Patient-centered Decision Research Articles

Integrated oncological treatment decision-making: Creating a practice of patient-centred decision-making.

Integrated oncological treatment decision-making: Creating a practice of patient-centred decision-making.

The CT-derived fat-free muscle fraction is associated with inflammation and predicts outcome in patients with aortic stenosis undergoing TAVR

Abstract Background The ESC guidelines underscore the importance of objective risk stratification in making patient-centered decision for valve interventions. However, they primarily rely on surgical risk scores, not considering essential factors such as frailty. Computed tomography (CT) is a routine part of the pre-interventional workup in patients undergoing TAVR and allows for body composition analysis, including the assessment of fat-free muscle fraction (FFMF) as an indicator of muscle quality. Purpose This study aimed to assess the correlation between FFMF and both inflammation and endocrine disorders, and to investigate the predictive value of FFMF in patients with aortic stenosis undergoing TAVR. Methods The study included 789 patients undergoing TAVR between 2017 and 2019. Evaluations involved CT scans to assess body composition. Using densitometric thresholds, the skeletal muscle area at L3/L4 level was separated into fatty and lean muscle to calculate the FFMF. The cohort was divided into tertiles of high, medium, and low FFMF, Figure 1. Results The study population was 45.5% female with a mean age of 81.2±6.0 years. Overall, 261 (33.1%) patients had a high FFMF, 293 (37.1%) had a medium FFMF, and 235 (29.8%) had a low FFMF. Patients with a low FFMF were older (82.3±5.9 vs 81.6±5.6 vs 79.8±6.2 years, p<0.01) and had higher rates of atrial fibrillation (52 vs 43 vs 37%, p<0.01), compared to those with a medium and high FFMF. Regarding body composition, low FFMF patients had a higher percentage of body fat (28.7±11.2 vs 26.8±9.1 vs 24.2±9.6%, p=0.01) and a lower percentage of body muscle (30.9±5.3 vs 31.3±4.2 vs 32.7±4.4%, p=0.03). Moreover, a low FFMF was associated with inflammation, as indicated by increased levels of C-reactive protein (6.3 vs 4.2 vs 3.1 mg/l, p<0.01) and procalcitonin (0.06 vs 0.05 vs 0.05 µg/l, p=0.01). Endocrinological assessment revealed lower levels of estradiol (6.8 vs 14.7 vs 15.0 pg/ml, p=0.02) and testosterone (0.18 vs 0.48 vs 2.35 ng/ml, p<0.01) as well as higher levels of cortisol (8.9 vs 7.7 vs 7.6μg/dl, p=0.05) in low FFMF patients. Regarding clinical outcomes, low FFMF was associated with increased one-year mortality (23.4%) compared to medium (11.6%) or low FFMF (3.8%, p<0.01), Figure 2A. This difference persisted over five years (p<0.01), Figure 2B. ROC curve analysis showed that FFMF had the strongest association with one-year mortality (AUC 0.75, p<0.01) and was superior to the STS-PROM (AUC 0.65) and EuroSCORE II (AUC 0.64). Multivariate analysis revealed that low FFMF was independently associated with mortality following TAVR (OR: 3.19 [CI: 1.64 – 6.22], p<0.01). Conclusion The CT-derived FFMF is associated with inflammation and endocrinological disorder in patients undergoing TAVR. Importantly, a low FFMF is a strong and independent predictor of dismal outcomes. FFMF assessment can seamlessly integrate into routine pre-interventional CTs, offering a promising objective parameter for outcome prediction.

Perspectives and Misconceptions of an Online Adult Male Cohort Regarding Prostate Cancer Screening.

Congruent with most guideline publishers, the Canadian Urological Association (CUA) recommends shared decision-making (SDM) on PSA screening (PSAS) for prostate cancer (PCa) following a discussion of its benefits and harms. However, there are limited data on how the general male population feels about these topics. A survey was completed by 906 male-identifying participants (age > 18) recruited via Amazon Mechanical Turk (MTurk), which is a crowdsourcing platform providing minimal compensation. Participants answered questions regarding demographics (15), personal/family history (9), PCa/PSA knowledge (41), and opinions regarding PSAS (45). The median age was 38.2 (SD = 12.0), with 22% reporting a family history of PCa and 20% reporting personally undergoing PSAS. Although most participants had heard of PCa (85%) and that they could be screened for it (81%), they generally did not feel knowledgeable about PCa or PSAS guidelines. Most want to talk to their clinician about PCa and PSAS (74%) and are supportive of SDM (48%) or patient-centered decision-making (25%). In general, participants thought PSAS was still worthwhile, even if it led to additional testing or side effects. Similarly, participants thought higher-risk patients should be screened earlier (p < 0.001). A number of misconceptions were evident in the responses. Men approaching the age of PSAS do not feel knowledgeable about PCa or PSAS and want their clinician to discuss these topics with them. The majority believe in PSAS and would like to undergo this screening following SDM. Clinicians also have a role in correcting common misconceptions about PCa.

Comparing Innervated and Non-Innervated Glabrous Skin Flaps for Volar Digital Defects: Insights from Patient-Reported Outcomes.

Volar soft tissue defects in digits necessitate reconstructions that restore appearance sensation and minimize complications. This study compares innervated toe pulp (TP) and non-innervated medialis pedis (MP) flaps for reconstructing such defects, focusing on objective and subjective outcomes. Between 1998 and 2017, 101 free glabrous skin flap reconstructions were performed at our institution for volar digital soft tissue injuries, comprising 75 TP and 26 MP flaps. Follow-up assessments included the Michigan Hand Outcomes Questionnaire, Disabilities of the Arm, Shoulder and Hand Questionnaire, Foot and Ankle Disability Index, and sensory testing (static and moving two-point discrimination, Semmes-Weinstein monofilament test). Data analysis utilized the Mann-Whitney U test and Pearson correlation coefficients. The study cohort included 29 participants (15 TP, 14 MP) with an average follow-up of 106 months. Functional and sensory outcomes revealed no significant differences between TP and MP flaps. Both flap types achieved satisfactory function and sensibility, with no statistically significant distinctions in patient-reported outcomes. Subjective complaints were similarly distributed across both groups, with a few reports of cold intolerance and discomfort at the donor site in the TP group. TP and MP flaps provide adequate coverage and sensory outcomes for volar digital defects without significant differences between innervated and non-innervated flap transfers. The flap choice should be tailored to individual patient needs and defect characteristics, emphasizing the importance of patient-centered decision-making in reconstructive surgery. Further research is required to explore the long-term outcomes of these reconstruction methods, especially for larger defects.

Patient-Identified Treatment Goals for Psoriatic Disease: Results From a US Patient Survey.

Despite advancements in the treatment landscape for psoriasis (PsO) and psoriatic arthritis (PsA), some patients may not achieve the desired disease improvement due to undertreatment. Understanding patient perspectives on treatment expectations can inform patient-centered decisions and enhance treatment satisfaction. To describe patient-identified treatment goals and expectations for managing psoriatic disease. A cross-sectional study was conducted using a survey through MyPsoriasisTeam, an online social community. The survey was available to its US-based patients aged ≥21years with self-reported diagnoses of PsO and/or PsA. The study assessed patients' treatment goals, satisfaction with treatment outcomes, and satisfaction with health care providers (HCPs). Responses were summarized using descriptive statistics. This analysis included 386 patients (PsO, n = 130; PsA with/without PsO, n = 256). Treatment goals varied by psoriatic disease type. The top 3 treatment goals for PsO were reduce itching (73.1%), reduction in size/thickness (68.5%), and reduction in the number of plaques (63.1), and for PsA, were reducing joint pain (77.7%), lessening fatigue (64.8%), and reducing joint stiffness (62.1%). Patient satisfaction with treatment outcomes was low (extremely/very satisfied: PsO, 7.5%/8.5% and PsA, 9.2%/20.2%). Overall, 73.1% with PsO were treated by a dermatologist, and a dermatologist or rheumatologist treated 74.6% with PsA. Overall, patient satisfaction with HCPs who treated their disease was lacking (PsO, 19.3% and 19.3%; PsA, 27.3% and 33.6% were extremely and very satisfied, respectively). These findings suggest the need for enhanced communication between patients and HCPs to align treatment goals and expectations and to improve treatment satisfaction and disease management.

Development of the World Federation of Hemophilia Shared Decision-Making Tool.

The use of shared decision-making (SDM) in clinical settings is becoming more prevalent. The evolving and increasingly complex treatment landscape of haemophilia management has augmented the need and desire for SDM between patients and their healthcare team. SDM tools have been used in other chronic conditions and can be an effective form of education for patients and clinicians. The World Federation of Hemophilia (WFH) partnered with people with haemophilia (PWH), patient advocacy groups, and healthcare practitioners to form an expert working group to develop an educational tool for PWH and their caregivers. The primary objectives included educating PWH on the available prophylactic treatments and facilitating discussion between PWH and their healthcare team. The tool was proposed and developed by the expert working group, workshopped at conference round tables, and evaluated in two focus groups. The interactive WFH SDM Tool guides users through the SDM treatment journey and provides an opportunity for reflection on current disease impact and treatment preferences, educational fact sheets and videos, and a comparison between treatment classes. Two forms of the SDM Tool are available: an online platform with a summary page that may be printed and shared and a printable workbook. All evidence in the tool is based on the prescribing information or phase III clinical trial publications. The Tool will be updated twice each year. The WFH SDM Tool is the first available resource that translates published guidance on SDM in haemophilia into a practical, user-friendly tool aimed at facilitating patient-centred treatment decisions.

Advance Care Planning of Patients Undergoing High-Risk Surgery: A Concept Analysis

The aim of this research was to clarify the concept of advance care planning (ACP) for patients undergoing high-risk surgery. The Walker &amp; Avant’s approach to concept analysis was used. ACP for the patient who received a high-risk surgery was defined as follows: patients who are aware of the risks of surgery are initiated voluntarily with the need to participate in anticipatory decision-making. To do this, patients define their life-prolonging treatment, provided that appropriate treatment is guaranteed, and prepare for end-of-life care decisions through discussions involving healthcare providers and surrogate decision-makers. It is a continuous, patient-centered decision that allows the patient’s treatment goals to transition over time. The goal of the ACP is to focus on quality of life and care rather than determining end-of-life care. The development of this concept contributes to an assessment of the value of ACP support, which can lead to improved approaches to help patients recover in a short period.

How Do Australians Manage Diagnostic Testing Risks? Focus Groups Linked to a Model of Behaviour Change.

Diagnostic tests carry significant risks, and communications are needed to help lay people consider these. The development of communications has been hindered by poor knowledge about how lay people understand and negotiate testing risks. We examined lay Australians' perceptions of diagnostic testing risks and how these risks are managed. We completed 12 semistructured online focus groups with 61 Australian adults (18+) between April and June 2022. Participants were divided into younger/older (> 50 years) and male/female groups. Using semistructured discussion and exploring two hypothetical scenarios, we examined attitudes to diagnostic tests, their risks and how test risks were managed. Themes were identified, subanalysed to identify age and gender differences and mapped to the COM-B model of behaviour change. The six themes provided detailed accounts of how participants considered themselves able, empowered and assertive when negotiating testing risks and of complex ways in which relationships with health workers, personal experiences and structural factors influenced negotiating testing risks. COM-B identified multiple opportunities for leveraging these lay beliefs in health promotion. It also identified barriers, including narrow concepts of testing risks, challenges during shared decision-making and overestimation of personal influence on testing decisions. Our findings matter because they are a novel, detailed account of testing risk beliefs, linked to a model for behaviour change. This will directly inform development of test risk/benefit communications, which are a research priority. The study design enabled participants to influence the discussion agenda, and they could comment on the analysis. Participants contributed insights about their needs, beliefs and experiences related to medical testing, and these will be used to shape future patient-centred decision tools.

In-Center Hemodialysis Experiences Among Latinx Adults: A Qualitative Study

Latinx individuals are more likely to start and remain receiving in-center hemodialysis, over home dialysis, than non-Latinx White individuals. The objective of our study was to understand the drivers of sustained in-center dialysis and deterrents of switching to home dialysis use for Latinx individuals receiving in-center dialysis. This qualitative study used semistructured one-on-one interviews. Latinx adults receiving in-center hemodialysis therapy at 2 urban dialysis clinics in Denver, Colorado between November 2021 and March2023. In-center hemodialysis, Latinx ethnicity. Qualitative. Interviews were analyzed with thematic analysis using inductive coding. Theoretical framework development used principles of grounded theory. In total, 25 Latinx adults (10 [40%] female and 15 [60%] male) receiving in-center hemodialysis therapy participated. One theme demonstrated that Latinx individuals experienced hardship with in-center dialysis but used Latinx values to persevere: Psychosocial resilience using Latinx cultural values (faith and spiritual coping, belief in predestination and acceptance, optimism and positive attitude toward treatment, and positive relationships with health care professionals and peers). Two themes illustrate barriers to starting or switching to home dialysis: Insufficient knowledge of kidney replacement therapy (lack of awareness of kidney disease, lack of preparation for dialysis) and Barriers to patient-centered decision making in dialysis treatment (lack of peer perspective toguide dialysis decision making, fear and apprehension of home dialysis, lack of socioemotional support, perception of housing issues). Most participants were from the same geographic area and country of origin, and some may have been uninsured because of immigration status. As Latinx people are less likely to be treated with home dialysis modalities, this study offers important context as to what factors drove sustained in-center dialysis use for this population. Coping mechanisms that promoted resilience with in-center dialysis treatment motivated individuals to remain on in-center hemodialysis, and positive dialysis relationships in the dialysis center strengthened this experience. Switching to home dialysis is hindered by lack of knowledge as well as lack of patient-centered dialysis decision making. Understanding the drivers of sustained in-center hemodialysis use for Latinx individuals is important for future efforts at improving patient-centered education, framing conversations around modality choice, and care for this population.

"Dr. AI Will See You Now": How Do ChatGPT-4 Treatment Recommendations Align With Orthopaedic Clinical Practice Guidelines?

Artificial intelligence (AI) is engineered to emulate tasks that have historically required human interaction and intellect, including learning, pattern recognition, decision-making, and problem-solving. Although AI models like ChatGPT-4 have demonstrated satisfactory performance on medical licensing exams, suggesting a potential for supporting medical diagnostics and decision-making, no study of which we are aware has evaluated the ability of these tools to make treatment recommendations when given clinical vignettes and representative medical imaging of common orthopaedic conditions. As AI continues to advance, a thorough understanding of its strengths and limitations is necessary to inform safe and helpful integration into medical practice. (1) What is the concordance between ChatGPT-4-generated treatment recommendations for common orthopaedic conditions with both the American Academy of Orthopaedic Surgeons (AAOS) clinical practice guidelines (CPGs) and an orthopaedic attending physician's treatment plan? (2) In what specific areas do the ChatGPT-4-generated treatment recommendations diverge from the AAOS CPGs? Ten common orthopaedic conditions with associated AAOS CPGs were identified: carpal tunnel syndrome, distal radius fracture, glenohumeral joint osteoarthritis, rotator cuff injury, clavicle fracture, hip fracture, hip osteoarthritis, knee osteoarthritis, ACL injury, and acute Achilles rupture. For each condition, the medical records of 10 deidentified patients managed at our facility were used to construct clinical vignettes that each had an isolated, single diagnosis with adequate clarity. The vignettes also encompassed a range of diagnostic severity to evaluate more thoroughly adherence to the treatment guidelines outlined by the AAOS. These clinical vignettes were presented alongside representative radiographic imaging. The model was prompted to provide a single treatment plan recommendation. Each treatment plan was compared with established AAOS CPGs and to the treatment plan documented by the attending orthopaedic surgeon treating the specific patient. Vignettes where ChatGPT-4 recommendations diverged from CPGs were reviewed to identify patterns of error and summarized. ChatGPT-4 provided treatment recommendations in accordance with the AAOS CPGs in 90% (90 of 100) of clinical vignettes. Concordance between ChatGPT-generated plans and the plan recommended by the treating orthopaedic attending physician was 78% (78 of 100). One hundred percent (30 of 30) of ChatGPT-4 recommendations for fracture vignettes and hip and knee arthritis vignettes matched with CPG recommendations, whereas the model struggled most with recommendations for carpal tunnel syndrome (3 of 10 instances demonstrated discordance). ChatGPT-4 recommendations diverged from AAOS CPGs for three carpal tunnel syndrome vignettes; two ACL injury, rotator cuff injury, and glenohumeral joint osteoarthritis vignettes; as well as one acute Achilles rupture vignette. In these situations, ChatGPT-4 most often struggled to correctly interpret injury severity and progression, incorporate patient factors (such as lifestyle or comorbidities) into decision-making, and recognize a contraindication to surgery. ChatGPT-4 can generate accurate treatment plans aligned with CPGs but can also make mistakes when it is required to integrate multiple patient factors into decision-making and understand disease severity and progression. Physicians must critically assess the full clinical picture when using AI tools to support their decision-making. ChatGPT-4 may be used as an on-demand diagnostic companion, but patient-centered decision-making should continue to remain in the hands of the physician.

Reviewing Ethical Guidelines for the Care of Patients with Do-Not-Resuscitate Orders after 30 Years: Rethinking Our Approach at a Time of Transition.

The American Society of Anesthesiologists (ASA) opposes automatic reversal of do-not-resuscitate orders during the perioperative period, instead advocating for a goal-directed approach that aligns decision-making with patients' priorities and clinical circumstances. Implementation of ASA guidelines continues to face significant barriers including time constraints, lack of longitudinal relationships with patients, and difficulty translating goal-focused discussion into concrete clinical plans. These challenges mirror those of advance care planning more generally, suggesting a need for novel frameworks for serious illness communication and patient-centered decision-making. This review considers ASA guidelines in the context of ongoing transitions to serious illness communication and increasingly multidisciplinary perioperative care. It aims to provide practical guidance for the practicing anesthesiologist while also acknowledging the complexity of decision-making, considering limitations inherent to anesthesiologists' role, and outlining a need to conceptualize delivery of ethically informed care as a collaborative, multidisciplinary endeavor.

Clinician perspectives on the perioperative roles and responsibilities of anesthesia, surgery, and primary care

BackgroundAlthough high-risk older patients benefit from a multidisciplinary approach to perioperative care, the specific roles and responsibilities of the clinicians involved have yet to be adequately characterized. MethodsQualitative analysis of semi-structured interviews with four anesthesia preoperative clinic providers, seven surgeons, and nine primary care providers in northern New England. ResultsThe analysis revealed both distinct and overlapping roles and responsibilities. Anesthesia providers were described as a “safety net” and surgeons as “captain of the ship”, in charge of getting “all the ducks in a row” to avoid surgery delays and cancellations. Primary care providers saw themselves as the “quarterback”, ensuring care continuity and consideration of patient psychosocial factors. ConclusionsWhile all have a shared responsibility for facilitating patient-centered decision-making and a safe perioperative course, each discipline has different areas of focus and expertise. Role clarification can help optimize the distribution of responsibilities and enhance perioperative communication and collaboration.

CASCADE: A Community-Engaged Action Model for Generating Rapid, Patient-Engaged Decisions in Clinical Research.

Integrating patient and community input is essential to the relevance and impact of patient-focused research. However, specific techniques for generating patient and community-informed research decisions remain limited. Here, we describes a novel CASCADE method (Community-Engaged Approach for Scientific Collaborations and Decisions) that was developed and implemented to make actionable, patient-centered research decisions during a federally funded clinical trial. The CASCADE approach includes 7 key pillars: (1) identifying a shared, specific, and actionable goal; (2) centering community input; (3) integrating both pre-registered statistical analyses and exploratory "quests"; (4) fixed-pace scheduling, supported by technology; (5) minimizing opportunities for cognitive biases typical to group decision making; (6) centering diversity experiences and perspectives, including those of individual patients; (7) making decisions that are community-relevant, rigorous, and feasible. Here, we implemented these pillars within a three-day CASCADE panel, attended by diverse members of a research project team that included community interest-holders. The goal of our panel was to identify ways to improve an algorithm for matching patients to specific types of telehealth programs within an active, federally funded clinical trial. The CASCADE panel was attended by 27 participants, including 5 community interest-holders. Data reviewed to generate hypotheses and make decisions included (1) pre-registered statistical analyses, (2) results of 12 "quests" that were launched during the panel to answer specific panelist questions via exploratory analyses or literature review, (3) qualitative and quantitative patient input, and (4) team member input, including by staff who represented the target patient population for the clinical trial. Panel procedures resulted in the generation of 18 initial and 12 final hypotheses, which were translated to 19 decisional changes. The CASCADE approach was an effective procedure for rapidly, efficiently making patient-centered decisions during an ongoing, federally funded clinical trial. Opportunities for further development will include exploring best-practice structural procedures, enhancing greater opportunities for pre-panel input by community interest-holders, and determining how to best standardize CASCADE outputs. The CASCADE procedure was developed in the context of NCT05999448.

Unveiling the Burden of Drug-Induced Impulsivity: A Network Analysis of the FDA Adverse Event Reporting System.

Impulsivity induced by dopaminergic agents, like pramipexole and aripiprazole, can lead to behavioral addictions that impact on social functioning and quality of life of patients and families (e.g., resulting in unemployment, marital problems, anxiety). These secondary effects, interconnected in networks of signs and symptoms, are usually overlooked by clinical trials, not reported in package inserts, and neglected in clinical practice. This study explores the syndromic burden of impulsivity induced by pramipexole and aripiprazole, pinpointing key symptoms for targeted mitigation. An event-event Information Component (IC) on the FDA Adverse Event Reporting System (FAERS) (January 2004 to March 2022) identified the syndrome of events disproportionally co-reported with impulsivity, separately for pramipexole and aripiprazole. A greedy-modularity clustering on composite network analyses (positive pointwise mutual information [PPMI], Ising, Φ) identified sub-syndromes. Bayesian network modeling highlighted possible precipitating events. Suspected drug-induced impulsivity was documented in 7.49% pramipexole and 4.50% aripiprazole recipients. The highest IC concerned obsessive-compulsive disorder (reporting rate = 26.77%; IC median = 3.47, 95% confidence interval [CI] = 3.33-3.57) and emotional distress (21.35%; 3.42, 3.26-3.54) for pramipexole, bankruptcy (10.58%; 4.43, 4.26-4.55) and divorce (7.59%; 4.38, 4.19-4.53) for aripiprazole. The network analysis identified delusional jealousy and dopamine dysregulation sub-syndromes for pramipexole, obesity-hypoventilation and social issues for aripiprazole. The Bayesian network highlighted anxiety and economic problems as potentially precipitating events. The under-explored consequences of drug-induced impulsivity significantly burden patients and families. Network analyses, exploring syndromic reactions and potential precipitating events, complement traditional techniques and clinical judgment. Characterizing the secondary impact of reactions will support informed patient-centered decision making.

What could improve surgical data system at health facilities with high surgical volume in Ethiopia?

BackgroundThe effective management of surgical and anesthesia care relies on quality data and its readily availability for both patient-centered decision-making and facility-level improvement efforts. Recognizing this critical need, the Strengthening Systems for Improved Surgical Outcomes (SSISO) project addressed surgical care data management and information use practices across 23 health facilities from October 2019 to September 2022. This study aimed to evaluate the effectiveness of SSISO interventions in enhancing practices related to surgical data capture, reporting, analysis, and visualization.MethodsThis study employed a mixed method, pre- post intervention evaluation design to assess changes in data management and utilization practices at intervention facilities. The intervention packages included capacity building trainings, monthly mentorship visits facilitated by a hub-and-spoke approach, provision of data capture tools, and reinforcement of performance review teams. Data collection occurred at baseline (February – April 2020) and endline (April – June 2022). The evaluation focused on the availability and appropriate use of data capture tools, as well as changes in performance review practices. Appropriate use of registers was defined as filling all the necessary data onto the registers, and this was verified by completeness of selected key data elements in the registers.ResultsThe proportion of health facilities with Operation Room (OR) scheduling, referral, and surgical site infection registers significantly increased by 34.8%, 56.5% and 87%, respectively, at project endline compared to baseline. Availability of OR and Anesthesia registers remained high throughout the project, at 91.3% and 95.6%, respectively. Furthermore, the appropriate use of these registers improved, with statistically significant increases observed for OR scheduling registers (34.8% increase). Increases were also noted for OR register (9.5% increase) and anesthesia register (4.5% increase), although not statistically significant. Assessing the prior three months reports, the report submissions to the Ministry of Health/Regional Health Bureau (MOH/RHB) rose from 85 to 100%, reflecting complete reporting at endline period. Additionally, the proportion of surgical teams analyzing and displaying data for informed decision-making significantly increased from 30.4% at baseline to 60.8% at endline period.ConclusionThe implemented interventions positively impacted surgical data management and utilization practice at intervention facilities. These positive changes were likely attributable to capacity building trainings and regular mentorship visits via hub-and-spoke approach. Hence, we recommend further investigation into the effectiveness of similar intervention packages in improving surgical data management, data analysis and visualization practices in low- and middle-income country settings.

Artificial intelligence in total and unicompartmental knee arthroplasty

The application of Artificial intelligence (AI) and machine learning (ML) tools in total (TKA) and unicompartmental knee arthroplasty (UKA) emerges with the potential to improve patient-centered decision-making and outcome prediction in orthopedics, as ML algorithms can generate patient-specific risk models. This review aims to evaluate the potential of the application of AI/ML models in the prediction of TKA outcomes and the identification of populations at risk.An extensive search in the following databases: MEDLINE, Scopus, Cinahl, Google Scholar, and EMBASE was conducted using the PIOS approach to formulate the research question. The PRISMA guideline was used for reporting the evidence of the data extracted. A modified eight-item MINORS checklist was employed for the quality assessment. The databases were screened from the inception to June 2022.Forty-four out of the 542 initially selected articles were eligible for the data analysis; 5 further articles were identified and added to the review from the PUBMED database, for a total of 49 articles included. A total of 2,595,780 patients were identified, with an overall average age of the patients of 70.2 years ± 7.9 years old. The five most common AI/ML models identified in the selected articles were: RF, in 38.77% of studies; GBM, in 36.73% of studies; ANN in 34.7% of articles; LR, in 32.65%; SVM in 26.53% of articles.This systematic review evaluated the possible uses of AI/ML models in TKA, highlighting their potential to lead to more accurate predictions, less time-consuming data processing, and improved decision-making, all while minimizing user input bias to provide risk-based patient-specific care.

Trauma patients with metastatic cancer undergoing emergent surgery: A matched cohort analysis

BackgroundThere is a paucity of literature guiding trauma surgeons in the care of patients with active metastatic cancer (MC). Even less is known regarding outcomes for MC patients requiring emergent surgery after trauma. We hypothesized that trauma patients with active Metastatic Cancer (MC) have an increased mortality rate and undergo increased rates of withdrawal of care (WoC) within 72-hours following emergent operations, compared to similarly matched patients without MC. MethodsPatients with active MC at the time of traumatic injury were matched 1:2 against patients without active MC based on demographics, comorbidities, vital signs on admission, and injury profile. ResultsFrom 43,826 patients, 0.2 % had MC. After matching 39 MC patients to 78 without MC, there was no difference in demographics, comorbidities, injury severity score, mechanism of injury, vitals on admission (blood pressure, heart rate, respiration rate) and need for blood transfusion (all p > 0.05). Compared to patients without MC, patients with MC had higher rates and associated risk of death during index hospitalization (38.5 % vs. 15.2 %, p = 0.005; OR 3.49, CI 1.43–8.51, p = 0.006), as well as a higher rate and associated risk of WoC within 72-hours (12.8 % vs. 1.3 %, p = 0.007; OR 11.47, CI 1.29–101.93, p = 0.029). ConclusionTrauma patients with MC requiring emergent thoracic or abdominal surgery have a high risk of death and an over ten-fold higher associated risk for WoC within the first three days. In some cases, palliative care consultation should be considered, and counseling should be offered to this high-risk trauma population to enable individualized and patient-centric decisions. Key messageThis research highlights the importance of a multidisciplinary team consisting of trauma surgeons, oncologist, and palliative care physicians in caring for the high-risk trauma patients with disseminated cancer requiring urgent surgery.

Preoperative prediction of nodal status using clinical data and artificial intelligence derived mammogram features enabling abstention of sentinel lymph node biopsy in breast cancer.

Patients with clinically node-negative breast cancer have a negative sentinel lymph node status (pN0) in approximately 75% of cases and the necessity of routine surgical nodal staging by sentinel lymph node biopsy (SLNB) has been questioned. Previous prediction models for pN0 have included postoperative variables, thus defeating their purpose to spare patients non-beneficial axillary surgery. We aimed to develop a preoperative prediction model for pN0 and to evaluate the contribution of mammographic breast density and mammogram features derived by artificial intelligence for de-escalation of SLNB. This retrospective cohort study included 755 women with primary breast cancer. Mammograms were analyzed by commercially available artificial intelligence and automated systems. The additional predictive value of features was evaluated using logistic regression models including preoperative clinical variables and radiological tumor size. The final model was internally validated using bootstrap and externally validated in a separate cohort. A nomogram for prediction of pN0 was developed. The correlation between pathological tumor size and the preoperative radiological tumor size was calculated. Radiological tumor size was the strongest predictor of pN0 and included in a preoperative prediction model displaying an area under the curve of 0.68 (95% confidence interval: 0.63-0.72) in internal validation and 0.64 (95% confidence interval: 0.59-0.69) in external validation. Although the addition of mammographic features did not improve discrimination, the prediction model provided a 21% SLNB reduction rate when a false negative rate of 10% was accepted, reflecting the accepted false negative rate of SLNB. This study shows that the preoperatively available radiological tumor size might replace pathological tumor size as a key predictor in a preoperative prediction model for pN0. While the overall performance was not improved by mammographic features, one in five patients could be omitted from axillary surgery by applying the preoperative prediction model for nodal status. The nomogram visualizing the model could support preoperative patient-centered decision-making on the management of the axilla.

Treatment of chronic kidney disease in older populations.

As the world population ages, an expected increase in the prevalence of chronic kidney disease (CKD) among older individuals will pose a considerable challenge for health care systems in terms of resource allocation for disease management. Treatment strategies for older patients with CKD should ideally align with those applied to the general population, focusing on minimizing cardiovascular events and reducing the risk of progression to kidney failure. Emerging therapies, such as SGLT-2 inhibitors and GLP-1 receptor agonists, hold promise for the effective management of CKD in older individuals. In addition, non-pharmacological interventions such as nutritional and exercise therapies have a crucial role. These interventions enhance the effects of pharmacotherapy and, importantly, contribute to the maintenance of cognitive function and overall quality of life. Various factors beyond age and cognitive function must be taken into account when considering kidney replacement therapy for patients with kidney failure. Importantly, all treatment options, including dialysis, transplantation and conservative management approaches, should be tailored to the individual through patient-centred decision-making. The dynamic integration of digital technologies into medical practice has the potential to transform the management of CKD in the aging population.

Design of a Model Using Machine Learning and Deep Dyna Q Learning Integration for Improved Disease Prediction in Remote Healthcare

In the domain of proactive healthcare management, the imperative for remote health monitoring has escalated, the remote health care in this scenario specially means, the patient is seating at the remote location that is not in the hospital setting, and doctor or healthcare worker is monitoring the health parameters gathered using biomedical sensors and passed through the network. Conventional methodologies, while partially effective, encounter challenges in predictive precision, responsiveness to evolving health dynamics, and managing the vast array of patient data. These limitations underscore the demand for a sophisticated, holistic solution catering to diverse use cases. This work introduces a pioneering framework amalgamating traditional machine learning (ML) models with the advanced capabilities of Deep Dyna Q Learning process to overcome existing constraints. This framework strategically utilizes ensemble of traditional algorithms which amalgamates the strengths of these diverse models. Central to this model is the integration of Deep Dyna Q Learning, empowering the system with real-time adaptability and dynamic decision-making process through reinforcement learning principles, thereby deriving insights from historical and simulated datasets to foster more nuanced, patient-centric decisions. The impact of this comprehensive approach is profound, evidenced by preliminary results showcasing significant enhancements in the efficiency of remote health monitoring systems. Notably, the model achieves increase in precision, accuracy and recall for disease prediction. These improvements signify a paradigm shift towards proactive and efficient healthcare interventions, especially in remote settings. The fusion of traditional ML techniques with Deep Dyna Q Learning emerges as a potent solution, heralding a revolution in remote health monitoring and establishing a new benchmark for proactive healthcare delivery scenarios.