Stool-Based Testing for Post-Polypectomy Colorectal Cancer Surveillance Safely Reduces Colonoscopies: The Molecular Stool Testing for Colorectal Cancer Surveillance Study.

BACKGROUND & AIMS: Colonoscopy-based surveillance to prevent colorectal cancer (CRC) causes substantial burden for patients and health care. Stool tests may help to reduce surveillance colonoscopies by limiting colonoscopies to individuals at increased risk of advanced neoplasia. METHODS: This cross-sectional observational study included individuals aged 50-75 years with surveillance indication. Before bowel preparation, participants collected samples for a multitarget stool DNA test and 2 fecal immunochemical tests (FITs). Test accuracy was calculated for all surveillance indications. For the post-polypectomy indication only, which is the most common and is associated with a relatively low CRC risk, long-term impact of stool-based surveillance was evaluated with the Adenoma and Serrated Pathway to Colorectal Cancer model. Stool-based strategies were simulated to tune each test's positivity threshold to obtain strategies at least as effective as colonoscopy surveillance. RESULTS: There were 3453 individuals with results for all stool tests and colonoscopy; 2226 had previous polypectomy, 1003 had previous CRC, and 224 had a familial risk. Areas under the receiver operating characteristic curve for advanced neoplasia were 0.72 (95% CI, 0.69-0.75) for the multitarget stool DNA test, 0.61 (95% CI, 0.58-0.64) for the FIT OC-SENSOR (Eiken Chemical Co, Tokyo, Japan) and 0.59 (95% CI, 0.56-0.61) for the FIT FOB-Gold (Sentinel, Milan, Italy). Stool-based post-polypectomy surveillance strategies at least as effective as colonoscopy surveillance reduced the number of colonoscopies by 15%-41% and required 5.6-9.5 stool tests over a person's lifetime. Multitarget stool DNA-based surveillance was more costly than colonoscopy surveillance, whereas FIT-based surveillance saved costs. CONCLUSIONS: This study found that stool-based post-polypectomy surveillance strategies can be safe and cost-effective, with potential to reduce the number of colonoscopies by up to 41%. CLINICALTRIALS: gov, Number: NCT02715141.

Artificial intelligence-enhanced patient evaluation: bridging art and science.

The advent of digital health and artificial intelligence (AI) has promised to revolutionize clinical care, but real-world patient evaluation has yet to witness transformative changes. As history taking and physical examination continue to rely on long-established practices, a growing pipeline of AI-enhanced digital tools may soon augment the traditional clinical encounter into a data-driven process. This article presents an evidence-backed vision of how promising AI applications may enhance traditional practices, streamlining tedious tasks while elevating diverse data sources, including AI-enabled stethoscopes, cameras, and wearable sensors, to platforms for personalized medicine and efficient care delivery. Through the lens of traditional patient evaluation, we illustrate how digital technologies may soon be interwoven into routine clinical workflows, introducing a novel paradigm of longitudinal monitoring. Finally, we provide a skeptic's view on the practical, ethical, and regulatory challenges that limit the uptake of such technologies.

Unleashing the full potential of digital outcome measures in clinical trials: eight questions that need attention.

The use of digital health technologies to measure outcomes in clinical trials opens new opportunities as well as methodological challenges. Digital outcome measures may provide more sensitive and higher-frequency measurements but pose vital statistical challenges around how such outcomes should be defined and validated and how trials incorporating digital outcome measures should be designed and analysed. This article presents eight methodological questions, exploring issues such as the length of measurement period, choice of summary statistic and definition and handling of missing data as well as the potential for new estimands and new analyses to leverage the time series data from digital devices. The impact of key issues highlighted by the eight questions on a primary analysis of a trial are illustrated through a simulation study based on the 2019 Bellerophon INOPulse trial which had time spent in MVPA as a digital outcome measure. These eight questions present broad areas where methodological guidance is needed to enable wider uptake of digital outcome measures in trials.

Is the price right? Paying for value today to get more value tomorrow.

BACKGROUND: Contemporary debates about drug pricing feature several widely held misconceptions, including the relationship between incentives and innovation, the proportion of total healthcare spending on pharmaceuticals, and whether the economic evaluation of a medicine can be influenced by things other than clinical efficacy. MAIN BODY: All citizens should have access to timely, equitable, and cost-effective care covered by public funds, private insurance, or a combination of both. Better managing the collective burden of diseases borne by today's and future generations depends in part on developing better technologies, including better medicines. As in any innovative industry, the expectation of adequate financial returns incentivizes innovators and their investors to develop new medicines. Estimating expected returns requires that they forecast revenues, based on the future price trajectory and volume of use over time. How market participants decide what price to set or accept can be complicated, and some observers and stakeholders want to confirm whether the net prices society pays for novel medicines, whether as a reward for past innovation or an incentive for future innovation, are commensurate with those medicines' incremental value. But we must also ask "value to whom?"; medicines not only bring immediate clinical benefits to patients treated today, but also can provide a broad spectrum of short- and long-term benefits to patients, their families, and society. Spending across all facets of healthcare has grown over the last 25 years, but both inpatient and outpatient spending has outpaced drug spending growth even as our drug armamentarium is constantly improving with safer and more effective medicines. In large part, this is because, unlike hospitals, drugs typically go generic, thus making room in our budgets for new and better ones, even as they often keep patients out of hospitals, driving further savings. CONCLUSION: A thorough evaluation of drug spending and value can help to promote a better allocation of healthcare resources for both the healthy and the sick, both of whom must pay for healthcare. Taking a holistic approach to assessing drug value makes it clear that a branded drug's value to a patient is often only a small fraction of the drug's total value to society. Societal value merits consideration when determining whether and how to make a medicine affordable and accessible to patients: a drug that is worth its price to society should not be rendered inaccessible to ill patients by imposing high out-of-pocket costs or restricting coverage based on narrow health technology assessments (HTAs). Furthermore, recognizing the total societal cost of un- or undertreated conditions is crucial to gaining a thorough understanding of what guides the biomedical innovation ecosystem to create value for society. It would be unwise to discourage the development of new solutions without first appreciating the cost of leaving the problems unsolved.

Tribulations and future opportunities for artificial intelligence in precision medicine.

Upon a diagnosis, the clinical team faces two main questions: what treatment, and at what dose? Clinical trials' results provide the basis for guidance and support for official protocols that clinicians use to base their decisions. However, individuals do not consistently demonstrate the reported response from relevant clinical trials. The decision complexity increases with combination treatments where drugs administered together can interact with each other, which is often the case. Additionally, the individual's response to the treatment varies with the changes in their condition. In practice, the drug and the dose selection depend significantly on the medical protocol and the medical team's experience. As such, the results are inherently varied and often suboptimal. Big data and Artificial Intelligence (AI) approaches have emerged as excellent decision-making tools, but multiple challenges limit their application. AI is a rapidly evolving and dynamic field with the potential to revolutionize various aspects of human life. AI has become increasingly crucial in drug discovery and development. AI enhances decision-making across different disciplines, such as medicinal chemistry, molecular and cell biology, pharmacology, pathology, and clinical practice. In addition to these, AI contributes to patient population selection and stratification. The need for AI in healthcare is evident as it aids in enhancing data accuracy and ensuring the quality care necessary for effective patient treatment. AI is pivotal in improving success rates in clinical practice. The increasing significance of AI in drug discovery, development, and clinical trials is underscored by many scientific publications. Despite the numerous advantages of AI, such as enhancing and advancing Precision Medicine (PM) and remote patient monitoring, unlocking its full potential in healthcare requires addressing fundamental concerns. These concerns include data quality, the lack of well-annotated large datasets, data privacy and safety issues, biases in AI algorithms, legal and ethical challenges, and obstacles related to cost and implementation. Nevertheless, integrating AI in clinical medicine will improve diagnostic accuracy and treatment outcomes, contribute to more efficient healthcare delivery, reduce costs, and facilitate better patient experiences, making healthcare more sustainable. This article reviews AI applications in drug development and clinical practice, making healthcare more sustainable, and highlights concerns and limitations in applying AI.

Factors Associated with Veteran Self-Reported Use of Digital Health Devices.

BACKGROUND: Digital health devices (DHDs), technologies designed to gather, monitor, and sometimes share data about health-related behaviors or symptoms, can support the prevention or management of chronic conditions. DHDs range in complexity and utility, from tracking lifestyle behaviors (e.g., pedometer) to more sophisticated biometric data collection for disease self-management (e.g., glucometers). Despite these positive health benefits, supporting adoption and sustained use of DHDs remains a challenge. OBJECTIVE: This analysis examined the prevalence of, and factors associated with, DHD use within the Veterans Health Administration (VHA). DESIGN: National survey. PARTICIPANTS: Veterans who receive VHA care and are active secure messaging users. MAIN MEASURES: Demographics, access to technology, perceptions of using health technologies, and use of lifestyle monitoring and self-management DHDs. RESULTS: Among respondents, 87% were current or past users of at least one DHD, and 58% were provided a DHD by VHA. Respondents 65 + years were less likely to use a lifestyle monitoring device (AOR 0.57, 95% CI [0.39, 0.81], P = .002), but more likely to use a self-management device (AOR 1.69, 95% [1.10, 2.59], P = .016). Smartphone owners were more likely to use a lifestyle monitoring device (AOR 2.60, 95% CI [1.42, 4.75], P = .002) and a self-management device (AOR 1.83, 95% CI [1.04, 3.23], P = .037). CONCLUSIONS: The current analysis describes the types of DHDs that are being adopted by Veterans and factors associated with their adoption. Results suggest that various factors influence adoption, including age, access to technology, and health status, and that these relationships may differ based on the functionalities of the device. VHA provision of devices was frequent among device users. Providing Veterans with DHDs and the training needed to use them may be important factors in facilitating device adoption. Taken together, this knowledge can inform future implementation efforts, and next steps to support patient-team decision making about DHD use.

Systematic Review of the Cost of Illness of Parkinson's Disease from a Societal Perspective.

Previous reviews on the cost of illness (COI) of Parkinson's disease (PD) have often focused on health-care costs due to PD, underestimating its effects on other sectors. This systematic review determines the COI of PD from a societal perspective. The protocol was registered in PROSPERO (ID: CRD42023428937). Embase, Medline, and EconLit were searched up to October 12, 2023, for studies determining the COI of PD from a societal perspective. From 2812 abstracts, 17 studies were included. The COI of PD averaged €20,911.37 per patient per year, increasing to almost €100,000 in the most severely affected patients. Health-care costs accounted for 46.1% of total costs, followed by productivity loss (37.4%) and costs to patient and family (16.4%). The COI of PD strongly varied between different geographical regions, with costs in North America 3.6 times higher compared to Asia. This study is the first to identify the relative importance of different cost items. Most important were reduced employment, government benefits, informal care, medication, nursing homes, and hospital admission. There was strong variety in the cost items that were included, with 55.2% of cost items measured in fewer than half of articles. Our review shows that PD-COI is high and appears in various cost sectors, with strong variety in the cost items included in different studies. Therefore, a guideline for the measurement of COI in PD should be developed to harmonize this. This article provides a first step toward the development of such a tool by identifying which cost items are most relevant. © 2024 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Integrated Devices: A New Regulatory Pathway to Promote Revolutionary Innovation.

Policy Points Current medical device regulatory frameworks date back half a century and are ill suited for the next generation of medical devices that involve a significant software component. Existing Food and Drug Administration efforts are insufficient because of a lack of statutory authority, whereas international examples offer lessons for improving and harmonizing domestic medical device regulatory policy. A voluntary alternative pathway built upon two-stage review with individual component review followed by holistic review for integrated devices would provide regulators with new tools to address a changing medical device marketplace.

Konectom™ cognitive processing speed test enables reliable remote, unsupervised cognitive assessment in people with multiple sclerosis: Exploring the use of substitution time as a novel digital outcome measure.

BACKGROUND: The Konectom™ smartphone-based cognitive processing speed (CPS) test is designed to assess processing speed and account for impact of visuomotor function on performance. OBJECTIVE: Evaluate reliability and validity of Konectom CPS Test, performed in clinic and remotely. METHODS: Data were collected from people with multiple sclerosis (PwMS) aged 18-64 years and healthy control participants (HC) matched for age, sex, and education. Remote test-retest reliability (intraclass correlation coefficients, ICC); correlation with established clinical measures (Spearman correlation coefficients); group analyses between cognitively impaired/unimpaired PwMS; and influence of age, sex, education, and upper limb motor function on CPS Test measures were assessed. RESULTS: Eighty PwMS and 66 HC participated. CPS Test measures from remote tests had good test-retest reliability (ICC of 0.67-0.87) and correlated with symbol digit modalities test (highest |ρ| = 0.80, p < 0.0001). Remote measures were stable (change from baseline < 5%) and correlated with MS disability (highest |ρ| = 0.39, p = 0.0004) measured by Expanded Disability Status Scale. CPS Test measures displayed sensitivity to cognitive impairment (highest d = 1.47). Demographics and motor function had the lowest impact on CPS Test substitution time, a measure accounting for visuomotor function. CONCLUSION: Konectom CPS Test measures provide valid, reliable remote measurements of cognitive processing speed in PwMS.

Real-world smartphone data can trace the behavioural impact of epilepsy: A case study.

BACKGROUND: Neurobehavioural comorbidities have a detrimental effect on the quality of life of people with epilepsy, yet tracking their impact is challenging as behaviour may vary with seizures and anti-seizure medication (ASM) side effects. Smartphones have the potential to monitor day-to-day neurobehavioural patterns objectively. We present the case of a man in his late twenties with drug-resistant focal epilepsy in whom we ascertained the effects of ASM withdrawal and a convulsive seizure on his touchscreen interactions. METHODS: Using a dedicated app, we recorded over 185 days the timestamps of 718,357 interactions. We divided the various smartphone behaviours according to the next-interval dynamics of the interactions by using a joint interval distribution (JID). During two ASM load transitions, namely before versus during tapering and tapering versus restarting medication, we used cluster-based permutation tests to compare the JIDs. We also compared the JID of the seizure day to the average of the previous 3 days. RESULTS: The cluster-based permutation tests revealed significant differences, with accelerated next-interval dynamics during tapering and a reversal upon medication restart. The day of the convulsion exhibited a marked slowing of next-interval dynamics compared to the preceding 3 days. CONCLUSION: Our findings suggest that the temporal dynamics of smartphone touchscreen interactions may help monitor neurobehavioural comorbidities in neurological care.