other respiratory infections in the future. The kit has been tested and validated by Prof. Amita Jain in several Covid positive patient samples at King George Medical University, Lucknow.

Dr. Shradha Goenka, Managing Director, Biotech Desk Pvt. Ltd., said the kit was likely to be rolled out by mid-February. “We are working on regulatory approvals and the assembly of the kit. We are keeping our fingers crossed for an early release”, said Dr Goenka.

Prof. Tapas K. Kundu, Director CSIR-CDRI, said the Institute is rapidly gaining expertise in antiviral research for therapeutics and diagnostics to combat any kind of viral infections. The team led by Dr Atul Goel is fully prepared for the detection of broad spectrum and specific pathogenic viral infection. This kit for SARS-Cov-2 omicron diagnosis has been submitted to the Indian Council of Medical Research (ICMR) for validation and should be available for the people of the country soon.

The research team consisted of Dr. Niti Kumar, Dr. Ashish Arora, Ms. Surbhi Mundra, Ms. Varsha Kumari, Mr. Kundan Singh Rawat, and Ms. Priyanka Pandey, besides Dr. Goel.

ISW/SP/CSIR-CDRI/OMICRON/24/01/2022

Credits: India Science Wire

The post CSIR-CDRI scientists develop RT-PCR kit for Omicron variant appeared first on InnoHEALTH magazine.

AI and IoT in Healthcare: Need of Future

InnoHEALTH Magazine — Wed, 10 Jul 2019 08:54:11 +0000

Healthcare is transitioning from human touch of doctors, nurses and allied health professionals to devices and now information technology. In today’s world, healthcare is buzzing with new domain of Artificial Intelligence (AI) or should it be called assisted intelligence, machine learning, big data, block chain, Internet of Things (IoT), connected healthcare, mHealth, eHealth, cybersecurity and many more. These terminologies are being used by many without knowing its definition,use and limitation. It is creating a new community of providers. All this is good as long as we are not servient to technology and we control it for the benefit of providers and patients. Even medical personnel these days want to diagnose without touching the patients, without any concern for evidence-based medicine,human touch and compassion. Technology has made big in-roads in healthcare,but should it dispense health professionals as few think.

There is no doubt AI and IoT are big help in radiology and early diagnosis of cancer etc. but can never replace human intervention. India is also fast changing to adopt new technologies. As per a recent estimate, AI has potential of bringing $957 billion to the Indian economy by 2035. This may be the cause for luring young professionals to this new domain.

AI, as described by the domain experts – application of AI in healthcare, can be classified into Descriptive, Predictive, and Prescriptive. Our effort here is to learn and share newer knowledge by various initiatives taken by us through our annual conference, magazines, training programs, club meetings, webinars and the most recent delegation to Sweden under InnoBRIDGE 2019 to learn the best practices and explore synergies. On the request of our stakeholders, the next planned initiative is InnoBRIDGE USA 2020.

This issue is based on the theme of AI & IoT in Healthcare. The next one would be on Unmet Needs in Healthcare: Leading to Innovation. Do share your views and research for the benefit of all who believe in change through innovation. Let us think more on the basic issues of healthcare and how we can use technology to improve healthcare for common man at an optimum cost.

Ideate, Innovate and Incubate for the Bottom of Pyramid. Let us strive together to make India a developed economy from an emerging economy. The population of1.3 billion should be an asset and not a liability for the nation. A healthy India only can make wealthy India.

The post AI and IoT in Healthcare: Need of Future appeared first on InnoHEALTH magazine.

Software as Medical Device

InnoHEALTH Magazine — Wed, 09 May 2018 05:23:22 +0000

The tectonic shifts in technology are transforming human life in ways unfathomable just a few years ago. Health-tech and med-tech are touching our lives continuously through a number of ways – from simple wearable devices to complex invasive devices; simple AI software which can predict and sense to complex AI software which can diagnose; sensors and other hardware devices including the mobile phone with ever-increasing computing power.

Some of these have made human lives so dependable on these devices, gadgets, software. In some cases, these are dumping human intelligence. We witnessed software wherein by looking at a camera on the mobile phone. The software can predict the heart rate and many other vitals. What if human intelligence gave way in believing the reading as true? The software or the camera is not a medical device. Hence outside the purview of regulations usually applicable to medical devices. Can we ignore the risks? If so, should software be treated as a medical device?

Software as Medical Device (SaMD)

A broadly accepted definition of a SaMD is the one issued by the International Medical Devices Regulation Forum (“IMDRF”); Currently, Australia, Brazil, Canada, China, Europe, Japan, Russia, Singapore and the USA are member countries to this Forum. The FDA has adopted this definition in the US. The Medical Device Directive adopted by the EU in 2010, and in major countries such as Australia, Canada and Japan.

The term “Software as a Medical Device” is defined as software intended to be used for one or more medical purposes that perform these purposes without being part of a hardware medical device. It includes an in vitro diagnostic medical device. SaMD must be capable of running on a computer platform that is not of a medical purpose. And should not need a hardware medical device to achieve its purpose. It can be interfaced or used in a combination with other devices. But cannot be used to drive a hardware device.

The definition, Mobile Application Meeting, also consider as SaMDs. The medical purpose‟ that it must intend to serve can be diagnostic, preventive, investigative, life-sustaining, for treatment of disease or injury, disinfection, control of conception or purely informative. In some jurisdictions, aids for persons with disabilities, devices for assisted reproduction and devices incorporating animal and/or human tissues are also recognized.

A SaMD can also be a means to suggest mitigation of a disease or provide aid to diagnosis. There are further guidelines on the definition of changes to SaMDs- they can be adaptive, corrective or preventive in nature. The manufacturer of SaMD would be a natural or legal person who has the intention for the software to be used under his/its name. It would not include a distributor or the manufacturer of an accessory. The final legal responsibility lies with the manufacturer unless it specifically imposes on another party by the country’s regulatory authority.

Putting them to use

SaMDs are now available in abundance in the Indian market. Both foreign manufacturers, as well as Indian manufacturers, are introducing so many forms of SaMDs. This includes the use of artificial intelligence, IoT, general software etc. Interesting, many SaMDs are enjoying high adoption rates not only for early users but continued users. The glaring point is that there is no legislative framework or guidance policy which works as a guiding principle for the SaMD manufacturers or at least as a self-regulating piece of legislation, in India.

The Medical Devices Rules, 2017 which has come into effect from January 1, 2018. Now defined medical devices and has made a clear distinction between drugs and medical devices. But still, this definition does not include SaMDs or software as a medical device. Interestingly, the draft Medical Devices Rules, 2016 on basis of which the Medical Devices Rules, 2017 have been formalized included software in the definition of medical device. AI, IoT, general software, wearable, and wellness and customized medical devices are flooding with the market. Software as a medical device as a whole should consider with equal importance in the sector. Curiously, the definition of medical devices under Foreign Direct Investment policy includes software.

Regulations

The IMDRF has worked extensively in setting guiding principles for governing SaMD and has put in place a regulatory structure for how the SaMDs shall be governed, regulated, clinically evaluated and how the data shall be evaluated and then used by the SaMD. While India has not yet included any software or apps in its regulatory purview. Countries like U.S.A, Singapore, Australia, EU and Japan has issued guidance documents to make the app developers aware of what might subject to regulation.

The common theme that determines the classification is the level of risk that these apps pose to the consumers. For example, let’s take an app which allows a user to take ECG test by putting their fingers on an external device which is connected wirelessly to the smartphone. It checks the electrical activity of the heart. Such apps may be considered as risky and be subject to regulation since the belief is that any incorrect analysis may hamper a user’s treatment. However, the Government authorities need to strike a balance while assessing these risks so that not all apps need to be certified under the law so that innovation is not hampered.

It is indeed a very fine balance. General wellness apps or products such as apps tracking and assisting in maintaining healthy body weight. Products are generally kept out of the purview of law versus apps which tracks and assists in say monitoring blood sugar or other vitals or treats specific health issues or provides guidance for treatment of specific illnesses. The whole purpose to bring these apps under regulation is that there is a certain amount of rigour before the apps are released to the market. And there is onus and responsibility on these makers. It should enable the app developers to be mindful of how is the product advertises, claims as well.

To protect consumers, certain jurisdictions, like Singapore, have mandated the manufacturers/ app developers to put a clarification statement on their product or on their apps. This statement should clearly state that this app or product is not intended to be used in a diagnosis, monitoring, management or treatment of any disease. Keeping all the innovation in health-tech space, India should provide guidance on SaMDs. The regulatory framework in India for medical devices is by the Central Drugs Standards Organization widely known as CDSCO.

The new Medical Devices Rules, 2017 are comprehensive and now extensively covers almost 351 medical devices and about 247 in-vitro medical devices. It still does not cover SaMDs. Given the increased use of mobile technology and awareness, guidelines on SaMDs could contribute to improving the affordability and availability of healthcare, including rural India, which has a huge user base. Gradual rigour in legislation will allow India to meet increased need, according to when resources for monitoring and enforcement become more available. India already follows the IMDRF regulations with respect to clinical trials. And the clinical evaluation of medical devices, with respect to documents, licensing and safety standards.

It is important for the legislation to allow the industry to grow and achieve its potential. Especially in a country like India where there is a need for the better point of care medical solutions. But at the same time provide unambiguous guidance. A good starting point would be a self-regulating mechanism with a set of standards, methods and procedures, clinical evaluation process. Such guidance would help improve innovation as well and guide the nascent Indian SaMD industry.

(Author is a qualified lawyer who has a keen interest in how tectonic shifts in technology is impacting healthcare delivery. The intersection of law, innovation, interaction with man and machine excites him. Manas works with NovoJuris Legal deeply in AI, IOT, health-tech, med-tech, devices and more in the healthcare segment)

A new paradigm for use of machine intelligence in healthcare

Want to write for InnoHEALTH? send us your article at magazine@innovatiocuris.com

The post Software as Medical Device appeared first on InnoHEALTH magazine.

India's first smartphone insertable cardiac monitor

InnoHEALTH Magazine — Fri, 04 May 2018 10:30:52 +0000

Abbott, one of India’s leading healthcare companies recently launched the latest Insertable Cardiac Monitor (ICM) across the country which is also the world’s first smartphone compatible ICM to aid physicians who can remotely monitor their patients for even the most difficult to detect cardiac arrhythmias including irregular heartbeats, atrial fibrillation etc.

It is designed to continuously monitor a patient’s heart rhythm and proactively transmit information via Bluetooth to Abbott’s dedicated mobile app for this, allowing physicians to follow their patients remotely and accurately diagnose arrhythmias that may require further treatment. This device provides a win-win situation for both the doctor and the patient.

For doctors the device allows for effective management of patients by diagnosing patients having infrequent but potentially fatal episodes of cardiac arrhythmias while enhancing patient compliance through smartphone connectivity. For patients it provides a new way to get monitored for abnormal heart rythms while staying connected to their doctors remotely and engaged in their healthcare.Once implanted just under the skin in the chest during a quick, minimally invasive outpatient procedure this ICM continuously monitors heart rhythms to detect a range of cardiac arrhythmias. It is also the slimmest ICM available today. It is the size of two paper clips, stacked on top of each other. While the ICM continu- ously monitors for abnormal heart rhythms and transmits data to a patient’s doctor, the app also allows patients to track symptoms proactively,sync their data with their clinic at any time, and view their transmission history without having to contact their clinic to confirm successful data transfers. Patients can also re- cord their symptoms such as fainting spells or heart palpitations in the app on their smart phones, to complement the information being monitored by the device.

The device has already received the CE Mark and USFDA approvals and is available in the EU, U.S.A and Australia The insertable cardiac monitor is extremely useful as it provides early diagnosis and timely treatment to events which could be catastrophic in nature if left unattended. This device for sure is taking cardiac monitoring to a whole new level.

Want to write for InnoHEALTH? send us your article at magazine@innovatiocuris.com

The post India's first smartphone insertable cardiac monitor appeared first on InnoHEALTH magazine.