Explore the vast range of titles available.

ABSTRACTObjectivesThis study examined the effectiveness of an integrated care pathway (ICP), including a medication algorithm, to treat agitation associated with dementia. DesignAnalyses of data (both prospective and retrospective) collected during routine clinical care. SettingGeriatric Psychiatry Inpatient Unit. ParticipantsPatients with agitation associated with dementia (n = 28) who were treated as part of the implementation of the ICP and those who received treatment-as-usual (TAU) (n = 28) on the same inpatient unit before the implementation of the ICP. Two control groups of patients without dementia treated on the same unit contemporaneously to the TAU (n = 17) and ICP groups (n = 36) were included to account for any secular trends. InterventionICP. MeasurementsCohen Mansfield Agitation Inventory (CMAI), Neuropsychiatric Inventory Questionnaire (NPIQ), and assessment of motor symptoms were completed during the ICP implementation. Chart review was used to obtain length of inpatient stay and rates of psychotropic polypharmacy. ResultsPatients in the ICP group experienced a reduction in their scores on the CMAI and NPIQ and no changes in motor symptoms. Compared to the TAU group, the ICP group had a higher chance of an earlier discharge from hospital, a lower rate of psychotropic polypharmacy, and a lower chance of having a fall during hospital stay. In contrast, these outcomes did not differ between the two control groups. ConclusionsThese preliminary results suggest that an ICP can be used effectively to treat agitation associated with dementia in inpatients. A larger randomized study is needed to confirm these results.

An inherent risk of algorithmic personalization is disproportionate targeting of individuals from certain groups (or demographic characteristics, such as gender or race), even when the decision maker does not intend to discriminate based on those “protected” attributes. This unintended discrimination is often caused by underlying correlations in the data between protected attributes and other observed characteristics used by the algorithm to create predictions and target individuals optimally. Because these correlations are hidden in high-dimensional data, removing protected attributes from the database does not solve the discrimination problem; instead, removing those attributes often exacerbates the problem by making it undetectable and in some cases, even increases the bias generated by the algorithm. We propose BEAT (bias-eliminating adapted trees) to address these issues. This approach allows decision makers to target individuals based on differences in their predicted behavior—hence, capturing value from personalization—while ensuring a balanced allocation of resources across individuals, guaranteeing both group and individual fairness. Essentially, the method only extracts heterogeneity in the data that is unrelated to protected attributes. To do so, we build on the general random forest (GRF) framework [S. Athey et al., Ann. Stat. 47, 1148–1178 (2019)] and develop a targeting allocation that is “balanced” with respect to protected attributes. We validate BEAT using simulations and an online experiment with N = 3,146 participants. This approach can be applied to any type of allocation decision that is based on prediction algorithms, such as medical treatments, hiring decisions, product recommendations, or dynamic pricing.

Abstract Objective Lumbar spinal stenosis (LSS) can lead to compression of the neural and vascular elements and is becoming more common due to degenerative changes that occur because of aging processes. Symptoms may manifest as pain and discomfort that radiates to the lower leg, thigh, and/or buttocks. The traditional treatment algorithm for LSS consists of conservative management (physical therapy, medication, education, exercise), often followed by epidural steroid injections (ESIs), and when nonsurgical treatment has failed, open decompression surgery with or without fusion is considered. In this review, the variables that should be considered during the management of patients with LSS are discussed, and the role of each treatment option to provide optimal care is evaluated. Results This review leads to the creation of an evidence-based practical algorithm to aid clinicians in the management of patients with LSS. Special emphasis is directed at minimally invasive surgery, which should be taken into consideration when conservative management and ESI have failed.

Background The ability of machine learning (ML) to process and learn from large quantities of heterogeneous patient data is gaining attention in the precision oncology community. Some remarkable developments have taken place in the domain of image classification tasks in areas such as digital pathology and diagnostic radiology. The application of ML approaches to the analysis of DNA data, including tumor-derived genomic profiles, microRNAs, and cancer epigenetic signatures, while relatively more recent, has demonstrated some utility in identifying driver variants and molecular signatures with possible prognostic and therapeutic applications. Methods We conducted semi-structured interviews with academic and clinical experts to capture the status quo, challenges, opportunities, ethical implications, and future directions. Results Our participants agreed that machine learning in precision oncology is in infant stages, with clinical integration still rare. Overall, participants equated ongoing developments with better clinical workflows and improved treatment decisions for more cancer patients. They underscored the ability of machine learning to tackle the dynamic nature of cancer, break down the complexity of molecular data, and support decision-making. Our participants emphasized obstacles related to molecular data access, clinical utility, and guidelines. The availability of reliable and well-curated data to train and validate machine learning algorithms and integrate multiple data sources were described as constraints yet necessary for future clinical implementation. Frequently mentioned ethical challenges included privacy risks, equity, explainability, trust, and incidental findings, with privacy being the most polarizing. While participants recognized the issue of hype surrounding machine learning in precision oncology, they agreed that, in an assistive role, it represents the future of precision oncology. Conclusions Given the unique nature of medical AI, our findings highlight the field’s potential and remaining challenges. ML will continue to advance cancer research and provide opportunities for patient-centric, personalized, and efficient precision oncology. Yet, the field must move beyond hype and toward concrete efforts to overcome key obstacles, such as ensuring access to molecular data, establishing clinical utility, developing guidelines and regulations, and meaningfully addressing ethical challenges.

Background: Scalp reconstruction requires knowledge of scalp anatomy and reconstructive options. Advances in the field have led to numerous procedures being at the disposal of the reconstructive surgeon, expanding treatment options for patients. Objective: To provide an algorithmic approach and general guidelines to consider when deciding on which scalp surgery will optimize cosmetic and functional outcomes. Methods & materials: Previous literature was searched for the last 20 years to provide an updated guide. Results: Taking into consideration the location, size and local scalp anatomy of a presenting defect will lead to optimal surgical outcomes. Other confounding factors such as bone exposure and extremely large defects will affect decision making. An algorithmic approach has been provided in this review. Conclusion: While many reconstructive surgical options are available, the best ones will depend on individual presentation of scalp defects. Location and size are first line considerations while local scalp anatomy will allow for tailoring of reconstructive options. This will help to maximize cosmetic and aesthetic considerations.

Phakic intraocular lenses (IOL) are a boon for patients who want spectacle independence but are unable to get refractive correction through laser platforms due to high refractive error or certain corneal contraindications. Phakic IOL's (PIOL) have their own set of complications and challenges, the most important being getting the sizing right. This paper attempts to solve the problem of accurate sizing of PIOL's. Parameters needed for calculating the ideal size of PIOL's have been studied in a step by step manner using all possible tools depending upon the availability and preference of the surgeon. The pros and cons of using a particular tool for measurements have been highlighted along with illustrative case examples to help surgeons who are starting PIOL implantation surgery.

The application of machine-learning technologies to medical practice promises to enhance the capabilities of healthcare professionals in the assessment, diagnosis, and treatment, of medical conditions. However, there is growing concern that algorithmic bias may perpetuate or exacerbate existing health inequalities. Hence, it matters that we make precise the different respects in which algorithmic bias can arise in medicine, and also make clear the normative relevance of these different kinds of algorithmic bias for broader questions about justice and fairness in healthcare. In this paper, we provide the building blocks for an account of algorithmic bias and its normative relevance in medicine.

Breast cancer is the most common cancer affecting women globally. Despite the significant impact of deep learning models on breast cancer diagnosis and treatment, achieving fairness or equitable outcomes across diverse populations remains a challenge when some demographic groups are underrepresented in the training data. We quantified the bias of models trained to predict breast cancer stage from a dataset consisting of 1000 biopsies from 842 patients provided by AIM-Ahead (Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity). Notably, the majority of data (over 70%) were from White patients. We found that prior to post-processing adjustments, all deep learning models we trained consistently performed better for White patients than for non-White patients. After model calibration, we observed mixed results, with only some models demonstrating improved performance. This work provides a case study of bias in breast cancer medical imaging models and highlights the challenges in using post-processing to attempt to achieve fairness.

Introduction Hypertension is the leading risk factor for death, affecting over one billion people worldwide, yet control rates are poor and stagnant. We developed a remote hypertension management program that leverages digitally transmitted home blood pressure (BP) measurements, algorithmic care pathways, and patient–navigator communications to aid patients in achieving guideline‐directed BP goals. Methods Patients with uncontrolled hypertension are identified through provider referrals and electronic health record screening aided by population health managers within the Mass General Brigham (MGB) health system. Non‐licensed patient navigators supervised by pharmacists, nurse practitioners, and physicians engage and educate patients. Patients receive cellular or Bluetooth‐enabled BP devices with which they monitor and transmit scheduled home BP readings. Evidence‐based medication changes are made according to a custom hypertension algorithm approved within a collaborative drug therapy management (CDTM) agreement with MGB and implemented by pharmacists. Using patient‐specific characteristics, we developed different pathways to optimize medication regimens. The renin–angiotensin–aldosterone system‐blocker pathway prescribed ARBs/ACE inhibitors first for patients with diabetes, impaired renal function, and microalbuminuria; the standard pathway started patients on calcium channel blockers. Regimens were escalated frequently, adding thiazide‐type diuretics, and including beta blockers and mineralocorticoid receptor antagonists if needed. Discussion We have developed an algorithmic approach for the remote management of hypertension with demonstrated success. A focus on algorithmic decision‐making streamlines tasks and responsibilities, easing the potential for scalability of this model. As the backbone of our remote management program, this clinical algorithm can improve BP control and innovate the management of hypertension in large populations.

Background Dose painting planning would be more complicated due to different levels of prescribed doses and more complex evaluation with conventional plan quality indices considering uniform dose prescription. Therefore, we tried to introduce new indices for evaluating the dose distribution conformity and homogeneity of treatment volumes based on the tumoral cell density and relative volumes of each lesion in prostate IMRT. Methods CT and MRI scans of 20 male patients having local prostate cancer were used for IMRT DP planning. Apparent diffusion coefficient (ADC) images were imported to a MATLAB program to identify lesion regions based on ADC values automatically. Regions with ADC values lower than 750 mm 2 /s and regions with ADC values higher than 750 and less than 1500 mm 2 /s were considered CTV 70Gy (clinical tumor volume with 70 Gy prescribed dose), and CTV 60Gy , respectively. Other regions of the prostate were considered as CTV 53Gy . New plan evaluation indices based on evaluating the homogeneity (IOE(H)), and conformity (IOE(C)) were introduced, considering the relative volume of each lesion and cellular density obtained from ADC images. These indices were compared with conventional homogeneity and conformity indices and IOEs without considering cellular density. Furthermore, tumor control probability (TCP) was calculated for each patient, and the relationship of the assessed indices were evaluated with TCP values. Results IOE (H) and IOE (C) with considering cellular density had significantly lower values compared to conventional indices and IOEs without considering cellular density. (P < 0.05). TCP values had a stronger relationship with IOE(H) considering cell density (R 2  = -0.415), and IOE(C) without considering cell density (R 2  = 0.624). Conclusion IOE plan evaluation indices proposed in this study can be used for evaluating prostate IMRT dose painting plans. We suggested to consider cell densities in the IOE(H) calculation formula and it’s appropriate to calculate IOE(C) without considering cell density values.