Cancer remains a major public health and economic burden on patients, families, and healthcare systems. But breakthrough advances in cancer biology in the last two decades have dramatically changed our understanding of its pathogenesis and, consequently, our strategies to beat it.

The progress in managing blood cancers, specifically lymphoma, has raised optimism in the medical community. Lymphomas are a diverse group of cancers that affect the lymphatic system and are one of the most common malignancies worldwide and in Saudi Arabia. They are histologically categorized into Hodgkin's lymphoma and non- Hodgkin's lymphoma (NHL), where each category has many subtypes.

Related: Pregnancy-associated breast cancer: How common is it?

Until the late 1990s, all we had in our battle against cancer were conventional treatment methods with surgery, radiation, and chemotherapy. With the more advanced medical tools at our disposal, drug development and discovery have shifted toward personalised cancer treatment with molecular and immunological targeted agents.

A good example is chimeric antigen receptor T-cell (CAR T-cell) therapy, a revolutionary approach for treating different haematologic malignancies, including NHL, acute lymphoblastic leukemia, and multiple myeloma. The currently available CAR T-cell therapies are genetically engineered autologous T lymphocytes with an enhanced immune response against a specific tumour antigen, CD19 in the case of NHL.

Related: HIPEC increases cancer survival rates but lacks regional awareness

The introduction of anti-CD19 CAR T-cell therapies to the market has given new hope to patients with refractory and relapsed aggressive B-cell lymphomas who progressed despite multiple prior treatments. This represents a paradigm shift in NHL treatment, where it induced an impressive response rate of 82 per cent in ZUMA-1 study with a five-year overall survival rate of 43 per cent and a 63.1-month median follow up. This encouraged the medical community to explore other ways to optimise the clinical impact of CAR-T cell therapy by studying how to integrate it with allogeneic hematopoietic stem cell transplantation or checkpoint blockade in the future.

More promising new innovative cellular therapeutics are on the future horizon for cancer patients, such as "off-the-shelf" or allogeneic CAR-T cell and CAR natural killer cell-based immunotherapy. This type of treatment may eventually replace conventional chemotherapy, which is the standard of care for patients with advanced stage Diffuse Large B Cell Lymphoma (DLBCL) for the past 20 years. While the addition of rituximab to CHOP (cyclophosphamide, doxorubicin, vincristine, and prednisone) in 2010 has shown significant benefit over CHOP in all categories of older patients, only about two-thirds of patients are typically cured with R-CHOP in the first-line setting. Many clinical trials over the past years have evaluated different ways to improve R-CHOP outcomes with no luck.

Furthermore, there is a huge unmet need for effective treatment options in refractory and relapsed DLBCL. The prognosis of these patients is generally poor, where only 30 per cent to 40 per cent of patients will respond to chemotherapy.

Additionally, the safety of intense chemotherapy regimens for the treatment of NHL is a significant concern, especially in older, frail patients with other comorbidities. This becomes a challenge, as we know that survival of lymphoma patients is correlated with achievement of complete remission; hence, dose reductions could compromise the treatment outcomes. A recent challenge we have been facing regionally and globally is the shortage of essential conventional chemotherapy agents. This has led to treatment delays or treating urgent cases with suboptimal alternative chemotherapy regimens.

Any progress in diagnosing and treating lymphoma is welcome news in Saudi Arabia, where NHL is ranked as the second most common cancer type in Saudi men and fifth among Saudi women (Source: Saudi Cancer Registry, 2016). The median age of diagnosis is 50 years in males compared to 57 years in females, which is remarkably younger than the reported median age of diagnosis in the U.S.

Diffuse Large B Cell Lymphoma is the most common subtype of NHL, where it accounts for half of NHL cases in both genders among the Saudi population. More than 40 per cent of DLBCL cases present with an advanced-disease stage, which is associated with a lower survival rate. This delay in seeking medical attention could be explained by the lack of public awareness about the disease, especially since the clinical presentation includes unspecific symptoms, in addition to the absence of effective screening methods for early detection.

An important note to consider is that the local literature reporting lymphoma in Saudi Arabia is limited, as the reported data may not represent lymphoma epidemiology in the Kingdom. More data are needed, especially from peripheral hospitals.

Cancer management is complex, and various medical professionals play a critical role in the overall patient journey. As pharmacists, our responsibilities in CAR-T cell therapy programmes include policy development, clinical assessment of bridging and lymphodepleting chemotherapy, toxicity management, and patient and staff education. Pharmacists with an experience in cellular therapy are highly needed in clinical practice, as this treatment modality continues to evolve to effectively treat incurable haematologic malignancies and potentially even solid tumours.  

Our contributions support Saudi Vision 2030, which envisions the Kingdom emerging as a top healthcare destination. The country's goal is to have pioneer healthcare services by allowing patients to access emerging innovative treatment modalities for different diseases.

---
Dr. Bashayer Alshehri is the Stem Cell Transplantation and Cellular Therapy Senior Clinical Pharmacist, National Guard Health Affairs in Riyadh, Saudi Arabia.

A new kind of soft robot has been developed using metal particles and external magnets to make a slime-like substance that can move around, change shape and even grip objects.

The research by the Chinese University of Hong Kong was initially posited in March, with findings published by Wiley.

A different team of researchers from the same university have taken the concept a step further by using sticky tape to give the magnetised particles different forms, with these ‘microbots’ capable of changing shape in relation to the magnetic field they’re exposed to.

In their experiments, the team demonstrated the soft robots’ capabilities to move through water and along flat surfaces, while one crawled over a pig’s stomach tissue to attach and detach a therapeutic patch to an ulcer.

The team says the process of creating the robots can be automated, and predicts that one day the tiny robots could be printed out in long rolls and then cut to size.

Results from the study were recently published in a paper ‘Untethered small-scale magnetic soft robot with programmable magnetisation and integrated multifunctional modules.’

While potentially ground-breaking for the future of certain surgical procedures, a challenge remains in the toxicity of the magnetic materials used.

Research into how to mitigate this problem is ongoing, with the team that created the initial slime robot working on a protective coating to make the substance safe for health care applications.

This article was originally published on IoT World Today. 

An MIT alumna has developed a mobile app that uses AI to classify various skin conditions, ranging from melanoma to shingles.

Co-founded by MIT alumna Susan Conover, Piction Health aims to help primary care physicians recognise skin conditions so they can quickly refer patients to dermatologists who may have life-threatening melanoma.

She was inspired by her own experience of finding a suspicious mole but was informed it would take three months before she could see a dermatologist. Though her mole turned out to be benign, she realised there was a need for a more efficient process.

The original objective was to identify skin cancer based on images taken with the mobile app, but Conover and her co-founder, Pranav Kuber, expanded their database to assist clinicians with identifying more frequent skin conditions, such as acne, eczema and shingles.

“All these other conditions are the ones that are often referred to in dermatology, and dermatologists become frustrated because they’d prefer to be spending time on skin cancer cases or other conditions that need their help. We realised we needed to pivot away from skin cancer in order to help skin cancer patients see the dermatologist faster,” Conover told SciTechDaily.

Training an algorithm to identify various skin diseases is much more complex than only diagnosing melanoma. Piction has accumulated what it said is the world’s largest image database of rashes with more than 1 million photos from 18 countries, taken by dermatologists.

“We decided it’s better to just jump to making the full product … that identifies all different rashes across multiple body parts and skin tones and age groups,” said Conover.

The machine learning tool can assist physicians with distinguishing between skin diseases for better patient care. Conover said the software can decrease the case evaluation time by 30 per cent, which can expedite potential melanoma cases to dermatologists while allowing primary care physicians to treat more routine cases. Most of the skin conditions diagnosed by clinicians are skin rashes such as eczema, rosacea, or psoriasis.

The model can also decrease costs for health care institutions by eliminating needless prescriptions, unwarranted referrals, or repeated doctor’s visits.

Piction plans on launching several pilots, including platforms that can assist with wound treatment or identify infectious diseases, such as leprosy. The company wants to partner with nonprofit groups to assist clinicians who do not have easy access to specialists or diagnostic tools. 

This article was originally published on AI Business.

Colombia ranks high in healthcare efficiency than USA, Canada and Australia, according to WHO. This is a testament to the country’s powerhouses that are fuelling tech-driven solutions in the market. ProColumbia USA’s Executive Director Ricardo Pedroza, tells us more about this phenomenon led by digital transformation.

Watch the full interview below:

Related: Healthcare opportunities in tech-friendly Colombia

Ricardo Pedroza is an experienced executive, passionate about strategy, leadership, people and results. He has worked in the US, Europe and Latin America in the IT sector, as well as in international affairs, capital investment and exports. He has been working at ProColombia for about 5 years; he first started as Executive director for ProColombia in Germany and he’s been one year and a half the Executive Director of ProColombia in the United States.

For more info on the business matchmaking forum or to register, click here

Diagnosis and treatment plans are at the heart of the clinical practice, but decision-making determines the success of the diagnostic process. Surprisingly, a correct diagnosis is not made as often as it is thought. The underlying factors contributing to diagnostic error have multiple causes, including a no-fault error, system-related, and most common cognitive errors. A no-fault error is described as when the disease is masked or is in an uncommon appearance or due to uncooperative, misleading information by the patient, while system-related errors are due to technical failure and equipment problems, organisational processes, flaws, and problems with policies and procedures, inefficient processes, teamwork, and communication.

Whilst the most common factor in diagnostic error is a cognitive error where problems involved faulty synthesis, knowledge or data gathering, and cognitive judgment. In most cases leading to premature closure after an initial diagnosis was reached without considering reasonable alternatives. Common illnesses are commonly misdiagnosed, because their signs and symptoms are overlapping with those of numerous other diseases, ruling out the possibility of other diseases which in many cases lead to fatal cases.

Understanding errors

Related: The dawn of the metaverse in healthcare

According to research system errors contributed to the diagnostic error in 65 per cent of the cases and cognitive factors in 74 per cent. Usually, diagnosis reflects the clinician’s knowledge, clinical acumen, and problem-solving skills; however, it is not a lack of knowledge that leads to failure; over the past half-century, cognitive psychologists and neuroscientists have indicated the cognitive and affective state of the human mind's vulnerability to memory fallacies, cognitive biases, incorrect assumptions, and other reasoning failures.

Cognitive failures are best understood in the context of how our brains manage and process information through the reasoning process.

Related: AI tool predicts Parkinson’s from breathing patterns

Memory, attention, judgment, and decision-making in contemporary theories of clinical reasoning adopt the dual-process processing model system, which consists of two systems of thinking. Type 1 is autonomous, subconscious, fast, and intuitive, is generally either hard-wired or acquired through repeated experience, and doesn’t require working memory. It is considered an independent cognitive ability and mostly serves us well and is indispensable in enabling us to get through life in a fixed-action mindless pattern. Type 2, on the other hand, is conscious, controlled, slow, reflective logical, and analytical requiring working memory following laws of science and logic and is collated with cognitive ability. Descriptions of the operating characteristics of the dual processing system provide a useful starting point for learning about medical decision-making.

Generally, it seems that much of our everyday thinking is flawed and our thinking is a mixture of system 1 and system 2 and clinicians are not immune to the problem.

Addressing biases

Typically, diagnostic error is viewed as a cognitive failing and cognitive theories about human memory propose that such errors may arise from both Type 1 and Type 2 reasoning; however, Type 1 arising from the intuitive mode is the primary source of cognitive failure that can lead to cognitive biases, fallacies, and thinking failures.

More than 100 biases of information processing can interfere with sound clinical reasoning and decision-making influencing medical disciplines with at least 50 cognitive biases applicable in medicine. However, anchoring and confirmation are prominent in cognitive errors.

For example, when a patient undergoes an analytic assessment for chest pain in a cardiac clinic that culminates in angiography, the conclusion is invariably correct.

By contrast, when physician practices prioritise information and data that support their initial impressions or beliefs, an anchoring bias has occurred.

In another case, a 60-year-old male arrived in the emergency room (ER) with flank pain and hematuria. The fast and frugal approach to his complaint involves primarily a pattern recognition heuristic that leads to a diagnosis of renal colic. This may well be correct. Occasionally, however, it will be a dissecting abdominal aortic aneurysm, and the heuristic will have catastrophically failed. When common illnesses' symptoms overlap with other diseases' symptoms heuristics or mental shortcuts used in clinical decision-making often serve well, but occasionally fail (Pat Croskerry, 2005).

Another may be countertransference, an effective bias that can be triggered by past experiences, such as a patient’s behaviour or appearance evoking a memory of a previous similar encounter with the physician and producing a biased response or occurs when the therapist projects their unresolved conflicts onto the client.

Despite, diagnostic error and analytic failures being commonly multifactorial in origin, typically involving both system-related and cognitive factors like biases; cognitive overload, fatigue, sleep deprivation, or emotional agitations also play a major role. In an impact, an affective state with its vulnerability to mood alterations as anyone else, decision-making and judgment are affected, yet the impact of the affective state on decision-making has gained little attention to date such as in a caregiving role.

Organisational changing conditions, like the deployment of ongoing new technology systems, change management, business transformation where physicians are racing to keep up with digital transformation extorted requirements and interpersonal development, conflicts, and lack of effective leadership in the workplace may lead to temporary or ongoing changes in the affective state of physicians. Optimal perception, attention, memory, and reasoning performance become impaired.

Stress, fatigue, and profound psychological effects such as anger, guilt, inadequacy, and depression, are well known to produce irritability, intolerance, and other mood changes that will also exert an influence on judgment. The impact of diagnostic failure on patient safety does not appear to have been fully recognised yet and we remain unrealistic about acknowledging the impact of cognitive biases and affective states and their effect on clinical reasoning. Despite the substantial impact of our evolving understanding of cognitive psychology, organisational psychology, and neuroscience, and the significant influence on academic medicine over the past 20 to 30 years; major social sciences have not historically been considered within the remit of medicine.

Securing optimised performance

To drive critical meta-cognition thinking, fortunately, cognitive psychology and organisational neuroscience provide insights into how to prevent biases and it would be beneficial to include them in the medical school curriculum part of the solution is to maintain a culture that works toward recognising the psychological safety of physicians at work and safety of patients at clinics.

Recognising that such cognitive errors are not inevitable, organisational neuroscientists and psychologists can help:

• Curate educative programmes, cognitive tutoring systems, training and coaching for medical students, residents, and fellows on cognitive biases, and the role they play in diagnostic and treatment errors.
• Help physicians become more self-aware and familiarised with the many types of cognitive biases and build effective debiasing strategies and provide interventions to guard against our psychological defence mechanisms that hinder humans from examining their thinking, motivation, and desires too closely.
• Build a critical thinking program of neuroscience and coaching, teaching how decision-making works where cognitive biases are addressed, taught, and learned. This is by showing how cognition, memory, and attention apply to clinical cases and how to fix biases and de-bias oneself during diagnosis.
• Help with building the “ability” to maintain keen vigilance and mindfulness to engage in the purposeful, self-regulatory judgment of one's thinking.
• Provide interventions to build habitual memory focus through self-directed mind-ware awareness, enhancing the memory to retrieve rules, knowledge, procedures, and strategies to aid decision-making and problem-solving as soon as the situation arises.
• Work closely with leadership on fostering the psychological safety and well-being of the physicians in the workplace strengthening the emotional and attentional intelligence by which it is important to note that, the affected state of the human is inseparable from thinking and plays an integral part in our ability to process information meaningfully, make good decisions, drive optimised performance, and avoid affective pitfalls.
   

In the age of digital transformation, clinical decision support software or artificial intelligence (AI) methods, in particular, machine learning (ML), reinforcement learning, and deep learning, which have been there for the past 15 years and are not something new to the medical field are well-suited to deal and aide physicians in evaluating multiple outcomes to optimise diagnosis.

However, deep learning models are less easily interpretable and may be biased too, and to establish a causal link still, requires an immense amount of big data to be generated and the fact that any biased data learned by AI remains a factor in question in the decision support system, given that just like AI algorithms fed by humans who are mostly unaware of their own biases determine the quality of the clinical decision, potentially creating a new bias that is data bias among the medical field. Hence, the need to focus on the stabilisation of human bias before creating a dissonance between human and AI biases.

Bridging social sciences such as psychology and neuroscience within the social ecosystems including all forms of organisations, educational and medical systems, and raising awareness to build a life-long commitment toward self-de-biasing and learning on the significance of safeguarding self’s critical thinking and cognition is the major goal to focus on in our transition towards cognitive and digital societies.
 

References Diagnostic Error in Internal Medicine | Health Care Safety | JAMA Internal Medicine | JAMA Network Diagnostic Failure: A Cognitive and Affective Approach - Advances in Patient Safety: From Research to Implementation (Volume 2: Concepts and Methodology) - NCBI Bookshelf (nih.gov) https://journalofethics.ama-assn.org/article/believing-overcoming-cognitive-biases/2020-09 https://www.ncbi.nlm.nih.gov/books/NBK20487/ Medical Error Reduction and Prevention - StatPearls - NCBI Bookshelf (nih.gov) The Causes of Errors in Clinical Reasoning: Cognitive Biases, Knowledge Deficits, and Dual Process Thinking - PubMed (nih.gov)

Maha Chehab is a Business Psychologist and Organisational Neuroscience Specialist | Change and Transformation | Cognitive and Digital Enterprises.

An AI tool developed by neurological experts could detect the onset of Parkinson’s disease by evaluating nocturnal breathing patterns, according to a paper in Nature Medicine.

The scientists from MIT, University of Rochester Medical Center, Mayo Clinic and Boston University developed a diagnostic tool capable of accurately predicting Parkinson’s disease based on one night of breathing data.

A passive monitoring system or a belt worn around the abdomen uses a low-power radio signal to analyse the breathing patterns of sleeping patients. The algorithm used to analyse the findings was trained on breathing data from 12,000 nights of sleep and 120,000 hours of breathing from 757 Parkinson’s disease patients.  

Twelve patients who didn’t have Parkinson’s, but later developed the disease, were flagged by the tool. The researchers are working to develop a new study to validate their results.

“All the indications so far are positive and we hope that we can start detecting Parkinson’s much earlier,” Dina Katabi, Ph.D., a computer scientist and principal investigator from MIT, told STAT News.

The link between breathing changes and Parkinson’s disease was first suggested by James Parkinson himself in the early 19th century. Currently, there are no reliable biomarkers for detecting or tracking Parkinson’s disease. The charity Parkinson’s UK suggests it’s the fastest-growing neurological disease, with some seven million people suffering globally, according to Radboud University.

The AI tool monitored the breathing patterns, blood pulses and muscle twitching during the continuous inhale and exhale phases. Since the device can be used at a patient’s home instead of strictly in a clinical setting, specialists can diagnose a much greater number of people.

Furthermore, researchers were able to distinguish between Parkinson’s and Alzheimer’s disease. With early detection, patients can begin clinical trials and test whether a drug is working. Neurological diseases typically have a high failure rate in trials because it’s difficult to evaluate symptoms and monitor the effectiveness of the treatments.

“It’s hard to say whether nocturnal breathing is going to be the measure you’re going to see a change in response to treatment. It may be more useful for diagnosis,” said Ray Dorsey, the study’s co-author and Parkinson’s disease expert at the University of Rochester. “But I think if you can get objective measures of disease in the real world, this would tell you in a shorter period of time whether a drug works.”

This article was originally published on AI Business.