Rotator cuff tears are arguably the defining musculoskeletal complaint of middle age. The supraspinatus, the tendon that runs over the top of the shoulder and helps lift the arm away from the body, is the structure most frequently involved. Population studies cited in the report indicate that around twenty percent of people in their sixties carry a rotator cuff tear, a figure that climbs past fifty percent by the eighties. Complete tears often end in the operating theater, but partial-thickness tears occupy an uncomfortable middle ground: there is no consensus on the optimal management strategy, and conventional conservative treatments, including rest, physical therapy, non-steroidal anti-inflammatory drugs, and corticosteroid injections, leave a substantial share of patients with persistent pain and functional limitation. Studies referenced by the authors suggest that up to forty percent of patients fare poorly with these standard approaches, and corticosteroid injections, while offering short-term relief, have been linked in the literature to potential detrimental effects on tendon healing and structural integrity.

The patient at the center of the report was, in many respects, the archetype of this treatment-resistant group. A right-hand-dominant nurse, she had endured twenty-four months of left shoulder pain, on her non-dominant side, driven in part by the repetitive overhead reaching, lifting, and patient-transfer demands of her profession. Her baseline magnetic resonance imaging confirmed a nine-millimeter partial-thickness, articular-sided tear of the supraspinatus tendon, with the remainder of the shoulder unremarkable: no significant bursal thickening, a normal biceps tendon, and an intact acromioclavicular joint. Before electroacupuncture was considered, she had already failed an extensive conservative program, including twelve weeks of structured physiotherapy with ultrasound therapy, manual therapy, and rotator cuff strengthening, six weeks of twice-daily oral diclofenac, and two subacromial injections of methylprednisolone administered two months apart. She was selected retrospectively from routine clinical practice because she met predefined criteria, including complete adherence to treatment and comprehensive clinical and imaging follow-up, and she provided written informed consent for both treatment and publication.

The intervention itself combined a twelve-session electroacupuncture protocol with a daily home exercise program, and the technical details are what give the report its scientific texture. An expert physiotherapist trained in acupuncture inserted single-use stainless steel needles, 0.25 millimeters in diameter and 30 millimeters long, at four shoulder points: Large Intestine 16, Triple Burner 14, Small Intestine 10, and an Ashi point at the tip of the coracoid process, which corresponds anatomically to the region of the supraspinatus insertion and was chosen for focal stimulation. The point selection followed traditional meridian theory and previously published protocols for shoulder disorders, with LI-16 and TB-14 serving as local points and SI-10 as an adjacent one. Electrodes connected LI-16 and TB-14 together, and SI-10 to the coracoid-tip point, delivering a symmetric biphasic pulsed current at a fixed frequency of 5 hertz for twenty minutes per session, with sessions twice weekly.

Current intensity, capped at five milliamperes, was titrated individually to produce a strong but comfortable, non-painful paresthesia, the sensation known in traditional practice as De-Qi, without triggering forceful muscle contractions. Safety considerations were explicit: because the shoulder points lie near the thorax, needle angle and depth at LI-16 and TB-14 were carefully controlled to avoid pleural puncture, and needles were never oriented transversely toward the rib cage. Alongside the needling, the patient followed a phased home program: pendulum exercises and passive range-of-motion work with a cane or pulley in the first two weeks; scapular retraction, isometric holds, and elastic-band rotation exercises from weeks three to six; and a maintenance regimen of strengthening three to four times weekly thereafter. She documented adherence above ninety percent during the active treatment phase, modified her work duties temporarily, and received no oral analgesics, anti-inflammatories, or injections during the treatment period, a detail that strengthens the temporal association between the intervention and her recovery.

The outcomes were striking by any measure. Pain on the numeric rating scale fell from eight out of ten at baseline to three out of ten at week six, and to zero at the six-month follow-up, a one hundred percent reduction. The Disabilities of the Arm, Shoulder and Hand questionnaire score improved from 72.5 to 28.3 at week six and 12.3 at six months, an overall eighty-three percent improvement that far exceeds the established minimal clinically important difference of 10.8 points for shoulder disorders. Range of motion improved across every plane tested: active abduction rose from 95 to 160 degrees by week six and 175 degrees at six months, flexion from 100 to 180 degrees, and external rotation from 25 to 60 degrees. She returned to full work duties by the three-month occupational review, achieving precisely the goals she had set for herself: pain-free work and avoidance of surgery.

The most provocative finding, however, was structural. A repeat magnetic resonance scan at six months, acquired with identical imaging parameters on the same 1.5-Tesla scanner, using oblique coronal T2-weighted fat-suppressed fast spin-echo sequences with 3.5-millimeter slice thickness, showed an estimated reduction in tear dimensions from nine millimeters to approximately four millimeters in the oblique coronal plane. The reviewing shoulder-fellowship-trained orthopedic surgeon also noted a qualitative reduction in T2 signal hyperintensity within the tendon, potentially consistent with decreased tendinosis, although the authors emphasize that signal intensity was assessed descriptively and not normalized to a reference tissue. No progression of the tear or new pathology was identified, and the patient reported no adverse effects beyond mild, transient soreness at the needle sites after the first two sessions, which resolved within twenty-four hours.

The authors are candid about the caveats, and they are substantial. Measurement of partial-thickness tears is inherently variable, depending on slice selection, sequence parameters, and reader interpretation, and the reviewing surgeon was not blinded to the time point. More fundamentally, the concurrent home exercise program is the report’s most significant confounder: because electroacupuncture and exercise were delivered as a multimodal package, it is impossible to isolate the specific effect of either component. The improvements may reflect synergy, or they may have been driven primarily by the rehabilitative exercises, with electroacupuncture providing adjunctive pain relief that facilitated adherence. Natural healing, placebo effects, and regression to the mean all remain possible in an uncontrolled single-patient design, and the specific protocol, including point selection, frequency, and treatment dose, has not been systematically optimized.

Nevertheless, the case gains plausibility from a growing body of mechanistic work on electroacupuncture and tendon biology. In a rat model of Achilles tendon rupture, researchers found that electroacupuncture increased fibroblast proliferation, collagen synthesis, and the mechanical strength of healing tendons. Separate animal work on rotator cuff injury reported reduced levels of the inflammatory cytokines interleukin-1 beta and tumor necrosis factor alpha, alongside increased anti-inflammatory interleukin-10, potentially creating a more favorable environment for repair. Other studies have shown that electroacupuncture modulates matrix metalloproteinase activity, enhancing extracellular matrix remodeling, and that electrical stimulation more broadly promotes cellular migration, local blood flow, and growth factor production in connective tissue. The 5-hertz frequency used in this case aligns with research suggesting that low-frequency stimulation optimally triggers endorphin and growth factor release relevant to tissue repair.

Where the case fits into the broader evidence base remains an open question. Prior trials of acupuncture for shoulder pain have generally addressed mixed etiologies rather than imaging-confirmed rotator cuff tears, though meta-analytic evidence suggests acupuncture adds benefit to exercise-based physical therapy compared with exercise alone, and conventional non-operative care for small supraspinatus tears typically yields satisfactory outcomes in roughly seventy-five percent of patients, but over three to six months and with residual symptoms common. The authors call for randomized controlled trials comparing electroacupuncture against standard conservative care and sham acupuncture, incorporating both clinical and imaging endpoints, exploring dose-response relationships, and correlating biomarkers of tissue healing with outcomes to identify likely responders. Until such studies exist, this single nurse’s recovery, from eight-out-of-ten pain and a nine-millimeter tear to zero pain and a four-millimeter residual defect, stands as an intriguing, rigorously documented hypothesis generator rather than a practice-changing result, and a reminder that even ancient techniques can still surprise modern imaging.

Subject of Research: Electroacupuncture treatment of partial-thickness supraspinatus tendon tears

Article Title: Therapeutic Effects of Electroacupuncture on Partial‐Thickness Supraspinatus Tear: Clinical Case Report

Article References: Hajvalie, G., Takamjani, I. E., Sarrafzadeh, J., Saremi, H., & Asadi, M. R. (2026). Therapeutic Effects of Electroacupuncture on Partial‐Thickness Supraspinatus Tear: Clinical Case Report. Clinical Case Reports, 14(10), Article e73685. https://doi.org/10.1002/ccr3.73685

Image Credits: AI Generated

DOI: 10.1002/ccr3.73685

Keywords: electroacupuncture, supraspinatus tear, rotator cuff, shoulder pain, tendon healing, MRI, case report, physical therapy, DASH score, regenerative medicine, musculoskeletal disorders, Therapeutic

The study, published in BMC Medical Imaging by a multidisciplinary group from Xinjiang Medical University and its Sixth Affiliated Hospital, introduces a model called WEM-Mamba, short for Wavelet-Enhanced MedMamba. The work sits at the intersection of two of the hottest trends in medical deep learning: state space models, the efficient new architecture family that includes Mamba, and frequency domain analysis, which extracts information about textures and edges that spatial-domain models often overlook. According to the authors, most existing approaches, whether convolutional neural networks, vision transformers, or earlier Mamba variants, concentrate almost exclusively on modeling features in the spatial domain, leaving the rich frequency content of medical images underexploited. For a task like rotator cuff classification, where subtle textural signatures in the radiograph may hint at tendon damage, that omission could mean losing exactly the evidence that matters most.

To understand why frequency matters, it helps to think about what an X-ray actually encodes. Radiographs are dense grids of intensity values, and while clinicians read them as pictures of bones and soft tissue shadows, mathematically they can be decomposed into components that vary at different spatial scales and orientations. Fine, rapidly changing patterns correspond to high-frequency content such as edges and fine texture; smooth, slowly varying patterns correspond to low-frequency content such as broad anatomical structures. The Haar wavelet transform, a classical mathematical tool that dates back decades, provides a principled way to split an image into these frequency bands while keeping the spatial location of each feature intact. WEM-Mamba exploits this by embedding a Haar wavelet decomposition step directly inside its core processing module, so the network can examine the image simultaneously through spatial and frequency lenses.

Technically, the framework builds on MedMamba, a medical imaging variant of the Mamba architecture. Mamba and its relatives are built on state space models, which process sequences, including sequences of image patches, using recurrent-style computations that scale linearly with input length rather than quadratically as attention mechanisms in transformers do. That efficiency makes state space models attractive for medical imaging, where high-resolution images and limited training data are the norm. The researchers’ key innovation is the Wavelet-Enhanced SS-Conv-SSM module, or WESS. In this module, an input feature map is decomposed by the Haar wavelet transform into multiple frequency sub-bands. These sub-bands are processed and then synergistically fused with the global context modeling that the state space model provides, before an inverse wavelet transform can reconstruct the enhanced representation. The result is a hybrid design in which convolutional operations capture local detail, the state space model captures long-range dependencies across the image, and the wavelet pathway injects multi-band frequency features that neither of the other two components would extract on their own.

The team evaluated WEM-Mamba on a dataset of shoulder X-ray images collected retrospectively from routine clinical examinations at the Sixth Affiliated Hospital of Xinjiang Medical University, with ethics approval and anonymized patient data. They benchmarked their model against fifteen representative competitors spanning the major architecture families: convolutional neural networks, transformers, multi-layer perceptrons, and Mamba variants. WEM-Mamba came out on top, achieving an accuracy of 0.8950, an F1-score of 0.9309, a precision of 0.9078, a recall of 0.9552, and an area under the curve of 0.9116. Notably, the recall figure, which measures how many true tears the model successfully flags, is the highest of its headline metrics, a property that matters greatly in screening contexts where missed diagnoses carry the greatest cost. Equally important for real-world deployment, the model is compact: it contains 14.92 million parameters and requires only 2.04 gigafloating-point operations per inference, a footprint modest enough to run on ordinary clinical hardware rather than specialized computing clusters.

The performance-to-cost ratio is one of the study’s most compelling aspects. Deep learning models in medical imaging have often chased accuracy at the expense of size and speed, producing architectures too heavy for the very hospitals that need them most. By combining the linear-scaling efficiency of state space models with the lightweight Haar wavelet transform, the authors demonstrate that careful architectural design, rather than brute-force scale, can deliver strong classification performance on modest computational budgets. For clinics in underserved regions, where shoulder X-rays are already the first-line examination but specialist radiology expertise may be scarce, a compact model that augments the initial radiograph with a tear probability estimate could meaningfully accelerate referrals for MRI and definitive treatment.

The research also carries a broader message for the machine learning community. Wavelet-based feature extraction has a long pedigree in signal processing and image compression, but it has been somewhat eclipsed in the deep learning era by purely learned representations. The success of WEM-Mamba suggests that classical mathematical transforms and modern sequence models are not rivals but complements. The wavelet decomposition imposes a physically meaningful inductive bias, telling the network explicitly where the fine textures and edges live, while the state space model supplies the flexible global reasoning that fixed transforms cannot. In domains where training data are limited, as is nearly always the case in medicine, building such structural knowledge into the architecture may prove more data-efficient than expecting a generic network to rediscover it from scratch.

Caveats remain, and the authors are candid about them. The study was conducted on a single-center dataset, and all conclusions are explicitly framed as valid under the data and experimental settings of this particular investigation. The researchers state that further validation on larger-scale, multi-center, and external datasets is required before the approach can be considered robust, and that the clinical application value of the framework needs continued assessment in subsequent research. Single-center datasets can encode site-specific scanner settings, patient demographics, and imaging protocols, all of which can inflate apparent performance when a model is tested on data from the same source. Multi-center trials with external test sets are the standard next step for any diagnostic AI aspiring to clinical use, and this work is no exception.

Nevertheless, the study represents a thoughtful and timely contribution to computer-aided diagnosis of musculoskeletal injuries. It addresses a genuine clinical bottleneck, the gap between cheap first-line X-rays and definitive but costly MRI, with a method that is technically novel, computationally lean, and empirically competitive. The work was supported by a range of Chinese research funding programs, including the National Natural Science Foundation of China and multiple Xinjiang regional initiatives, and the article is published open access, making the full technical details available to researchers worldwide. If the promised multi-center validation bears out the single-center results, wavelet-enhanced state space models like WEM-Mamba could become a standard tool in the radiology toolbox, helping ensure that a patient’s first, cheapest image is not the last word on their shoulder pain.

Subject of Research: A wavelet-enhanced Mamba-based deep learning framework for classifying rotator cuff tears in shoulder X-ray images

Article Title: WEM-Mamba: a Wavelet-Enhanced MedMamba framework for rotator cuff tear classification in X-ray images

Article References: Wang, Z., Liu, Z., Li, J., Aboduaini, Y., Abulaiti, A., Li, S., Yakufu, M., Halike, A., Xv, L., & Li, G. (2026). WEM-Mamba: a Wavelet-Enhanced MedMamba framework for rotator cuff tear classification in X-ray images. BMC Medical Imaging. https://doi.org/10.1186/s12880-026-02740-2

Image Credits: AI Generated

DOI: 10.1186/s12880-026-02740-2

Keywords: rotator cuff tear, deep learning, Mamba, state space model, wavelet transform, frequency domain features, X-ray imaging, medical image classification, computer-aided diagnosis, shoulder pain, MedMamba, BMC Medical Imaging

The study was designed as an analytical cross-sectional survey, a snapshot approach that captures a population at a single point in time. Researchers from Bacha Khan Medical College in Mardan, Ayub Medical College in Abbottabad, and COMSATS University in Islamabad recruited medical and dental undergraduates across Khyber Pakhtunkhwa and administered a structured questionnaire combining demographic questions with three validated instruments. The Smartphone Addiction Scale-Short Version, known as SAS-SV, was used to classify participants into low and high addiction risk categories. Upper extremity disability was measured with the QuickDASH questionnaire, an abbreviated version of the Disabilities of the Arm, Shoulder and Hand tool widely used in orthopedic research. Pain intensity was recorded using the Verbal Rating Scale, or VRS. All data were analyzed in SPSS version 27.0.

The numbers that emerged were striking. High addiction risk users reported significantly higher daily use, higher SAS-SV scores, and higher QuickDASH scores, with all three comparisons reaching a statistical significance level of p less than .001. In practical terms, students flagged as high risk were not merely using their phones more; they were also reporting substantially more difficulty performing tasks with their arms, shoulders, and hands, from lifting objects to managing fine motor activities. The QuickDASH instrument scores functional limitation across a range of everyday activities, so elevated scores among heavy users suggest that phone-related strain is beginning to interfere with real-world function, not just producing occasional aches.

When the researchers examined pain by body region, the pattern sharpened. Musculoskeletal pain was more frequent among high risk users overall, and the differences were statistically significant for two specific sites: the shoulder, with a p value of .042, and the wrist and hand, with a p value of .043. These are precisely the anatomical regions that biomechanical models of smartphone use would predict. Holding a phone for extended periods requires sustained contraction of the trapezius and shoulder stabilizers, often with the arm elevated and the neck flexed forward. Meanwhile, the thumb and wrist endure repetitive flexion and extension as users scroll and type, loading tendons and joints in ways that mirror the mechanisms behind tendinopathy and repetitive strain injuries long documented in keyboard workers.

To untangle which factors independently predicted pain, the team turned to logistic regression, a statistical technique that estimates the odds of an outcome while controlling for other variables. Among high addiction risk users, age, gender, daily hours of use, perceived impact of the phone on daily life, and SAS-SV scores were all significantly associated with pain in multiple body regions. In the low risk group, the picture was narrower: only SAS-V scores and pain at selected sites, specifically the lower back and wrist, showed significant associations. This asymmetry suggests that once smartphone use reaches the high risk range, its physical consequences spread across the body, whereas in moderate users the effects remain more localized and closely tied to the addiction score itself.

Disability, as measured by QuickDASH, followed its own distinct pattern. In low risk users, disability scores were significantly associated with SAS-SV scores and elbow pain. In high risk users, however, the significant associations shifted to female gender and the presence of pain at multiple sites. The gender finding deserves attention. Previous research on digital device ergonomics has repeatedly found that women report more musculoskeletal symptoms from device use, potentially due to differences in hand size relative to device dimensions, wrist geometry, muscle strength, and pain sensitivity. That female gender emerged as a significant correlate of disability specifically in the high risk group hints that heavy phone use may amplify pre-existing anatomical and physiological vulnerabilities.

The study’s setting gives its findings particular weight. Medical students face a double burden: the academic demands of their training, which involve long hours of reading and screen work, and the near-universal smartphone dependence of their generation. In Pakistan, as elsewhere, phones have become the primary portal for study materials, social connection, and entertainment. The researchers note that smartphone addiction has emerged as a growing public health concern among university students and is linked to poor posture and repetitive movements, habits that contribute to pain in the neck, shoulders, and upper extremities. If future physicians are accumulating musculoskeletal damage before they even begin clinical practice, the implications extend beyond individual health to the resilience of the healthcare workforce itself.

The study was approved by the Institutional Review Board of Bacha Khan Medical College Mardan under reference number 796/BKMC, and written informed consent was obtained from all participants before enrollment. The authors declare no competing interests and received no financial support for the work. As an open access publication, the article is available to researchers, clinicians, and educators worldwide, and its early-release status means the citable version of record will follow with further edits.

Cross-sectional designs have inherent limits, and the authors’ own framing is careful. Because exposure and outcome are measured simultaneously, such studies can establish association but not definitive causation; it remains possible that students in pain turn to their phones more, or that shared underlying factors drive both. Self-reported scales also depend on honest and accurate recall. Nevertheless, the consistency of the findings with prior work, including earlier cross-sectional studies linking smartphone overuse to neck and wrist pain in medical and nursing undergraduates and to pain among college students more broadly, strengthens the case that the relationship is real and clinically meaningful.

The authors’ conclusion points toward prevention rather than alarm. High addiction risk users among medical students, they write, are significantly associated with musculoskeletal pain and upper extremity disability, especially in the shoulders and wrists, and preventive strategies such as ergonomic education, early screening, and awareness are essential to reduce these health risks. In practice, that could mean teaching students neutral wrist positioning and regular micro-breaks, integrating posture awareness into medical curricula, and using brief screening tools like the SAS-SV to identify heavy users before pain becomes chronic. For a generation whose hands rarely leave their screens, the study is a reminder that the most common medical instrument many future doctors will ever hold is the one already in their palm, and that it, too, deserves to be used with care.

Subject of Research: Smartphone addiction risk and its association with musculoskeletal pain and upper extremity disability among medical students

Article Title: Musculoskeletal pain and upper extremity disability in relation to smartphone addiction risk among medical students of Khyber Pakhtunkhwa

Article References: Maaz, M., Ullah, M., Tahir, M., Amir, S., Khan, M. H., & Ahmad, M. (2026). Musculoskeletal pain and upper extremity disability in relation to smartphone addiction risk among medical students of Khyber Pakhtunkhwa. Discover Social Science and Health, 6(1), Article 112. https://doi.org/10.1007/s44155-026-00450-2

Image Credits: AI Generated

DOI: 10.1007/s44155-026-00450-2

Keywords: smartphone addiction, musculoskeletal pain, upper extremity disability, medical students, QuickDASH, SAS-SV, shoulder pain, wrist pain, ergonomics, cross-sectional study, Pakistan, public health